diff --git a/High Throughput Algae Cell Detection/Dataset/DATASET.md b/High Throughput Algae Cell Detection/Dataset/DATASET.md
new file mode 100644
index 000000000..f2b0d4a30
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Dataset/DATASET.md	
@@ -0,0 +1,50 @@
+# [VisAlgae 2023 Challenge Dataset](https://www.kaggle.com/datasets/marquis03/high-throughput-algae-cell-detection?select=train) 🌿🔬
+
+## Overview
+
+Microalgae play a vital role in various fields, including marine environments, biomedical research, clean energy, and food engineering. Monitoring the abundance and species composition of microalgae is crucial for identifying environmental issues and maintaining ecological balance. The VisAlgae 2023 Challenge Dataset addresses the need for a high-throughput, multi-classification, and multi-scale microalgae cell detection method using microfluidic chip technology.
+
+## Dataset Description 📊
+
+### Objective
+The dataset aims to facilitate the development of object detection algorithms for high-throughput algae cell detection. The challenges include detecting small targets, handling multiscale issues, managing motion blur, dealing with complex backgrounds, and maximizing detection accuracy.
+
+### Microfluidic Platform 💧
+Experiments were conducted on a high-throughput microfluidic platform, capturing dynamic video data of microalgal cells under different fields of view and imaging conditions.
+
+### Algal Cell Types 🦠
+The dataset comprises six types of microalgal cells:
+
+- Platymonas (Class 0)
+- Chlorella (Class 1)
+- Dunaliella salina (Class 2)
+- Effrenium (Class 3)
+- Porphyridium (Class 4)
+- Haematococcus (Class 5)
+
+### Data Split 📂
+- Training Set: 700 images
+- Testing Set: 300 images
+
+### Annotation Format 🗒️
+Annotations for the training set are provided in YOLO format, with each image having a corresponding .txt file. The format for each line in the .txt file is as follows:
+
+```
+Class, x_center, y_center, w, h
+```
+
+### Classes 📋
+- 0: Platymonas
+- 1: Chlorella
+- 2: Dunaliella salina
+- 3: Effrenium
+- 4: Porphyridium
+- 5: Haematococcus
+
+## VisAlgae Challenge and Workshop 🚀
+
+The dataset is part of the second International "Vision Meets Algae" (VisAlgae) Challenge and Workshop, held in conjunction with the IEEE Cybermatics Conference. Researchers and developers are invited to participate in the challenge to address practical issues in high-throughput algae cell detection. The dataset provides a real-world scenario for developing innovative object detection algorithms that can contribute to the advancement of microalgae research and ecological protection.
+
+## Acknowledgments 🙌
+
+This dataset is made possible by the collaborative efforts of the organizers of VisAlgae 2023 and contributors to microalgae research. We encourage participants to explore creative solutions and contribute to the development of tools that will enhance ecological protection and resource management in the field of microalgae research. 🌍🔍
\ No newline at end of file
diff --git a/High Throughput Algae Cell Detection/Dataset/labels.csv b/High Throughput Algae Cell Detection/Dataset/labels.csv
new file mode 100644
index 000000000..80c59c011
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Dataset/labels.csv	
@@ -0,0 +1,1759 @@
+,image,Class,x_center,y_center,w,h
+0,00001.txt,4,0.2510504201680672,0.3462171052631578,0.0220588235294117,0.0608552631578947
+1,00001.txt,4,0.3358718487394957,0.8552631578947368,0.0194327731092436,0.0657894736842105
+2,00001.txt,3,0.2660189075630252,0.8774671052631579,0.0267857142857142,0.0641447368421052
+3,00002.txt,2,0.5727415966386554,0.8486842105263157,0.025735294117647,0.069078947368421
+4,00002.txt,1,0.6625525210084033,0.131578947368421,0.0089285714285714,0.0263157894736842
+5,00002.txt,1,0.1139705882352941,0.8215460526315789,0.0084033613445378,0.0246710526315789
+6,00003.txt,2,0.5580357142857143,0.4975328947368421,0.0194327731092436,0.0707236842105263
+7,00003.txt,2,0.3511029411764705,0.1537828947368421,0.0215336134453781,0.0674342105263157
+8,00003.txt,4,0.573266806722689,0.4013157894736842,0.0183823529411764,0.0592105263157894
+9,00003.txt,2,0.4424894957983193,0.8643092105263157,0.0215336134453781,0.0608552631578947
+10,00003.txt,1,0.7870273109243697,0.5731907894736842,0.0089285714285714,0.03125
+11,00004.txt,0,0.6313025210084033,0.8544407894736842,0.042016806722689,0.0838815789473684
+12,00004.txt,3,0.1323529411764706,0.537828947368421,0.0315126050420168,0.0789473684210526
+13,00004.txt,1,0.8167016806722689,0.2828947368421052,0.0115546218487394,0.0361842105263157
+14,00005.txt,0,0.2439600840336134,0.8338815789473684,0.0309873949579831,0.0986842105263157
+15,00005.txt,0,0.2014180672268907,0.850328947368421,0.0267857142857142,0.1019736842105263
+16,00006.txt,1,0.0123424369747899,0.3865131578947368,0.0110294117647058,0.0361842105263157
+17,00006.txt,1,0.0157563025210084,0.4629934210526315,0.0115546218487394,0.03125
+18,00006.txt,1,0.103203781512605,0.763157894736842,0.0099789915966386,0.0296052631578947
+19,00006.txt,4,0.8789390756302521,0.6743421052631579,0.0173319327731092,0.0493421052631578
+20,00006.txt,2,0.7166491596638656,0.731907894736842,0.0215336134453781,0.0526315789473684
+21,00006.txt,3,0.9826680672268908,0.5016447368421052,0.0273109243697479,0.0756578947368421
+22,00007.txt,1,0.111344537815126,0.5830592105263157,0.0147058823529411,0.037828947368421
+23,00007.txt,1,0.1131827731092437,0.6439144736842105,0.0099789915966386,0.0279605263157894
+24,00007.txt,0,0.1410189075630252,0.6085526315789473,0.0299369747899159,0.0888157894736842
+25,00007.txt,1,0.4115021008403361,0.5115131578947368,0.0099789915966386,0.0296052631578947
+26,00007.txt,1,0.6281512605042017,0.7615131578947368,0.009453781512605,0.0296052631578947
+27,00008.txt,1,0.2329306722689075,0.6340460526315789,0.0110294117647058,0.0345394736842105
+28,00008.txt,1,0.8629201680672268,0.5460526315789473,0.0126050420168067,0.0394736842105263
+29,00008.txt,2,0.8868172268907563,0.3108552631578947,0.0246848739495798,0.0592105263157894
+30,00008.txt,3,0.945640756302521,0.1620065789473684,0.025735294117647,0.0904605263157894
+31,00008.txt,4,0.3466386554621848,0.763157894736842,0.0220588235294117,0.0657894736842105
+32,00009.txt,5,0.1927521008403361,0.2746710526315789,0.0451680672268907,0.125
+33,00009.txt,4,0.58140756302521,0.5526315789473684,0.0126050420168067,0.0361842105263157
+34,00010.txt,1,0.2586659663865546,0.3462171052631578,0.0110294117647058,0.0345394736842105
+35,00010.txt,5,0.5404411764705882,0.856907894736842,0.0336134453781512,0.0921052631578947
+36,00011.txt,2,0.470063025210084,0.4251644736842105,0.0210084033613445,0.0411184210526315
+37,00011.txt,4,0.5735294117647058,0.3791118421052631,0.0220588235294117,0.0674342105263157
+38,00011.txt,3,0.6336659663865546,0.8404605263157894,0.025735294117647,0.0855263157894736
+39,00012.txt,1,0.0856092436974789,0.3939144736842105,0.009453781512605,0.03125
+40,00012.txt,1,0.2321428571428571,0.4851973684210526,0.009453781512605,0.0263157894736842
+41,00012.txt,4,0.1218487394957983,0.4695723684210526,0.0210084033613445,0.0608552631578947
+42,00012.txt,4,0.9230567226890756,0.5148026315789473,0.0120798319327731,0.0394736842105263
+43,00012.txt,2,0.3403361344537815,0.6924342105263157,0.0262605042016806,0.0526315789473684
+44,00012.txt,3,0.5527836134453781,0.8371710526315789,0.0320378151260504,0.0723684210526315
+45,00013.txt,0,0.4128151260504201,0.4547697368421052,0.01890756302521,0.1036184210526315
+46,00013.txt,3,0.7179621848739496,0.8338815789473684,0.0220588235294117,0.0888157894736842
+47,00013.txt,1,0.8146008403361344,0.0583881578947368,0.0105042016806722,0.03125
+48,00014.txt,2,0.9831932773109244,0.6233552631578947,0.0273109243697479,0.0559210526315789
+49,00014.txt,3,0.9797794117647058,0.6768092105263157,0.0309873949579831,0.0740131578947368
+50,00014.txt,1,0.7867647058823529,0.841282894736842,0.009453781512605,0.03125
+51,00014.txt,1,0.7161239495798319,0.2014802631578947,0.0099789915966386,0.03125
+52,00014.txt,1,0.5619747899159664,0.4276315789473684,0.0105042016806722,0.0328947368421052
+53,00014.txt,4,0.7977941176470588,0.4152960526315789,0.0220588235294117,0.0674342105263157
+54,00015.txt,1,0.1165966386554621,0.6652960526315789,0.0105042016806722,0.03125
+55,00015.txt,1,0.229516806722689,0.9235197368421052,0.0084033613445378,0.0246710526315789
+56,00015.txt,1,0.4761029411764705,0.9177631578947368,0.0078781512605042,0.0230263157894736
+57,00015.txt,2,0.8195903361344538,0.1307565789473684,0.0225840336134453,0.0641447368421052
+58,00016.txt,1,0.1872373949579832,0.1192434210526315,0.0141806722689075,0.0411184210526315
+59,00016.txt,1,0.5932247899159664,0.2993421052631578,0.0131302521008403,0.0427631578947368
+60,00016.txt,1,0.694327731092437,0.3733552631578947,0.0105042016806722,0.0361842105263157
+61,00016.txt,3,0.5848214285714285,0.8700657894736842,0.0299369747899159,0.0789473684210526
+62,00016.txt,4,0.4191176470588235,0.7713815789473684,0.0241596638655462,0.0723684210526315
+63,00017.txt,0,0.0693277310924369,0.6134868421052632,0.0378151260504201,0.0986842105263157
+64,00017.txt,3,0.0782563025210084,0.350328947368421,0.0273109243697479,0.0756578947368421
+65,00017.txt,1,0.8080357142857143,0.5139802631578947,0.0099789915966386,0.0345394736842105
+66,00017.txt,1,0.986344537815126,0.1233552631578947,0.0157563025210084,0.0460526315789473
+67,00018.txt,5,0.8802521008403361,0.5370065789473684,0.0504201680672268,0.1299342105263158
+68,00019.txt,5,0.8240546218487395,0.4202302631578947,0.0588235294117647,0.1726973684210526
+69,00019.txt,4,0.5929621848739496,0.4407894736842105,0.0231092436974789,0.069078947368421
+70,00019.txt,1,0.152048319327731,0.1282894736842105,0.0120798319327731,0.0328947368421052
+71,00020.txt,1,0.4910714285714285,0.381578947368421,0.009453781512605,0.0328947368421052
+72,00020.txt,1,0.5877100840336135,0.5814144736842105,0.0126050420168067,0.03125
+73,00020.txt,1,0.4508928571428571,0.3075657894736842,0.0131302521008403,0.0394736842105263
+74,00020.txt,1,0.0945378151260504,0.2902960526315789,0.0115546218487394,0.03125
+75,00020.txt,1,0.3991596638655462,0.8297697368421052,0.0115546218487394,0.0345394736842105
+76,00021.txt,1,0.1273634453781512,0.5896381578947368,0.0110294117647058,0.0345394736842105
+77,00021.txt,1,0.1783088235294117,0.1184210526315789,0.0099789915966386,0.0328947368421052
+78,00021.txt,1,0.7991071428571428,0.5180921052631579,0.0110294117647058,0.0361842105263157
+79,00022.txt,5,0.8734243697478992,0.5863486842105263,0.0462184873949579,0.1595394736842105
+80,00022.txt,3,0.966123949579832,0.6011513157894737,0.0309873949579831,0.0904605263157894
+81,00022.txt,1,0.464548319327731,0.544407894736842,0.0099789915966386,0.0328947368421052
+82,00022.txt,1,0.5254726890756303,0.7047697368421052,0.0078781512605042,0.0279605263157894
+83,00023.txt,5,0.2408088235294117,0.5394736842105263,0.0603991596638655,0.1381578947368421
+84,00023.txt,1,0.5955882352941176,0.6833881578947368,0.0105042016806722,0.03125
+85,00023.txt,2,0.9464285714285714,0.2648026315789473,0.0294117647058823,0.0592105263157894
+86,00023.txt,2,0.8188025210084033,0.7088815789473684,0.0178571428571428,0.0789473684210526
+87,00023.txt,4,0.9774159663865546,0.5353618421052632,0.0252100840336134,0.0740131578947368
+88,00024.txt,2,0.1748949579831932,0.3396381578947368,0.0346638655462184,0.0509868421052631
+89,00024.txt,1,0.2158613445378151,0.4300986842105262,0.0105042016806722,0.03125
+90,00024.txt,1,0.313813025210084,0.2664473684210526,0.0078781512605042,0.0263157894736842
+91,00024.txt,1,0.7182247899159664,0.2277960526315789,0.0141806722689075,0.0411184210526315
+92,00024.txt,4,0.8637079831932772,0.8445723684210525,0.0225840336134453,0.0674342105263157
+93,00025.txt,2,0.7040441176470588,0.4185855263157894,0.0225840336134453,0.0707236842105263
+94,00025.txt,3,0.6402310924369747,0.700657894736842,0.0262605042016806,0.0756578947368421
+95,00026.txt,2,0.4553571428571428,0.4769736842105262,0.0241596638655462,0.0460526315789473
+96,00026.txt,2,0.8476890756302521,0.5074013157894737,0.0220588235294117,0.0838815789473684
+97,00027.txt,5,0.1163340336134453,0.265625,0.0530462184873949,0.1694078947368421
+98,00027.txt,1,0.4051995798319328,0.2894736842105263,0.0089285714285714,0.0296052631578947
+99,00027.txt,1,0.8492647058823529,0.3388157894736842,0.0084033613445378,0.0263157894736842
+100,00028.txt,2,0.720063025210084,0.8453947368421052,0.0283613445378151,0.0657894736842105
+101,00028.txt,2,0.0874474789915966,0.1266447368421052,0.0204831932773109,0.0723684210526315
+102,00028.txt,1,0.3135504201680672,0.6439144736842105,0.0136554621848739,0.037828947368421
+103,00028.txt,3,0.4952731092436974,0.5394736842105263,0.0273109243697479,0.0888157894736842
+104,00029.txt,3,0.1486344537815126,0.6200657894736842,0.0252100840336134,0.0855263157894736
+105,00029.txt,1,0.523109243697479,0.1546052631578947,0.0105042016806722,0.0328947368421052
+106,00029.txt,0,0.6893382352941176,0.2993421052631578,0.0309873949579831,0.0822368421052631
+107,00029.txt,1,0.4267331932773109,0.7557565789473684,0.0089285714285714,0.0246710526315789
+108,00029.txt,1,0.7599789915966386,0.8560855263157894,0.009453781512605,0.0246710526315789
+109,00029.txt,2,0.8130252100840336,0.6167763157894737,0.0231092436974789,0.0493421052631578
+110,00030.txt,1,0.2830882352941176,0.2475328947368421,0.0126050420168067,0.0345394736842105
+111,00030.txt,1,0.5207457983193277,0.2105263157894736,0.0110294117647058,0.0296052631578947
+112,00030.txt,3,0.6586134453781513,0.1759868421052631,0.0273109243697479,0.0822368421052631
+113,00030.txt,5,0.6693802521008403,0.8116776315789473,0.048844537815126,0.1266447368421052
+114,00030.txt,1,0.9818802521008404,0.7911184210526315,0.0099789915966386,0.0263157894736842
+115,00031.txt,4,0.1021533613445378,0.3108552631578947,0.0215336134453781,0.0625
+116,00031.txt,3,0.1207983193277311,0.4342105263157894,0.0252100840336134,0.0625
+117,00031.txt,2,0.8125,0.6101973684210525,0.0210084033613445,0.0493421052631578
+118,00031.txt,1,0.9519432773109244,0.2450657894736842,0.0120798319327731,0.0361842105263157
+119,00032.txt,0,0.9690126050420168,0.2672697368421052,0.0378151260504201,0.0904605263157894
+120,00032.txt,1,0.4372373949579832,0.6217105263157895,0.0131302521008403,0.0394736842105263
+121,00033.txt,1,0.6625525210084033,0.1702302631578947,0.0120798319327731,0.03125
+122,00033.txt,3,0.5173319327731092,0.3100328947368421,0.0273109243697479,0.0838815789473684
+123,00033.txt,1,0.6919642857142857,0.5805921052631579,0.0194327731092436,0.0526315789473684
+124,00033.txt,4,0.9642857142857142,0.7590460526315789,0.0220588235294117,0.0641447368421052
+125,00033.txt,4,0.2804621848739496,0.5419407894736842,0.0241596638655462,0.0740131578947368
+126,00034.txt,5,0.1628151260504201,0.3700657894736842,0.042016806722689,0.131578947368421
+127,00034.txt,1,0.9566701680672268,0.3009868421052631,0.0141806722689075,0.0427631578947368
+128,00034.txt,1,0.7896533613445378,0.1924342105263158,0.0099789915966386,0.0328947368421052
+129,00034.txt,4,0.6636029411764706,0.7277960526315789,0.0204831932773109,0.0608552631578947
+130,00035.txt,2,0.1478466386554622,0.6060855263157895,0.0288865546218487,0.0542763157894736
+131,00035.txt,1,0.1202731092436974,0.522203947368421,0.0126050420168067,0.037828947368421
+132,00035.txt,2,0.6869747899159664,0.1184210526315789,0.0231092436974789,0.0723684210526315
+133,00035.txt,4,0.8392857142857143,0.765625,0.0231092436974789,0.0707236842105263
+134,00035.txt,3,0.9724264705882352,0.3511513157894737,0.0320378151260504,0.0805921052631579
+135,00036.txt,5,0.3736869747899159,0.4078947368421052,0.0656512605042016,0.2105263157894736
+136,00036.txt,1,0.6583508403361344,0.1842105263157894,0.0110294117647058,0.0361842105263157
+137,00037.txt,5,0.759453781512605,0.6422697368421052,0.065126050420168,0.1924342105263158
+138,00038.txt,2,0.6039915966386554,0.897203947368421,0.0294117647058823,0.0608552631578947
+139,00038.txt,1,0.7612920168067226,0.7886513157894737,0.0120798319327731,0.0411184210526315
+140,00038.txt,1,0.6376050420168067,0.9169407894736842,0.009453781512605,0.0246710526315789
+141,00038.txt,1,0.1011029411764705,0.5962171052631579,0.0110294117647058,0.03125
+142,00039.txt,2,0.6084558823529411,0.359375,0.0267857142857142,0.0805921052631579
+143,00039.txt,1,0.0485819327731092,0.8421052631578947,0.0089285714285714,0.0263157894736842
+144,00040.txt,0,0.1843487394957983,0.5583881578947368,0.0388655462184873,0.0838815789473684
+145,00040.txt,3,0.0667016806722689,0.5707236842105263,0.0273109243697479,0.0953947368421052
+146,00040.txt,1,0.4831932773109244,0.859375,0.009453781512605,0.0345394736842105
+147,00040.txt,4,0.5580357142857143,0.3330592105263157,0.016281512605042,0.0476973684210526
+148,00040.txt,1,0.0386029411764705,0.6578947368421052,0.0110294117647058,0.0361842105263157
+149,00041.txt,1,0.4574579831932773,0.6578947368421052,0.009453781512605,0.0296052631578947
+150,00041.txt,1,0.2833508403361344,0.6348684210526315,0.0099789915966386,0.0328947368421052
+151,00041.txt,4,0.0330882352941176,0.4152960526315789,0.0220588235294117,0.0674342105263157
+152,00041.txt,1,0.8048844537815125,0.1340460526315789,0.0089285714285714,0.03125
+153,00041.txt,1,0.8140756302521008,0.1332236842105263,0.0073529411764705,0.0296052631578947
+154,00042.txt,3,0.2347689075630252,0.3643092105263157,0.032563025210084,0.0707236842105263
+155,00042.txt,2,0.8897058823529411,0.5427631578947368,0.0252100840336134,0.0526315789473684
+156,00042.txt,4,0.4159663865546218,0.8314144736842105,0.0220588235294117,0.0674342105263157
+157,00042.txt,4,0.6919642857142857,0.7606907894736842,0.0225840336134453,0.0707236842105263
+158,00042.txt,1,0.6165966386554621,0.6455592105263157,0.0126050420168067,0.037828947368421
+159,00042.txt,1,0.8064600840336134,0.3462171052631578,0.0089285714285714,0.0213815789473684
+160,00043.txt,2,0.2360819327731092,0.6324013157894737,0.0215336134453781,0.0542763157894736
+161,00043.txt,4,0.6252626050420168,0.3601973684210526,0.0183823529411764,0.0526315789473684
+162,00043.txt,1,0.9600840336134452,0.4391447368421052,0.0147058823529411,0.0427631578947368
+163,00043.txt,3,0.9327731092436974,0.2689144736842105,0.0210084033613445,0.0674342105263157
+164,00043.txt,3,0.9159663865546218,0.2911184210526316,0.0252100840336134,0.0756578947368421
+165,00043.txt,1,0.759453781512605,0.4309210526315789,0.0105042016806722,0.0328947368421052
+166,00044.txt,0,0.4353991596638655,0.4539473684210526,0.0336134453781512,0.0756578947368421
+167,00044.txt,3,0.2980567226890756,0.4136513157894737,0.0309873949579831,0.0773026315789473
+168,00045.txt,0,0.7859768907563025,0.6685855263157895,0.0351890756302521,0.0904605263157894
+169,00045.txt,4,0.90625,0.5995065789473684,0.0246848739495798,0.0707236842105263
+170,00046.txt,5,0.6210609243697479,0.653782894736842,0.0677521008403361,0.1990131578947368
+171,00046.txt,1,0.5409663865546218,0.147203947368421,0.0115546218487394,0.0345394736842105
+172,00046.txt,2,0.3421743697478991,0.8733552631578947,0.0131302521008403,0.0592105263157894
+173,00046.txt,2,0.9852941176470588,0.4662828947368421,0.0157563025210084,0.0575657894736842
+174,00047.txt,5,0.9246323529411764,0.7804276315789473,0.0519957983193277,0.1365131578947368
+175,00048.txt,0,0.7308298319327731,0.4662828947368421,0.0351890756302521,0.0904605263157894
+176,00048.txt,2,0.7431722689075629,0.6504934210526315,0.0178571428571428,0.0608552631578947
+177,00049.txt,0,0.1927521008403361,0.3404605263157894,0.0283613445378151,0.0789473684210526
+178,00049.txt,0,0.5569852941176471,0.6883223684210525,0.0404411764705882,0.0904605263157894
+179,00049.txt,5,0.5023634453781513,0.2006578947368421,0.0414915966386554,0.131578947368421
+180,00049.txt,1,0.3453256302521008,0.3059210526315789,0.0099789915966386,0.0263157894736842
+181,00050.txt,0,0.9519432773109244,0.2023026315789473,0.039390756302521,0.0953947368421052
+182,00050.txt,1,0.9571953781512604,0.6792763157894737,0.0099789915966386,0.0263157894736842
+183,00050.txt,1,0.9065126050420168,0.4876644736842105,0.0126050420168067,0.0345394736842105
+184,00051.txt,2,0.2547268907563025,0.4819078947368421,0.0304621848739495,0.0526315789473684
+185,00051.txt,3,0.2297794117647058,0.4629934210526315,0.0309873949579831,0.0904605263157894
+186,00051.txt,3,0.7003676470588235,0.3667763157894737,0.0267857142857142,0.0822368421052631
+187,00052.txt,2,0.2935924369747899,0.740953947368421,0.0199579831932773,0.0740131578947368
+188,00052.txt,2,0.6376050420168067,0.71875,0.0157563025210084,0.0723684210526315
+189,00052.txt,1,0.8673844537815125,0.8371710526315789,0.0110294117647058,0.0328947368421052
+190,00053.txt,2,0.0506827731092437,0.5164473684210527,0.0288865546218487,0.0427631578947368
+191,00053.txt,2,0.7985819327731092,0.4934210526315789,0.0236344537815126,0.0657894736842105
+192,00053.txt,1,0.6980042016806722,0.6504934210526315,0.0147058823529411,0.0444078947368421
+193,00053.txt,3,0.9214810924369748,0.1858552631578947,0.0299369747899159,0.0888157894736842
+194,00054.txt,5,0.387079831932773,0.850328947368421,0.0346638655462184,0.1052631578947368
+195,00054.txt,3,0.2384453781512605,0.6661184210526315,0.0252100840336134,0.0986842105263157
+196,00054.txt,3,0.4579831932773109,0.653782894736842,0.0283613445378151,0.0740131578947368
+197,00054.txt,4,0.1756827731092436,0.6052631578947368,0.0183823529411764,0.0493421052631578
+198,00055.txt,0,0.927783613445378,0.569078947368421,0.0383403361344537,0.0986842105263157
+199,00055.txt,1,0.8839285714285714,0.3832236842105262,0.0157563025210084,0.0427631578947368
+200,00055.txt,1,0.7447478991596639,0.7598684210526315,0.0136554621848739,0.0296052631578947
+201,00055.txt,1,0.214548319327731,0.6398026315789473,0.0110294117647058,0.0328947368421052
+202,00055.txt,1,0.0850840336134453,0.6981907894736842,0.009453781512605,0.03125
+203,00055.txt,1,0.0417542016806722,0.1998355263157894,0.0099789915966386,0.0279605263157894
+204,00056.txt,5,0.5336134453781513,0.606907894736842,0.0462184873949579,0.1480263157894736
+205,00056.txt,2,0.4430147058823529,0.6587171052631579,0.0267857142857142,0.0575657894736842
+206,00056.txt,1,0.8873424369747899,0.2294407894736842,0.0089285714285714,0.0279605263157894
+207,00057.txt,2,0.3579306722689075,0.7779605263157894,0.0246848739495798,0.0756578947368421
+208,00057.txt,4,0.0456932773109243,0.3569078947368421,0.0220588235294117,0.0625
+209,00057.txt,3,0.9558823529411764,0.4539473684210526,0.0273109243697479,0.0789473684210526
+210,00057.txt,3,0.9051995798319328,0.3955592105263157,0.0278361344537815,0.0970394736842105
+211,00057.txt,1,0.7605042016806722,0.4745065789473684,0.009453781512605,0.0279605263157894
+212,00058.txt,1,0.0070903361344537,0.2886513157894737,0.0120798319327731,0.0345394736842105
+213,00058.txt,1,0.1961659663865546,0.1620065789473684,0.0099789915966386,0.03125
+214,00058.txt,1,0.6097689075630252,0.694078947368421,0.0084033613445378,0.0263157894736842
+215,00058.txt,1,0.4984243697478991,0.6365131578947368,0.009453781512605,0.0263157894736842
+216,00058.txt,0,0.604516806722689,0.3741776315789473,0.0357142857142857,0.09375
+217,00058.txt,4,0.828781512605042,0.453125,0.0231092436974789,0.0707236842105263
+218,00058.txt,1,0.8797268907563025,0.1324013157894736,0.0084033613445378,0.0246710526315789
+219,00059.txt,5,0.14390756302521,0.1825657894736842,0.0430672268907563,0.1447368421052631
+220,00059.txt,5,0.8815651260504201,0.2804276315789473,0.048844537815126,0.1430921052631578
+221,00059.txt,2,0.9453781512605042,0.1521381578947368,0.0262605042016806,0.0773026315789473
+222,00059.txt,3,0.1875,0.4449013157894737,0.0304621848739495,0.0740131578947368
+223,00059.txt,1,0.6554621848739496,0.2705592105263157,0.0147058823529411,0.0476973684210526
+224,00060.txt,2,0.0572478991596638,0.3898026315789473,0.0220588235294117,0.0493421052631578
+225,00060.txt,2,0.1470588235294117,0.0921052631578947,0.0241596638655462,0.0559210526315789
+226,00060.txt,1,0.125,0.4169407894736842,0.0105042016806722,0.0279605263157894
+227,00060.txt,1,0.2670693277310924,0.1537828947368421,0.0131302521008403,0.0476973684210526
+228,00061.txt,5,0.8621323529411764,0.4152960526315789,0.0498949579831932,0.1595394736842105
+229,00061.txt,1,0.9789915966386554,0.4152960526315789,0.0126050420168067,0.037828947368421
+230,00061.txt,4,0.4204306722689075,0.4333881578947368,0.0204831932773109,0.0608552631578947
+231,00062.txt,1,0.3416491596638655,0.5353618421052632,0.0152310924369747,0.0411184210526315
+232,00062.txt,3,0.3602941176470588,0.4473684210526315,0.0283613445378151,0.0789473684210526
+233,00062.txt,2,0.9327731092436974,0.4300986842105262,0.0283613445378151,0.0542763157894736
+234,00062.txt,1,0.8463760504201681,0.6274671052631579,0.0131302521008403,0.0411184210526315
+235,00062.txt,2,0.726890756302521,0.4481907894736842,0.01890756302521,0.0509868421052631
+236,00063.txt,0,0.2780987394957983,0.3643092105263157,0.0435924369747899,0.0871710526315789
+237,00063.txt,1,0.0890231092436974,0.2368421052631578,0.0183823529411764,0.0460526315789473
+238,00063.txt,1,0.6066176470588235,0.3725328947368421,0.0105042016806722,0.0345394736842105
+239,00063.txt,4,0.945640756302521,0.4136513157894737,0.0236344537815126,0.0641447368421052
+240,00064.txt,0,0.7310924369747899,0.803453947368421,0.0336134453781512,0.0871710526315789
+241,00064.txt,0,0.6368172268907563,0.1702302631578947,0.039390756302521,0.1299342105263158
+242,00064.txt,4,0.8067226890756303,0.6842105263157894,0.01890756302521,0.0460526315789473
+243,00064.txt,4,0.2998949579831932,0.8536184210526315,0.0199579831932773,0.0592105263157894
+244,00064.txt,1,0.1822478991596638,0.71875,0.0126050420168067,0.0361842105263157
+245,00065.txt,5,0.0317752100840336,0.4013157894736842,0.0635504201680672,0.1907894736842105
+246,00065.txt,4,0.6016281512605042,0.3042763157894737,0.0267857142857142,0.0789473684210526
+247,00065.txt,1,0.7891281512605042,0.553453947368421,0.016281512605042,0.0476973684210526
+248,00066.txt,5,0.9009978991596638,0.7327302631578947,0.0625,0.1759868421052631
+249,00066.txt,4,0.5372899159663865,0.3174342105263157,0.0220588235294117,0.0723684210526315
+250,00066.txt,1,0.2008928571428571,0.2113486842105263,0.0194327731092436,0.0542763157894736
+251,00067.txt,0,0.8946953781512604,0.1866776315789473,0.0362394957983193,0.1101973684210526
+252,00067.txt,1,0.936186974789916,0.3001644736842105,0.0194327731092436,0.0542763157894736
+253,00067.txt,4,0.0858718487394958,0.350328947368421,0.025735294117647,0.0756578947368421
+254,00068.txt,1,0.8889180672268907,0.2919407894736842,0.0099789915966386,0.03125
+255,00068.txt,1,0.8474264705882353,0.4917763157894737,0.0141806722689075,0.0427631578947368
+256,00068.txt,3,0.9330357142857142,0.6513157894736842,0.0225840336134453,0.0657894736842105
+257,00068.txt,4,0.14390756302521,0.2105263157894736,0.0220588235294117,0.069078947368421
+258,00068.txt,1,0.1945903361344537,0.6217105263157895,0.0120798319327731,0.0394736842105263
+259,00069.txt,5,0.1633403361344537,0.7615131578947368,0.0399159663865546,0.125
+260,00069.txt,4,0.2983193277310924,0.1381578947368421,0.0199579831932773,0.0657894736842105
+261,00070.txt,0,0.4577205882352941,0.6101973684210525,0.0309873949579831,0.069078947368421
+262,00070.txt,1,0.7565651260504201,0.4481907894736842,0.0120798319327731,0.037828947368421
+263,00071.txt,1,0.1286764705882352,0.3675986842105262,0.0115546218487394,0.037828947368421
+264,00071.txt,1,0.1512605042016806,0.8108552631578947,0.0147058823529411,0.0427631578947368
+265,00071.txt,1,0.1415441176470588,0.8338815789473684,0.0120798319327731,0.0394736842105263
+266,00071.txt,1,0.7106092436974789,0.6817434210526315,0.0115546218487394,0.0345394736842105
+267,00071.txt,1,0.725577731092437,0.1019736842105263,0.0099789915966386,0.0263157894736842
+268,00071.txt,3,0.418329831932773,0.381578947368421,0.0236344537815126,0.069078947368421
+269,00071.txt,4,0.4133403361344537,0.3157894736842105,0.0252100840336134,0.069078947368421
+270,00071.txt,4,0.6662289915966386,0.3314144736842105,0.0204831932773109,0.0641447368421052
+271,00072.txt,5,0.251313025210084,0.5871710526315789,0.0519957983193277,0.1447368421052631
+272,00072.txt,4,0.1980042016806722,0.4226973684210526,0.0231092436974789,0.069078947368421
+273,00072.txt,1,0.235031512605042,0.1151315789473684,0.0110294117647058,0.0328947368421052
+274,00072.txt,1,0.6365546218487395,0.319078947368421,0.0168067226890756,0.0493421052631578
+275,00072.txt,1,0.8306197478991596,0.653782894736842,0.0120798319327731,0.0411184210526315
+276,00072.txt,2,0.5848214285714285,0.1143092105263157,0.0183823529411764,0.0773026315789473
+277,00072.txt,1,0.4842436974789916,0.5345394736842105,0.0084033613445378,0.0296052631578947
+278,00072.txt,1,0.7434348739495797,0.8601973684210525,0.0068277310924369,0.0230263157894736
+279,00073.txt,2,0.9109768907563024,0.3075657894736842,0.0236344537815126,0.069078947368421
+280,00073.txt,4,0.3828781512605042,0.5213815789473684,0.0262605042016806,0.0723684210526315
+281,00073.txt,1,0.2079831932773109,0.5518092105263157,0.0126050420168067,0.037828947368421
+282,00073.txt,1,0.3135504201680672,0.921875,0.0115546218487394,0.03125
+283,00073.txt,1,0.5223214285714286,0.8042763157894737,0.0089285714285714,0.0263157894736842
+284,00073.txt,1,0.4191176470588235,0.765625,0.0105042016806722,0.0279605263157894
+285,00074.txt,2,0.1998424369747899,0.8930921052631579,0.0246848739495798,0.069078947368421
+286,00074.txt,2,0.7744222689075629,0.6677631578947368,0.025735294117647,0.0657894736842105
+287,00074.txt,3,0.9054621848739496,0.6858552631578947,0.0273109243697479,0.0756578947368421
+288,00074.txt,1,0.6055672268907563,0.1891447368421052,0.0073529411764705,0.0230263157894736
+289,00074.txt,1,0.5632878151260504,0.1282894736842105,0.0089285714285714,0.0263157894736842
+290,00075.txt,1,0.2539390756302521,0.1661184210526315,0.0110294117647058,0.0361842105263157
+291,00075.txt,2,0.5157563025210083,0.3725328947368421,0.0220588235294117,0.037828947368421
+292,00075.txt,4,0.4272584033613445,0.6891447368421052,0.0183823529411764,0.0559210526315789
+293,00075.txt,4,0.6305147058823529,0.5189144736842105,0.0215336134453781,0.0641447368421052
+294,00075.txt,1,0.1591386554621848,0.5550986842105263,0.0157563025210084,0.0476973684210526
+295,00076.txt,5,0.5677521008403361,0.25,0.0756302521008403,0.2236842105263157
+296,00076.txt,4,0.2022058823529411,0.2129934210526315,0.0220588235294117,0.0707236842105263
+297,00076.txt,1,0.2421218487394958,0.8684210526315789,0.0126050420168067,0.0394736842105263
+298,00076.txt,1,0.0858718487394958,0.7845394736842105,0.0099789915966386,0.0296052631578947
+299,00076.txt,1,0.4120273109243697,0.7870065789473684,0.0131302521008403,0.0345394736842105
+300,00077.txt,3,0.5099789915966386,0.2623355263157894,0.0294117647058823,0.0773026315789473
+301,00077.txt,3,0.6095063025210083,0.412828947368421,0.0278361344537815,0.0789473684210526
+302,00077.txt,3,0.9569327731092436,0.5657894736842105,0.0262605042016806,0.069078947368421
+303,00077.txt,1,0.3193277310924369,0.8840460526315789,0.0126050420168067,0.0345394736842105
+304,00078.txt,1,0.5249474789915967,0.2763157894736842,0.0120798319327731,0.0394736842105263
+305,00078.txt,4,0.4839810924369748,0.203125,0.0215336134453781,0.0641447368421052
+306,00078.txt,5,0.6168592436974789,0.756578947368421,0.0530462184873949,0.1282894736842105
+307,00079.txt,0,0.4789915966386554,0.7524671052631579,0.0304621848739495,0.1069078947368421
+308,00079.txt,3,0.3014705882352941,0.756578947368421,0.0294117647058823,0.0822368421052631
+309,00080.txt,2,0.9766281512605042,0.2228618421052631,0.0351890756302521,0.0444078947368421
+310,00080.txt,4,0.6998424369747899,0.1570723684210526,0.0215336134453781,0.0773026315789473
+311,00080.txt,4,0.421218487394958,0.825657894736842,0.0231092436974789,0.0625
+312,00080.txt,3,0.4445903361344537,0.8421052631578947,0.0278361344537815,0.0723684210526315
+313,00080.txt,1,0.7712710084033613,0.4967105263157894,0.0131302521008403,0.0394736842105263
+314,00080.txt,1,0.213235294117647,0.2557565789473684,0.0105042016806722,0.0279605263157894
+315,00081.txt,1,0.6278886554621849,0.3519736842105262,0.0141806722689075,0.0394736842105263
+316,00081.txt,0,0.0391281512605042,0.4662828947368421,0.0383403361344537,0.0838815789473684
+317,00082.txt,2,0.7851890756302521,0.7820723684210525,0.0178571428571428,0.0805921052631579
+318,00082.txt,4,0.580094537815126,0.6546052631578947,0.0204831932773109,0.0625
+319,00082.txt,3,0.8295693277310924,0.872532894736842,0.0288865546218487,0.0871710526315789
+320,00083.txt,1,0.1938025210084033,0.6990131578947368,0.0115546218487394,0.0328947368421052
+321,00083.txt,1,0.3629201680672269,0.6669407894736842,0.009453781512605,0.0279605263157894
+322,00083.txt,1,0.5283613445378151,0.4300986842105262,0.0084033613445378,0.0279605263157894
+323,00084.txt,1,0.2668067226890756,0.4383223684210526,0.0084033613445378,0.0279605263157894
+324,00084.txt,1,0.2886029411764705,0.8174342105263157,0.0089285714285714,0.0296052631578947
+325,00084.txt,1,0.6302521008403361,0.6768092105263157,0.0115546218487394,0.037828947368421
+326,00085.txt,0,0.9611344537815124,0.8379934210526315,0.032563025210084,0.100328947368421
+327,00085.txt,1,0.5819327731092436,0.4333881578947368,0.0105042016806722,0.037828947368421
+328,00085.txt,4,0.2689075630252101,0.6916118421052632,0.0241596638655462,0.0707236842105263
+329,00086.txt,0,0.2959558823529412,0.2976973684210526,0.0215336134453781,0.0723684210526315
+330,00086.txt,0,0.2872899159663865,0.3207236842105262,0.0210084033613445,0.0756578947368421
+331,00086.txt,2,0.1838235294117647,0.6578947368421052,0.0199579831932773,0.0559210526315789
+332,00086.txt,1,0.5480567226890756,0.819078947368421,0.0120798319327731,0.0361842105263157
+333,00086.txt,1,0.306985294117647,0.8519736842105262,0.0131302521008403,0.0394736842105263
+334,00086.txt,3,0.585609243697479,0.2902960526315789,0.0273109243697479,0.0740131578947368
+335,00086.txt,4,0.6917016806722689,0.8552631578947368,0.0220588235294117,0.069078947368421
+336,00087.txt,3,0.3802521008403361,0.7245065789473684,0.0315126050420168,0.0773026315789473
+337,00087.txt,3,0.7573529411764706,0.575657894736842,0.0294117647058823,0.069078947368421
+338,00087.txt,4,0.7563025210084033,0.6373355263157895,0.0241596638655462,0.0707236842105263
+339,00088.txt,2,0.5740546218487395,0.3026315789473684,0.0283613445378151,0.0526315789473684
+340,00088.txt,4,0.6517857142857143,0.6027960526315789,0.01890756302521,0.0542763157894736
+341,00088.txt,1,0.1680672268907563,0.4309210526315789,0.0115546218487394,0.0296052631578947
+342,00089.txt,2,0.6155462184873949,0.631578947368421,0.0241596638655462,0.0427631578947368
+343,00089.txt,4,0.3377100840336134,0.7425986842105263,0.0199579831932773,0.0575657894736842
+344,00089.txt,3,0.4112394957983193,0.1143092105263157,0.0231092436974789,0.0838815789473684
+345,00089.txt,5,0.0821953781512605,0.4144736842105262,0.0330882352941176,0.0953947368421052
+346,00090.txt,2,0.4422268907563025,0.8741776315789473,0.0283613445378151,0.0707236842105263
+347,00090.txt,3,0.5635504201680672,0.653782894736842,0.032563025210084,0.0871710526315789
+348,00091.txt,0,0.2736344537815126,0.6833881578947368,0.0315126050420168,0.0970394736842105
+349,00091.txt,3,0.97531512605042,0.459703947368421,0.0336134453781512,0.1036184210526315
+350,00091.txt,1,0.9501050420168068,0.7080592105263157,0.0126050420168067,0.037828947368421
+351,00092.txt,5,0.7405462184873949,0.7590460526315789,0.0346638655462184,0.0970394736842105
+352,00092.txt,2,0.6234243697478992,0.8684210526315789,0.0231092436974789,0.0493421052631578
+353,00093.txt,1,0.4023109243697478,0.1546052631578947,0.0105042016806722,0.0296052631578947
+354,00093.txt,1,0.6365546218487395,0.131578947368421,0.009453781512605,0.0296052631578947
+355,00093.txt,1,0.5525210084033613,0.5797697368421052,0.0105042016806722,0.03125
+356,00093.txt,4,0.5278361344537815,0.7779605263157894,0.0168067226890756,0.0493421052631578
+357,00093.txt,2,0.9669117647058824,0.8273026315789473,0.0241596638655462,0.0657894736842105
+358,00094.txt,2,0.9009978991596638,0.3527960526315789,0.0173319327731092,0.0641447368421052
+359,00094.txt,2,0.3973214285714285,0.1422697368421052,0.0225840336134453,0.0575657894736842
+360,00094.txt,1,0.6037289915966386,0.131578947368421,0.0120798319327731,0.0427631578947368
+361,00095.txt,1,0.4960609243697478,0.1389802631578947,0.0099789915966386,0.0345394736842105
+362,00095.txt,1,0.6520483193277311,0.5164473684210527,0.0099789915966386,0.0296052631578947
+363,00095.txt,3,0.8734243697478992,0.8799342105263157,0.0294117647058823,0.0888157894736842
+364,00096.txt,2,0.3424369747899159,0.8782894736842105,0.0199579831932773,0.0493421052631578
+365,00096.txt,0,0.4779411764705882,0.4547697368421052,0.0304621848739495,0.0871710526315789
+366,00097.txt,3,0.2652310924369748,0.4712171052631578,0.0273109243697479,0.0575657894736842
+367,00097.txt,4,0.1318277310924369,0.3338815789473684,0.0178571428571428,0.0559210526315789
+368,00097.txt,1,0.3348214285714285,0.2047697368421052,0.0089285714285714,0.03125
+369,00097.txt,1,0.3455882352941176,0.1924342105263158,0.009453781512605,0.0296052631578947
+370,00097.txt,1,0.3534663865546218,0.2162828947368421,0.009453781512605,0.0279605263157894
+371,00098.txt,1,0.7169117647058824,0.5411184210526315,0.009453781512605,0.0328947368421052
+372,00098.txt,1,0.5070903361344538,0.5337171052631579,0.0152310924369747,0.0411184210526315
+373,00098.txt,4,0.4847689075630252,0.7171052631578947,0.0199579831932773,0.0559210526315789
+374,00098.txt,4,0.626313025210084,0.7245065789473684,0.0225840336134453,0.0740131578947368
+375,00099.txt,2,0.2765231092436974,0.3404605263157894,0.0267857142857142,0.0559210526315789
+376,00099.txt,1,0.0320378151260504,0.834703947368421,0.0147058823529411,0.0444078947368421
+377,00100.txt,2,0.8771008403361344,0.3988486842105262,0.0178571428571428,0.0509868421052631
+378,00100.txt,4,0.1389180672268907,0.4991776315789473,0.0225840336134453,0.0674342105263157
+379,00100.txt,4,0.3820903361344537,0.3963815789473684,0.0194327731092436,0.0592105263157894
+380,00100.txt,3,0.3755252100840336,0.34375,0.0262605042016806,0.0723684210526315
+381,00100.txt,1,0.5575105042016807,0.5123355263157895,0.0078781512605042,0.0279605263157894
+382,00101.txt,5,0.1496848739495798,0.6167763157894737,0.0756302521008403,0.2664473684210526
+383,00101.txt,3,0.3426995798319328,0.5855263157894737,0.0278361344537815,0.0756578947368421
+384,00101.txt,1,0.2801995798319328,0.912828947368421,0.0131302521008403,0.0394736842105263
+385,00102.txt,1,0.9532563025210083,0.3223684210526316,0.009453781512605,0.0328947368421052
+386,00102.txt,1,0.6234243697478992,0.5814144736842105,0.0168067226890756,0.0411184210526315
+387,00102.txt,1,0.3027836134453781,0.5148026315789473,0.0152310924369747,0.0493421052631578
+388,00102.txt,1,0.3400735294117646,0.1143092105263157,0.0099789915966386,0.0279605263157894
+389,00102.txt,3,0.1341911764705882,0.7080592105263157,0.0278361344537815,0.0740131578947368
+390,00103.txt,0,0.3907563025210084,0.4350328947368421,0.0304621848739495,0.0871710526315789
+391,00103.txt,3,0.0648634453781512,0.3215460526315789,0.0288865546218487,0.0970394736842105
+392,00104.txt,2,0.2728466386554621,0.3453947368421052,0.0236344537815126,0.0493421052631578
+393,00104.txt,4,0.1370798319327731,0.8717105263157894,0.01890756302521,0.0559210526315789
+394,00105.txt,2,0.2534138655462185,0.2606907894736842,0.0225840336134453,0.0476973684210526
+395,00105.txt,1,0.2326680672268907,0.7911184210526315,0.0178571428571428,0.0493421052631578
+396,00105.txt,1,0.5446428571428571,0.537828947368421,0.0136554621848739,0.0460526315789473
+397,00106.txt,5,0.8324579831932772,0.5945723684210525,0.0472689075630252,0.1726973684210526
+398,00106.txt,2,0.8017331932773109,0.7072368421052632,0.0267857142857142,0.0592105263157894
+399,00106.txt,1,0.569327731092437,0.0978618421052631,0.0115546218487394,0.0345394736842105
+400,00106.txt,1,0.7045693277310924,0.3264802631578947,0.0120798319327731,0.03125
+401,00107.txt,3,0.0990021008403361,0.203125,0.0278361344537815,0.100328947368421
+402,00107.txt,1,0.4637605042016806,0.0863486842105263,0.0105042016806722,0.03125
+403,00107.txt,4,0.4621848739495798,0.7269736842105263,0.0241596638655462,0.0789473684210526
+404,00107.txt,4,0.5945378151260504,0.1932565789473684,0.0210084033613445,0.0674342105263157
+405,00108.txt,5,0.9608718487394956,0.819078947368421,0.0593487394957983,0.2072368421052631
+406,00108.txt,4,0.7069327731092436,0.2705592105263157,0.0231092436974789,0.0707236842105263
+407,00109.txt,2,0.9663865546218487,0.15625,0.0199579831932773,0.0526315789473684
+408,00109.txt,0,0.9640231092436974,0.2787828947368421,0.0309873949579831,0.0838815789473684
+409,00109.txt,4,0.9372373949579832,0.5427631578947368,0.0236344537815126,0.0723684210526315
+410,00109.txt,1,0.4199054621848739,0.7985197368421052,0.0120798319327731,0.0345394736842105
+411,00109.txt,1,0.5301995798319328,0.1060855263157894,0.0099789915966386,0.03125
+412,00109.txt,1,0.6607142857142857,0.0649671052631579,0.0084033613445378,0.0213815789473684
+413,00110.txt,0,0.3933823529411764,0.3157894736842105,0.0294117647058823,0.0953947368421052
+414,00110.txt,4,0.0853466386554621,0.3273026315789473,0.025735294117647,0.0723684210526315
+415,00110.txt,2,0.0572478991596638,0.8166118421052632,0.0210084033613445,0.0740131578947368
+416,00110.txt,3,0.91281512605042,0.6751644736842105,0.032563025210084,0.100328947368421
+417,00111.txt,2,0.3030462184873949,0.7771381578947368,0.0252100840336134,0.0608552631578947
+418,00111.txt,4,0.376313025210084,0.825657894736842,0.0236344537815126,0.0723684210526315
+419,00112.txt,5,0.1743697478991596,0.6143092105263157,0.0525210084033613,0.1661184210526315
+420,00112.txt,1,0.6754201680672268,0.2368421052631578,0.009453781512605,0.0263157894736842
+421,00112.txt,1,0.7886029411764706,0.1570723684210526,0.0078781512605042,0.0279605263157894
+422,00112.txt,2,0.5317752100840336,0.7055921052631579,0.0204831932773109,0.0559210526315789
+423,00113.txt,1,0.235031512605042,0.65625,0.0131302521008403,0.0394736842105263
+424,00113.txt,1,0.6076680672268907,0.1167763157894736,0.0105042016806722,0.0296052631578947
+425,00114.txt,1,0.5504201680672268,0.2952302631578947,0.0126050420168067,0.037828947368421
+426,00114.txt,1,0.7074579831932772,0.881578947368421,0.0136554621848739,0.0427631578947368
+427,00114.txt,1,0.7405462184873949,0.763157894736842,0.0105042016806722,0.0328947368421052
+428,00115.txt,1,0.5128676470588235,0.2220394736842105,0.0110294117647058,0.0361842105263157
+429,00115.txt,1,0.1079306722689075,0.3511513157894737,0.0099789915966386,0.0279605263157894
+430,00115.txt,4,0.8421743697478992,0.7508223684210525,0.0225840336134453,0.0641447368421052
+431,00116.txt,5,0.601890756302521,0.4786184210526315,0.0409663865546218,0.1085526315789473
+432,00116.txt,1,0.3469012605042016,0.6332236842105263,0.0099789915966386,0.0296052631578947
+433,00117.txt,1,0.0485819327731092,0.7713815789473684,0.0141806722689075,0.0427631578947368
+434,00117.txt,3,0.9487920168067226,0.6208881578947368,0.0267857142857142,0.0871710526315789
+435,00118.txt,1,0.4829306722689075,0.8042763157894737,0.0152310924369747,0.0460526315789473
+436,00118.txt,1,0.0874474789915966,0.6175986842105263,0.0110294117647058,0.037828947368421
+437,00118.txt,2,0.6704306722689075,0.2557565789473684,0.016281512605042,0.0641447368421052
+438,00118.txt,2,0.8161764705882353,0.5995065789473684,0.0168067226890756,0.037828947368421
+439,00119.txt,4,0.2111344537815126,0.3865131578947368,0.0220588235294117,0.0625
+440,00119.txt,1,0.1271008403361344,0.9070723684210524,0.0126050420168067,0.037828947368421
+441,00119.txt,1,0.7783613445378151,0.2006578947368421,0.009453781512605,0.0263157894736842
+442,00119.txt,3,0.4952731092436974,0.5682565789473684,0.0315126050420168,0.0904605263157894
+443,00120.txt,2,0.6491596638655462,0.8042763157894737,0.0178571428571428,0.0427631578947368
+444,00120.txt,1,0.8461134453781513,0.9004934210526315,0.0126050420168067,0.037828947368421
+445,00120.txt,4,0.8686974789915966,0.6480263157894737,0.0231092436974789,0.069078947368421
+446,00120.txt,3,0.5926995798319328,0.2393092105263157,0.0225840336134453,0.0641447368421052
+447,00120.txt,3,0.5772058823529411,0.2730263157894737,0.0262605042016806,0.0756578947368421
+448,00121.txt,2,0.6176470588235294,0.522203947368421,0.0262605042016806,0.0707236842105263
+449,00121.txt,3,0.707720588235294,0.4925986842105262,0.0246848739495798,0.0707236842105263
+450,00121.txt,4,0.4080882352941176,0.1504934210526315,0.0210084033613445,0.0641447368421052
+451,00122.txt,1,0.8991596638655461,0.7417763157894737,0.0115546218487394,0.0361842105263157
+452,00122.txt,1,0.634453781512605,0.6620065789473684,0.009453781512605,0.0279605263157894
+453,00122.txt,2,0.2423844537815126,0.6768092105263157,0.0246848739495798,0.0674342105263157
+454,00123.txt,0,0.1420693277310924,0.8536184210526315,0.0404411764705882,0.0888157894736842
+455,00123.txt,1,0.1294642857142857,0.7302631578947368,0.0131302521008403,0.0427631578947368
+456,00123.txt,1,0.297531512605042,0.6258223684210525,0.0131302521008403,0.0411184210526315
+457,00123.txt,1,0.3017331932773109,0.3018092105263157,0.0141806722689075,0.0411184210526315
+458,00124.txt,0,0.8637079831932772,0.2713815789473684,0.0341386554621848,0.0822368421052631
+459,00125.txt,4,0.6047794117647058,0.6825657894736842,0.0141806722689075,0.0427631578947368
+460,00125.txt,4,0.25,0.5180921052631579,0.0136554621848739,0.0361842105263157
+461,00125.txt,1,0.08140756302521,0.0838815789473684,0.009453781512605,0.0328947368421052
+462,00126.txt,1,0.0344012605042016,0.5460526315789473,0.0110294117647058,0.0328947368421052
+463,00126.txt,0,0.0632878151260504,0.5246710526315789,0.0236344537815126,0.0723684210526315
+464,00126.txt,3,0.0984768907563025,0.5427631578947368,0.0236344537815126,0.0855263157894736
+465,00126.txt,3,0.6835609243697479,0.4185855263157894,0.0194327731092436,0.0575657894736842
+466,00127.txt,0,0.6869747899159664,0.390625,0.032563025210084,0.0871710526315789
+467,00127.txt,5,0.680672268907563,0.1636513157894736,0.0346638655462184,0.09375
+468,00127.txt,1,0.0370273109243697,0.9300986842105262,0.0120798319327731,0.0345394736842105
+469,00127.txt,1,0.2024684873949579,0.3955592105263157,0.0099789915966386,0.037828947368421
+470,00128.txt,1,0.3999474789915966,0.924342105263158,0.0089285714285714,0.0296052631578947
+471,00128.txt,1,0.547531512605042,0.897203947368421,0.0099789915966386,0.0279605263157894
+472,00128.txt,1,0.7179621848739496,0.7491776315789473,0.0115546218487394,0.037828947368421
+473,00129.txt,3,0.4241071428571428,0.796875,0.025735294117647,0.0904605263157894
+474,00129.txt,3,0.6607142857142857,0.1233552631578947,0.0231092436974789,0.0822368421052631
+475,00129.txt,1,0.3616071428571428,0.1554276315789473,0.0110294117647058,0.037828947368421
+476,00129.txt,1,0.110031512605042,0.6241776315789473,0.0131302521008403,0.0411184210526315
+477,00130.txt,1,0.024422268907563,0.6455592105263157,0.0110294117647058,0.0411184210526315
+478,00130.txt,3,0.0391281512605042,0.6521381578947368,0.0236344537815126,0.0773026315789473
+479,00130.txt,4,0.2991071428571428,0.4777960526315789,0.0173319327731092,0.0575657894736842
+480,00130.txt,1,0.4099264705882353,0.6085526315789473,0.0089285714285714,0.0328947368421052
+481,00130.txt,4,0.8973214285714285,0.3092105263157894,0.0152310924369747,0.0493421052631578
+482,00130.txt,4,0.9847689075630252,0.1546052631578947,0.0262605042016806,0.0789473684210526
+483,00131.txt,3,0.5196953781512604,0.6899671052631579,0.0299369747899159,0.0838815789473684
+484,00131.txt,3,0.6604516806722689,0.3766447368421052,0.0246848739495798,0.0789473684210526
+485,00131.txt,1,0.4288340336134453,0.4662828947368421,0.0120798319327731,0.03125
+486,00131.txt,1,0.0863970588235294,0.7870065789473684,0.0110294117647058,0.0279605263157894
+487,00131.txt,1,0.0099789915966386,0.669407894736842,0.0115546218487394,0.0328947368421052
+488,00131.txt,1,0.017594537815126,0.897203947368421,0.0099789915966386,0.0246710526315789
+489,00132.txt,1,0.040703781512605,0.4210526315789473,0.0110294117647058,0.0296052631578947
+490,00132.txt,5,0.5540966386554622,0.4276315789473684,0.0430672268907563,0.1217105263157894
+491,00133.txt,2,0.9669117647058824,0.796875,0.0210084033613445,0.0674342105263157
+492,00133.txt,4,0.2552521008403361,0.6924342105263157,0.0231092436974789,0.0657894736842105
+493,00134.txt,2,0.0370273109243697,0.4490131578947368,0.0288865546218487,0.0493421052631578
+494,00134.txt,1,0.0112920168067226,0.5304276315789473,0.0110294117647058,0.0345394736842105
+495,00134.txt,4,0.0848214285714285,0.5337171052631579,0.0194327731092436,0.0575657894736842
+496,00134.txt,1,0.6478466386554621,0.2590460526315789,0.0120798319327731,0.037828947368421
+497,00134.txt,1,0.6646533613445378,0.2006578947368421,0.0099789915966386,0.0263157894736842
+498,00134.txt,1,0.4763655462184873,0.6677631578947368,0.0105042016806722,0.0328947368421052
+499,00135.txt,4,0.6662289915966386,0.4506578947368421,0.0215336134453781,0.0657894736842105
+500,00135.txt,1,0.6381302521008403,0.2746710526315789,0.0084033613445378,0.0296052631578947
+501,00135.txt,1,0.6165966386554621,0.2245065789473684,0.0084033613445378,0.0279605263157894
+502,00136.txt,2,0.0265231092436974,0.6044407894736842,0.0225840336134453,0.0476973684210526
+503,00136.txt,3,0.0522584033613445,0.6274671052631579,0.0330882352941176,0.1069078947368421
+504,00137.txt,2,0.1990546218487394,0.5246710526315789,0.0241596638655462,0.0559210526315789
+505,00137.txt,2,0.1777836134453781,0.5296052631578947,0.0225840336134453,0.0559210526315789
+506,00138.txt,0,0.8679096638655461,0.1546052631578947,0.0404411764705882,0.1282894736842105
+507,00139.txt,1,0.2355567226890756,0.4432565789473684,0.0152310924369747,0.0444078947368421
+508,00139.txt,1,0.7455357142857143,0.5402960526315789,0.0110294117647058,0.037828947368421
+509,00139.txt,1,0.7092962184873949,0.6652960526315789,0.0078781512605042,0.0246710526315789
+510,00139.txt,1,0.5225840336134454,0.3018092105263157,0.009453781512605,0.0279605263157894
+511,00140.txt,2,0.3886554621848739,0.1694078947368421,0.0252100840336134,0.0526315789473684
+512,00140.txt,4,0.3944327731092437,0.428453947368421,0.0220588235294117,0.0641447368421052
+513,00140.txt,1,0.797531512605042,0.4547697368421052,0.0120798319327731,0.037828947368421
+514,00140.txt,1,0.792016806722689,0.7450657894736842,0.0126050420168067,0.0361842105263157
+515,00140.txt,1,0.7565651260504201,0.0855263157894736,0.0099789915966386,0.0328947368421052
+516,00141.txt,5,0.7883403361344538,0.4136513157894737,0.0535714285714285,0.1529605263157894
+517,00141.txt,1,0.8581932773109243,0.2664473684210526,0.0147058823529411,0.0460526315789473
+518,00141.txt,1,0.8172268907563025,0.0912828947368421,0.0084033613445378,0.0279605263157894
+519,00141.txt,3,0.4435399159663865,0.653782894736842,0.0225840336134453,0.0773026315789473
+520,00141.txt,1,0.5454306722689075,0.4934210526315789,0.0089285714285714,0.0263157894736842
+521,00141.txt,1,0.3792016806722689,0.4292763157894737,0.009453781512605,0.0263157894736842
+522,00142.txt,5,0.3311449579831932,0.1981907894736842,0.0467436974789916,0.1726973684210526
+523,00142.txt,4,0.211922268907563,0.6858552631578947,0.0194327731092436,0.0625
+524,00143.txt,3,0.1255252100840336,0.2886513157894737,0.0294117647058823,0.0805921052631579
+525,00143.txt,2,0.6231617647058824,0.4539473684210526,0.0246848739495798,0.0657894736842105
+526,00143.txt,1,0.9301470588235292,0.2763157894736842,0.0136554621848739,0.0361842105263157
+527,00144.txt,3,0.3405987394957983,0.1800986842105263,0.0320378151260504,0.0904605263157894
+528,00144.txt,1,0.1397058823529411,0.694078947368421,0.0126050420168067,0.0328947368421052
+529,00144.txt,5,0.604516806722689,0.5090460526315789,0.0357142857142857,0.100328947368421
+530,00145.txt,0,0.1882878151260504,0.5805921052631579,0.0372899159663865,0.0789473684210526
+531,00145.txt,2,0.1533613445378151,0.7483552631578947,0.0178571428571428,0.0625
+532,00145.txt,1,0.4729516806722689,0.875,0.0131302521008403,0.0361842105263157
+533,00145.txt,1,0.4755777310924369,0.1883223684210526,0.0110294117647058,0.03125
+534,00146.txt,2,0.4871323529411764,0.6792763157894737,0.0236344537815126,0.0559210526315789
+535,00146.txt,2,0.5774684873949579,0.2310855263157894,0.0183823529411764,0.0509868421052631
+536,00146.txt,3,0.9112394957983192,0.1949013157894736,0.0273109243697479,0.0740131578947368
+537,00146.txt,4,0.0630252100840336,0.6101973684210525,0.01890756302521,0.0559210526315789
+538,00147.txt,0,0.5661764705882353,0.1957236842105263,0.032563025210084,0.1151315789473684
+539,00147.txt,1,0.4650735294117646,0.3207236842105262,0.0131302521008403,0.0361842105263157
+540,00148.txt,0,0.9046743697478992,0.2796052631578947,0.0320378151260504,0.0756578947368421
+541,00148.txt,3,0.2255777310924369,0.4942434210526315,0.0267857142857142,0.0871710526315789
+542,00149.txt,5,0.9556197478991596,0.3544407894736842,0.0730042016806722,0.2055921052631578
+543,00149.txt,1,0.9028361344537816,0.3470394736842105,0.0178571428571428,0.0526315789473684
+544,00149.txt,1,0.2100840336134453,0.6258223684210525,0.0105042016806722,0.03125
+545,00150.txt,0,0.1058298319327731,0.6077302631578947,0.0362394957983193,0.0838815789473684
+546,00150.txt,2,0.3282563025210084,0.0888157894736842,0.01890756302521,0.0592105263157894
+547,00151.txt,1,0.1872373949579832,0.6899671052631579,0.0110294117647058,0.0345394736842105
+548,00151.txt,0,0.1985294117647058,0.8338815789473684,0.0294117647058823,0.0789473684210526
+549,00151.txt,1,0.6024159663865546,0.6274671052631579,0.009453781512605,0.03125
+550,00152.txt,4,0.0879726890756302,0.8634868421052632,0.0215336134453781,0.0657894736842105
+551,00152.txt,4,0.9359243697478992,0.4901315789473684,0.0220588235294117,0.0657894736842105
+552,00152.txt,1,0.4684873949579832,0.5986842105263157,0.0115546218487394,0.0328947368421052
+553,00152.txt,1,0.9816176470588236,0.5370065789473684,0.0105042016806722,0.0279605263157894
+554,00152.txt,1,0.8970588235294117,0.5098684210526315,0.0115546218487394,0.0361842105263157
+555,00152.txt,1,0.9532563025210083,0.5838815789473684,0.0126050420168067,0.0361842105263157
+556,00153.txt,1,0.9894957983193275,0.2664473684210526,0.0136554621848739,0.0427631578947368
+557,00153.txt,2,0.4285714285714285,0.484375,0.0220588235294117,0.0641447368421052
+558,00153.txt,3,0.3834033613445378,0.4876644736842105,0.0315126050420168,0.0773026315789473
+559,00154.txt,1,0.1617647058823529,0.5518092105263157,0.0147058823529411,0.037828947368421
+560,00154.txt,1,0.4159663865546218,0.4876644736842105,0.0136554621848739,0.0345394736842105
+561,00154.txt,1,0.3949579831932773,0.303453947368421,0.0115546218487394,0.03125
+562,00154.txt,3,0.6530987394957983,0.1200657894736842,0.025735294117647,0.0723684210526315
+563,00154.txt,4,0.5932247899159664,0.772203947368421,0.0215336134453781,0.0674342105263157
+564,00154.txt,4,0.3734243697478991,0.4333881578947368,0.0210084033613445,0.0707236842105263
+565,00155.txt,0,0.2665441176470588,0.5189144736842105,0.0278361344537815,0.0707236842105263
+566,00155.txt,0,0.2857142857142857,0.5740131578947368,0.0367647058823529,0.1085526315789473
+567,00155.txt,3,0.6192226890756303,0.669407894736842,0.0315126050420168,0.0953947368421052
+568,00155.txt,1,0.9285714285714284,0.7039473684210525,0.0126050420168067,0.0361842105263157
+569,00155.txt,1,0.9737394957983192,0.8996710526315789,0.0084033613445378,0.0296052631578947
+570,00155.txt,3,0.8616071428571428,0.2516447368421052,0.0215336134453781,0.0592105263157894
+571,00155.txt,3,0.8768382352941176,0.2697368421052631,0.0288865546218487,0.0789473684210526
+572,00155.txt,3,0.8920693277310924,0.2746710526315789,0.0204831932773109,0.0657894736842105
+573,00156.txt,3,0.407563025210084,0.3889802631578947,0.0210084033613445,0.09375
+574,00156.txt,4,0.2914915966386554,0.6513157894736842,0.0168067226890756,0.0526315789473684
+575,00156.txt,4,0.4325105042016806,0.6759868421052632,0.0246848739495798,0.0723684210526315
+576,00157.txt,5,0.6089810924369747,0.8552631578947368,0.0446428571428571,0.1348684210526315
+577,00158.txt,1,0.0724789915966386,0.3939144736842105,0.0126050420168067,0.037828947368421
+578,00158.txt,1,0.2552521008403361,0.606907894736842,0.0136554621848739,0.0328947368421052
+579,00158.txt,1,0.2250525210084033,0.8519736842105262,0.0110294117647058,0.0328947368421052
+580,00158.txt,1,0.4254201680672269,0.7368421052631579,0.0115546218487394,0.0328947368421052
+581,00158.txt,1,0.4193802521008403,0.6455592105263157,0.0110294117647058,0.03125
+582,00158.txt,1,0.4151785714285714,0.6800986842105263,0.0120798319327731,0.037828947368421
+583,00158.txt,1,0.3970588235294117,0.6710526315789473,0.0105042016806722,0.0394736842105263
+584,00158.txt,1,0.3820903361344537,0.6570723684210525,0.0099789915966386,0.03125
+585,00158.txt,4,0.2618172268907563,0.5452302631578947,0.025735294117647,0.0773026315789473
+586,00159.txt,5,0.6559873949579832,0.7664473684210525,0.0451680672268907,0.0953947368421052
+587,00159.txt,3,0.8581932773109243,0.3585526315789473,0.0283613445378151,0.0756578947368421
+588,00160.txt,0,0.9732142857142856,0.53125,0.032563025210084,0.1019736842105263
+589,00160.txt,3,0.9419642857142856,0.4950657894736842,0.0299369747899159,0.0921052631578947
+590,00160.txt,1,0.7022058823529411,0.4572368421052631,0.0105042016806722,0.0361842105263157
+591,00160.txt,4,0.0617121848739495,0.5904605263157895,0.0194327731092436,0.0592105263157894
+592,00161.txt,2,0.4592962184873949,0.375,0.0299369747899159,0.0625
+593,00161.txt,1,0.3789390756302521,0.397203947368421,0.0131302521008403,0.0345394736842105
+594,00161.txt,4,0.0966386554621848,0.1636513157894736,0.0241596638655462,0.0740131578947368
+595,00162.txt,4,0.5921743697478992,0.1899671052631578,0.0225840336134453,0.0740131578947368
+596,00162.txt,1,0.0779936974789916,0.5583881578947368,0.016281512605042,0.0509868421052631
+597,00162.txt,1,0.3185399159663865,0.6858552631578947,0.0131302521008403,0.0394736842105263
+598,00162.txt,1,0.1906512605042016,0.6842105263157894,0.0105042016806722,0.0361842105263157
+599,00163.txt,0,0.5561974789915967,0.4292763157894737,0.0252100840336134,0.0855263157894736
+600,00163.txt,0,0.5840336134453781,0.4194078947368421,0.0262605042016806,0.0822368421052631
+601,00163.txt,1,0.1551995798319327,0.8955592105263157,0.0110294117647058,0.03125
+602,00163.txt,1,0.7633928571428571,0.3996710526315789,0.0120798319327731,0.0394736842105263
+603,00164.txt,1,0.5575105042016807,0.8536184210526315,0.0120798319327731,0.0361842105263157
+604,00164.txt,3,0.1402310924369748,0.1225328947368421,0.0273109243697479,0.0674342105263157
+605,00165.txt,4,0.0522584033613445,0.3601973684210526,0.0225840336134453,0.0657894736842105
+606,00165.txt,1,0.2878151260504201,0.3996710526315789,0.0115546218487394,0.0361842105263157
+607,00165.txt,1,0.3768382352941176,0.3462171052631578,0.0099789915966386,0.0279605263157894
+608,00165.txt,1,0.2678571428571428,0.9169407894736842,0.009453781512605,0.0279605263157894
+609,00166.txt,1,0.61265756302521,0.4958881578947368,0.0099789915966386,0.0345394736842105
+610,00166.txt,1,0.7618172268907563,0.9309210526315788,0.0099789915966386,0.0263157894736842
+611,00166.txt,1,0.8834033613445378,0.8848684210526315,0.0105042016806722,0.0328947368421052
+612,00167.txt,1,0.8865546218487395,0.7664473684210525,0.0126050420168067,0.0361842105263157
+613,00167.txt,2,0.5070903361344538,0.1011513157894736,0.0204831932773109,0.0641447368421052
+614,00168.txt,5,0.2686449579831932,0.3774671052631578,0.0603991596638655,0.1924342105263158
+615,00169.txt,5,0.7334558823529411,0.8289473684210525,0.0372899159663865,0.1085526315789473
+616,00169.txt,4,0.3188025210084033,0.3782894736842105,0.0262605042016806,0.0756578947368421
+617,00169.txt,4,0.9545693277310924,0.1200657894736842,0.0204831932773109,0.0625
+618,00169.txt,1,0.7765231092436975,0.5049342105263157,0.0099789915966386,0.0296052631578947
+619,00170.txt,1,0.4553571428571428,0.4268092105263157,0.0157563025210084,0.0509868421052631
+620,00170.txt,1,0.0722163865546218,0.5501644736842105,0.0141806722689075,0.0444078947368421
+621,00170.txt,2,0.2770483193277311,0.8898026315789473,0.0152310924369747,0.0592105263157894
+622,00170.txt,4,0.40625,0.7689144736842105,0.0194327731092436,0.0608552631578947
+623,00170.txt,4,0.4934348739495798,0.7294407894736842,0.0204831932773109,0.0641447368421052
+624,00170.txt,4,0.5606617647058824,0.7401315789473684,0.0215336134453781,0.069078947368421
+625,00171.txt,1,0.6601890756302521,0.2944078947368421,0.0126050420168067,0.0394736842105263
+626,00171.txt,1,0.9792542016806722,0.5,0.0099789915966386,0.0328947368421052
+627,00171.txt,1,0.631827731092437,0.8174342105263157,0.0084033613445378,0.0296052631578947
+628,00171.txt,4,0.6315651260504201,0.4983552631578947,0.0215336134453781,0.0625
+629,00172.txt,2,0.2510504201680672,0.7590460526315789,0.0168067226890756,0.0838815789473684
+630,00172.txt,4,0.0372899159663865,0.40625,0.0231092436974789,0.069078947368421
+631,00173.txt,0,0.4083508403361344,0.6636513157894737,0.0404411764705882,0.0904605263157894
+632,00173.txt,3,0.8442752100840336,0.4991776315789473,0.0278361344537815,0.0805921052631579
+633,00173.txt,1,0.798844537815126,0.8215460526315789,0.0168067226890756,0.0509868421052631
+634,00174.txt,5,0.8274684873949579,0.3297697368421052,0.0404411764705882,0.1101973684210526
+635,00174.txt,1,0.1473214285714285,0.194078947368421,0.0089285714285714,0.0296052631578947
+636,00175.txt,1,0.4375,0.5493421052631579,0.0147058823529411,0.0460526315789473
+637,00175.txt,1,0.6840861344537815,0.3856907894736842,0.0120798319327731,0.0345394736842105
+638,00175.txt,4,0.506827731092437,0.5271381578947368,0.0199579831932773,0.0575657894736842
+639,00175.txt,4,0.9532563025210083,0.15625,0.0231092436974789,0.0625
+640,00176.txt,1,0.7930672268907563,0.1118421052631578,0.0115546218487394,0.0361842105263157
+641,00176.txt,1,0.4104516806722689,0.2129934210526315,0.0110294117647058,0.0345394736842105
+642,00176.txt,1,0.4939600840336134,0.9013157894736842,0.0099789915966386,0.0296052631578947
+643,00176.txt,4,0.4787289915966386,0.850328947368421,0.0183823529411764,0.0625
+644,00177.txt,0,0.2933298319327731,0.5476973684210527,0.0299369747899159,0.0855263157894736
+645,00177.txt,0,0.1754201680672268,0.7993421052631579,0.0115546218487394,0.0328947368421052
+646,00177.txt,1,0.2321428571428571,0.1825657894736842,0.009453781512605,0.0263157894736842
+647,00177.txt,1,0.2313550420168067,0.2055921052631578,0.0089285714285714,0.0296052631578947
+648,00178.txt,2,0.5942752100840336,0.171875,0.0320378151260504,0.0608552631578947
+649,00178.txt,4,0.4698004201680672,0.2952302631578947,0.0225840336134453,0.0707236842105263
+650,00178.txt,3,0.4855567226890756,0.6578947368421052,0.0372899159663865,0.0986842105263157
+651,00179.txt,0,0.9705882352941176,0.5254934210526315,0.0241596638655462,0.0871710526315789
+652,00179.txt,0,0.6882878151260504,0.7524671052631579,0.0288865546218487,0.0838815789473684
+653,00179.txt,5,0.6583508403361344,0.2820723684210526,0.0414915966386554,0.1167763157894736
+654,00180.txt,0,0.5288865546218487,0.6809210526315789,0.0336134453781512,0.1052631578947368
+655,00180.txt,0,0.4256827731092437,0.8050986842105262,0.0225840336134453,0.09375
+656,00180.txt,0,0.3713235294117646,0.6620065789473684,0.0367647058823529,0.1036184210526315
+657,00180.txt,0,0.407563025210084,0.6644736842105263,0.0315126050420168,0.0756578947368421
+658,00180.txt,0,0.4086134453781512,0.7310855263157894,0.0262605042016806,0.0641447368421052
+659,00180.txt,0,0.4099264705882353,0.7902960526315789,0.025735294117647,0.0773026315789473
+660,00180.txt,3,0.3361344537815126,0.8009868421052632,0.0304621848739495,0.0822368421052631
+661,00180.txt,3,0.5640756302521008,0.6883223684210525,0.032563025210084,0.1134868421052631
+662,00180.txt,1,0.4558823529411764,0.2697368421052631,0.0105042016806722,0.0296052631578947
+663,00180.txt,1,0.8235294117647058,0.6521381578947368,0.0126050420168067,0.0444078947368421
+664,00181.txt,5,0.6462710084033613,0.3881578947368421,0.0603991596638655,0.1907894736842105
+665,00182.txt,1,0.9485294117647058,0.7425986842105263,0.0105042016806722,0.03125
+666,00182.txt,1,0.9464285714285714,0.7672697368421052,0.0105042016806722,0.03125
+667,00182.txt,2,0.96875,0.1776315789473684,0.0194327731092436,0.0493421052631578
+668,00182.txt,1,0.5378151260504201,0.2195723684210526,0.0178571428571428,0.0509868421052631
+669,00183.txt,1,0.1804096638655462,0.4662828947368421,0.0141806722689075,0.0476973684210526
+670,00183.txt,3,0.2134978991596638,0.3042763157894737,0.0267857142857142,0.0756578947368421
+671,00183.txt,4,0.3235294117647058,0.1332236842105263,0.0220588235294117,0.0723684210526315
+672,00183.txt,4,0.7962184873949579,0.6307565789473684,0.0231092436974789,0.0707236842105263
+673,00183.txt,1,0.9866071428571428,0.537828947368421,0.0141806722689075,0.0394736842105263
+674,00183.txt,1,0.7515756302521008,0.2582236842105263,0.009453781512605,0.0296052631578947
+675,00183.txt,5,0.7211134453781513,0.84375,0.0304621848739495,0.1085526315789473
+676,00184.txt,1,0.5832457983193277,0.5748355263157895,0.0120798319327731,0.0345394736842105
+677,00184.txt,1,0.9325105042016806,0.5814144736842105,0.0120798319327731,0.0411184210526315
+678,00184.txt,1,0.8965336134453781,0.6085526315789473,0.0073529411764705,0.0263157894736842
+679,00184.txt,3,0.9627100840336134,0.65625,0.0273109243697479,0.069078947368421
+680,00184.txt,2,0.7809873949579832,0.6916118421052632,0.0210084033613445,0.0542763157894736
+681,00184.txt,4,0.8655462184873949,0.6266447368421052,0.0210084033613445,0.069078947368421
+682,00185.txt,1,0.0661764705882353,0.4004934210526316,0.009453781512605,0.03125
+683,00185.txt,1,0.1218487394957983,0.8733552631578947,0.009453781512605,0.0263157894736842
+684,00185.txt,0,0.3337710084033613,0.4202302631578947,0.0278361344537815,0.0805921052631579
+685,00185.txt,3,0.4290966386554621,0.4777960526315789,0.0283613445378151,0.0773026315789473
+686,00186.txt,5,0.8135504201680672,0.1825657894736842,0.0430672268907563,0.125
+687,00186.txt,1,0.8214285714285714,0.3519736842105262,0.0136554621848739,0.0394736842105263
+688,00186.txt,1,0.2360819327731092,0.7557565789473684,0.0089285714285714,0.0279605263157894
+689,00187.txt,3,0.8973214285714285,0.5501644736842105,0.025735294117647,0.0674342105263157
+690,00187.txt,3,0.8802521008403361,0.6398026315789473,0.0262605042016806,0.0921052631578947
+691,00187.txt,1,0.0404411764705882,0.640625,0.0147058823529411,0.0444078947368421
+692,00187.txt,4,0.3739495798319328,0.8248355263157894,0.01890756302521,0.0707236842105263
+693,00187.txt,5,0.4571953781512605,0.2631578947368421,0.0351890756302521,0.1052631578947368
+694,00188.txt,1,0.2179621848739495,0.5723684210526315,0.0136554621848739,0.0394736842105263
+695,00188.txt,1,0.2329306722689075,0.591282894736842,0.0110294117647058,0.03125
+696,00188.txt,1,0.6922268907563025,0.4934210526315789,0.009453781512605,0.0328947368421052
+697,00188.txt,0,0.8109243697478992,0.4794407894736842,0.0294117647058823,0.0773026315789473
+698,00189.txt,1,0.0367647058823529,0.0863486842105263,0.0126050420168067,0.0411184210526315
+699,00189.txt,4,0.0354516806722689,0.194078947368421,0.0225840336134453,0.069078947368421
+700,00189.txt,0,0.0333508403361344,0.4498355263157894,0.0299369747899159,0.0904605263157894
+701,00189.txt,1,0.9396008403361344,0.606907894736842,0.0105042016806722,0.0328947368421052
+702,00190.txt,1,0.6536239495798319,0.0953947368421052,0.0131302521008403,0.0427631578947368
+703,00190.txt,1,0.8159138655462185,0.3182565789473684,0.0141806722689075,0.0476973684210526
+704,00190.txt,4,0.8689600840336134,0.3675986842105262,0.0204831932773109,0.0641447368421052
+705,00191.txt,0,0.3405987394957983,0.2944078947368421,0.0246848739495798,0.1052631578947368
+706,00191.txt,1,0.5039390756302521,0.8675986842105262,0.0204831932773109,0.0575657894736842
+707,00191.txt,1,0.7980567226890756,0.1998355263157894,0.0194327731092436,0.0608552631578947
+708,00191.txt,1,0.9164915966386554,0.5682565789473684,0.0105042016806722,0.0279605263157894
+709,00192.txt,4,0.7668067226890756,0.1430921052631578,0.0262605042016806,0.0756578947368421
+710,00192.txt,1,0.6152836134453781,0.3355263157894737,0.0131302521008403,0.0460526315789473
+711,00192.txt,1,0.6601890756302521,0.5592105263157895,0.0115546218487394,0.0296052631578947
+712,00192.txt,1,0.6449579831932772,0.5427631578947368,0.0136554621848739,0.0361842105263157
+713,00192.txt,1,0.6515231092436975,0.4671052631578947,0.0089285714285714,0.0263157894736842
+714,00192.txt,1,0.3332457983193277,0.5386513157894737,0.0131302521008403,0.0411184210526315
+715,00192.txt,1,0.1142331932773109,0.5526315789473684,0.0194327731092436,0.0526315789473684
+716,00192.txt,2,0.1502100840336134,0.6036184210526315,0.01890756302521,0.0723684210526315
+717,00192.txt,2,0.6966911764705882,0.6348684210526315,0.0225840336134453,0.0526315789473684
+718,00192.txt,2,0.5149684873949579,0.5205592105263157,0.0215336134453781,0.0509868421052631
+719,00192.txt,1,0.1662289915966386,0.8486842105263157,0.0099789915966386,0.0263157894736842
+720,00192.txt,3,0.2654936974789916,0.6661184210526315,0.025735294117647,0.0657894736842105
+721,00192.txt,3,0.2875525210084033,0.6809210526315789,0.0267857142857142,0.0756578947368421
+722,00193.txt,0,0.7728466386554621,0.5657894736842105,0.0372899159663865,0.0822368421052631
+723,00193.txt,2,0.9734768907563024,0.2203947368421052,0.0215336134453781,0.0756578947368421
+724,00193.txt,1,0.345063025210084,0.606907894736842,0.0126050420168067,0.0394736842105263
+725,00193.txt,1,0.4396008403361344,0.8643092105263157,0.009453781512605,0.0279605263157894
+726,00194.txt,0,0.9217436974789917,0.7014802631578947,0.0315126050420168,0.09375
+727,00194.txt,0,0.94984243697479,0.4605263157894737,0.025735294117647,0.1151315789473684
+728,00194.txt,1,0.8332457983193277,0.1389802631578947,0.0110294117647058,0.037828947368421
+729,00194.txt,1,0.8056722689075629,0.2129934210526315,0.009453781512605,0.0345394736842105
+730,00194.txt,1,0.7058823529411764,0.428453947368421,0.009453781512605,0.0345394736842105
+731,00194.txt,4,0.0934873949579832,0.2368421052631578,0.0210084033613445,0.069078947368421
+732,00194.txt,1,0.2061449579831932,0.2376644736842105,0.0110294117647058,0.03125
+733,00194.txt,1,0.2263655462184874,0.5567434210526315,0.0115546218487394,0.03125
+734,00195.txt,5,0.2983193277310924,0.4925986842105262,0.0462184873949579,0.1069078947368421
+735,00195.txt,0,0.6118697478991596,0.1200657894736842,0.0273109243697479,0.0822368421052631
+736,00195.txt,1,0.0191701680672268,0.4465460526315789,0.0152310924369747,0.0444078947368421
+737,00195.txt,1,0.5861344537815126,0.2754934210526316,0.0105042016806722,0.03125
+738,00195.txt,1,0.7219012605042017,0.2952302631578947,0.0099789915966386,0.0279605263157894
+739,00196.txt,2,0.6467962184873949,0.5361842105263157,0.0246848739495798,0.0526315789473684
+740,00196.txt,3,0.672531512605042,0.5098684210526315,0.0236344537815126,0.0756578947368421
+741,00197.txt,0,0.3757878151260504,0.6866776315789473,0.025735294117647,0.0707236842105263
+742,00197.txt,0,0.376313025210084,0.622532894736842,0.0320378151260504,0.0838815789473684
+743,00197.txt,1,0.0186449579831932,0.7236842105263157,0.0141806722689075,0.0394736842105263
+744,00197.txt,4,0.1349789915966386,0.125,0.0210084033613445,0.0592105263157894
+745,00198.txt,5,0.6242121848739496,0.2828947368421052,0.0572478991596638,0.1546052631578947
+746,00198.txt,4,0.5680147058823529,0.5575657894736842,0.0204831932773109,0.0625
+747,00198.txt,3,0.0824579831932773,0.453125,0.0210084033613445,0.0641447368421052
+748,00198.txt,1,0.1381302521008403,0.2754934210526316,0.009453781512605,0.0279605263157894
+749,00198.txt,1,0.3487394957983193,0.8404605263157894,0.009453781512605,0.0296052631578947
+750,00199.txt,1,0.9099264705882352,0.6743421052631579,0.0120798319327731,0.0427631578947368
+751,00199.txt,3,0.5821953781512604,0.8199013157894737,0.025735294117647,0.0707236842105263
+752,00199.txt,4,0.8547794117647058,0.5074013157894737,0.0215336134453781,0.0608552631578947
+753,00200.txt,0,0.1399684873949579,0.2664473684210526,0.0309873949579831,0.0855263157894736
+754,00200.txt,0,0.1951155462184874,0.3001644736842105,0.025735294117647,0.0871710526315789
+755,00200.txt,0,0.1741071428571428,0.2960526315789473,0.0225840336134453,0.0855263157894736
+756,00201.txt,1,0.4525,0.5583333333333333,0.0325,0.0433333333333333
+757,00201.txt,1,0.474375,0.5725,0.02375,0.035
+758,00201.txt,1,0.4975,0.8808333333333334,0.0275,0.0316666666666666
+759,00202.txt,3,0.1475,0.62,0.0525,0.0733333333333333
+760,00203.txt,0,0.27125,0.13,0.06,0.0833333333333333
+761,00203.txt,1,0.38375,0.3441666666666667,0.0175,0.0216666666666666
+762,00204.txt,0,0.791875,0.1416666666666666,0.05625,0.0833333333333333
+763,00205.txt,1,0.7475,0.2408333333333333,0.02,0.0283333333333333
+764,00206.txt,3,0.5750000000000001,0.8241666666666667,0.0625,0.0783333333333333
+765,00206.txt,1,0.62125,0.9416666666666668,0.02,0.03
+766,00207.txt,4,0.080625,0.7291666666666667,0.04375,0.0583333333333333
+767,00208.txt,3,0.831875,0.6900000000000001,0.05625,0.08
+768,00209.txt,2,0.2825,0.1533333333333333,0.0525,0.0466666666666666
+769,00209.txt,4,0.98625,0.7375,0.025,0.055
+770,00210.txt,1,0.626875,0.3916666666666667,0.01875,0.0266666666666666
+771,00211.txt,3,0.449375,0.5466666666666667,0.05375,0.08
+772,00211.txt,1,0.27375,0.7116666666666667,0.03,0.0333333333333333
+773,00212.txt,3,0.06875,0.4858333333333333,0.05,0.055
+774,00212.txt,1,0.08625,0.2008333333333333,0.03,0.0383333333333333
+775,00212.txt,1,0.534375,0.2733333333333334,0.02125,0.0266666666666666
+776,00213.txt,1,0.255,0.2733333333333334,0.0175,0.02
+777,00213.txt,1,0.1175,0.0833333333333333,0.01,0.0133333333333333
+778,00213.txt,1,0.593125,0.7150000000000001,0.01125,0.0166666666666666
+779,00214.txt,4,0.5425,0.3008333333333333,0.0375,0.0483333333333333
+780,00214.txt,1,0.196875,0.1916666666666666,0.02125,0.0266666666666666
+781,00214.txt,1,0.19625,0.2133333333333333,0.0225,0.0266666666666666
+782,00215.txt,3,0.2075,0.8091666666666667,0.0575,0.0716666666666666
+783,00216.txt,0,0.209375,0.1683333333333333,0.06125,0.0733333333333333
+784,00216.txt,4,0.2775,0.4191666666666667,0.0525,0.0683333333333333
+785,00217.txt,0,0.8668750000000001,0.1716666666666667,0.07375,0.0833333333333333
+786,00218.txt,1,0.4225,0.1925,0.02,0.0216666666666666
+787,00218.txt,1,0.425625,0.2125,0.01625,0.0183333333333333
+788,00218.txt,1,0.418125,0.6658333333333334,0.03125,0.035
+789,00218.txt,1,0.705,0.665,0.015,0.02
+790,00219.txt,3,0.3725,0.38,0.07,0.08
+791,00219.txt,4,0.558125,0.4741666666666667,0.06125,0.075
+792,00220.txt,1,0.695625,0.1916666666666666,0.01875,0.0233333333333333
+793,00220.txt,1,0.696875,0.2116666666666666,0.01625,0.0166666666666666
+794,00220.txt,1,0.203125,0.135,0.01875,0.0266666666666666
+795,00221.txt,5,0.7625000000000001,0.5441666666666667,0.125,0.1283333333333333
+796,00221.txt,1,0.76375,0.4725,0.0225,0.0316666666666666
+797,00221.txt,1,0.72875,0.1458333333333333,0.0175,0.0216666666666666
+798,00222.txt,2,0.071875,0.5858333333333333,0.04625,0.0516666666666666
+799,00222.txt,1,0.39625,0.135,0.02,0.03
+800,00222.txt,2,0.928125,0.1883333333333333,0.03125,0.0733333333333333
+801,00223.txt,4,0.084375,0.4091666666666667,0.04125,0.055
+802,00223.txt,1,0.59875,0.1341666666666666,0.0225,0.0283333333333333
+803,00224.txt,4,0.12375,0.7858333333333334,0.0475,0.0683333333333333
+804,00225.txt,2,0.53,0.4716666666666667,0.05,0.05
+805,00226.txt,1,0.3825,0.0858333333333333,0.01,0.0116666666666666
+806,00226.txt,1,0.170625,0.41,0.01625,0.0233333333333333
+807,00226.txt,1,0.005625,0.8225,0.01125,0.015
+808,00226.txt,1,0.296875,0.8758333333333334,0.01875,0.025
+809,00227.txt,2,0.698125,0.3166666666666667,0.04125,0.04
+810,00227.txt,1,0.558125,0.7991666666666667,0.02875,0.045
+811,00228.txt,1,0.974375,0.4841666666666667,0.03375,0.0416666666666666
+812,00229.txt,5,0.1875,0.255,0.0925,0.12
+813,00230.txt,2,0.87125,0.4441666666666667,0.05,0.0483333333333333
+814,00230.txt,4,0.665,0.5433333333333333,0.0425,0.05
+815,00230.txt,1,0.786875,0.8191666666666667,0.02125,0.025
+816,00231.txt,2,0.351875,0.3958333333333333,0.06625,0.0616666666666666
+817,00231.txt,1,0.244375,0.7283333333333334,0.03625,0.0466666666666666
+818,00232.txt,0,0.8725,0.6125,0.0575,0.0683333333333333
+819,00232.txt,3,0.65625,0.8141666666666667,0.05,0.0583333333333333
+820,00233.txt,1,0.201875,0.8066666666666668,0.01875,0.03
+821,00233.txt,1,0.6975,0.8266666666666668,0.015,0.02
+822,00233.txt,1,0.645625,0.0841666666666666,0.01125,0.015
+823,00234.txt,5,0.353125,0.65,0.11875,0.1566666666666666
+824,00234.txt,1,0.008125,0.6866666666666668,0.01625,0.0266666666666666
+825,00234.txt,4,0.8931250000000001,0.1716666666666667,0.04625,0.06
+826,00235.txt,4,0.449375,0.8266666666666668,0.04625,0.06
+827,00236.txt,3,0.966875,0.4308333333333333,0.06375,0.0716666666666666
+828,00236.txt,3,0.931875,0.4016666666666666,0.04625,0.0633333333333333
+829,00236.txt,3,0.70125,0.5925,0.055,0.0783333333333333
+830,00237.txt,1,0.8125,0.6741666666666667,0.025,0.035
+831,00237.txt,4,0.2275,0.2141666666666666,0.0525,0.0583333333333333
+832,00237.txt,1,0.51375,0.2966666666666667,0.025,0.0366666666666666
+833,00237.txt,4,0.29,0.5183333333333333,0.02,0.0266666666666666
+834,00238.txt,4,0.40125,0.8208333333333334,0.03,0.0416666666666666
+835,00238.txt,2,0.49625,0.2816666666666667,0.0625,0.0566666666666666
+836,00238.txt,2,0.37625,0.8733333333333334,0.055,0.0633333333333333
+837,00239.txt,3,0.749375,0.4133333333333334,0.05875,0.0733333333333333
+838,00239.txt,3,0.3675,0.8041666666666667,0.0675,0.075
+839,00239.txt,1,0.3025,0.5266666666666667,0.02,0.0233333333333333
+840,00240.txt,1,0.486875,0.3575,0.02625,0.0283333333333333
+841,00240.txt,1,0.909375,0.0833333333333333,0.01625,0.0133333333333333
+842,00241.txt,1,0.521875,0.295,0.01875,0.02
+843,00241.txt,1,0.0425,0.895,0.0175,0.02
+844,00242.txt,2,0.6637500000000001,0.8625,0.035,0.0583333333333333
+845,00242.txt,4,0.716875,0.5850000000000001,0.05125,0.0666666666666666
+846,00243.txt,5,0.5225,0.5141666666666667,0.145,0.1883333333333333
+847,00243.txt,1,0.376875,0.1875,0.02875,0.0416666666666666
+848,00243.txt,1,0.2825,0.63,0.02,0.0266666666666666
+849,00244.txt,1,0.59125,0.7441666666666668,0.0175,0.025
+850,00245.txt,2,0.278125,0.6175,0.05125,0.055
+851,00245.txt,1,0.351875,0.6683333333333333,0.02875,0.0333333333333333
+852,00245.txt,1,0.51375,0.8433333333333334,0.0275,0.0433333333333333
+853,00245.txt,4,0.503125,0.5291666666666667,0.02375,0.0316666666666666
+854,00246.txt,2,0.065625,0.5625,0.03625,0.0583333333333333
+855,00246.txt,3,0.6475,0.095,0.06,0.07
+856,00247.txt,1,0.4925,0.4941666666666667,0.0325,0.0383333333333333
+857,00248.txt,2,0.33875,0.6416666666666667,0.04,0.0366666666666666
+858,00248.txt,3,0.38,0.6708333333333334,0.075,0.0883333333333333
+859,00249.txt,1,0.65625,0.36,0.0225,0.0333333333333333
+860,00250.txt,5,0.124375,0.3241666666666667,0.13375,0.1183333333333333
+861,00250.txt,1,0.449375,0.5275000000000001,0.01875,0.0216666666666666
+862,00251.txt,4,0.64,0.6741666666666667,0.05,0.065
+863,00251.txt,4,0.514375,0.6625000000000001,0.06375,0.0883333333333333
+864,00251.txt,1,0.325625,0.2758333333333334,0.03125,0.0383333333333333
+865,00252.txt,2,0.080625,0.4808333333333334,0.04375,0.0483333333333333
+866,00253.txt,2,0.93375,0.4833333333333333,0.04,0.0466666666666666
+867,00254.txt,2,0.374375,0.6608333333333334,0.03625,0.0583333333333333
+868,00254.txt,1,0.698125,0.2816666666666667,0.01875,0.0266666666666666
+869,00255.txt,0,0.18375,0.2041666666666667,0.0675,0.0816666666666666
+870,00255.txt,3,0.7375,0.7366666666666667,0.05,0.0633333333333333
+871,00256.txt,2,0.515,0.67,0.045,0.0466666666666666
+872,00256.txt,3,0.465,0.6866666666666668,0.0625,0.08
+873,00257.txt,2,0.35,0.7908333333333334,0.0375,0.0583333333333333
+874,00257.txt,1,0.61125,0.8200000000000001,0.03,0.0333333333333333
+875,00257.txt,1,0.759375,0.4266666666666667,0.02625,0.04
+876,00257.txt,1,0.8425,0.4208333333333333,0.03,0.0416666666666666
+877,00257.txt,1,0.82625,0.3916666666666667,0.03,0.04
+878,00258.txt,5,0.223125,0.1241666666666666,0.10875,0.135
+879,00258.txt,1,0.976875,0.4358333333333333,0.02625,0.035
+880,00259.txt,5,0.8250000000000001,0.1241666666666666,0.1075,0.1416666666666666
+881,00260.txt,1,0.71125,0.7541666666666668,0.0325,0.045
+882,00260.txt,1,0.078125,0.7158333333333334,0.01875,0.025
+883,00261.txt,1,0.699375,0.2241666666666666,0.02375,0.0316666666666666
+884,00262.txt,0,0.4625,0.8166666666666668,0.06,0.07
+885,00263.txt,3,0.338125,0.7141666666666667,0.06875,0.0683333333333333
+886,00264.txt,2,0.785625,0.3316666666666666,0.04125,0.0666666666666666
+887,00264.txt,1,0.1075,0.4541666666666667,0.0225,0.0283333333333333
+888,00264.txt,1,0.168125,0.93,0.01875,0.0266666666666666
+889,00265.txt,4,0.34375,0.7058333333333334,0.0425,0.0616666666666666
+890,00266.txt,1,0.89,0.3508333333333333,0.04,0.0516666666666666
+891,00266.txt,4,0.428125,0.5133333333333334,0.04875,0.0633333333333333
+892,00266.txt,4,0.816875,0.7216666666666667,0.05125,0.07
+893,00266.txt,3,0.030625,0.5875,0.06125,0.095
+894,00267.txt,1,0.46375,0.5541666666666667,0.0325,0.0383333333333333
+895,00267.txt,1,0.218125,0.6858333333333334,0.01625,0.025
+896,00267.txt,4,0.034375,0.8541666666666667,0.05375,0.0683333333333333
+897,00268.txt,4,0.80375,0.8650000000000001,0.045,0.0633333333333333
+898,00268.txt,2,0.67,0.1883333333333333,0.0425,0.0633333333333333
+899,00269.txt,0,0.6525,0.2516666666666667,0.06,0.0733333333333333
+900,00269.txt,1,0.510625,0.2025,0.02625,0.035
+901,00269.txt,1,0.435625,0.745,0.01875,0.0233333333333333
+902,00269.txt,1,0.229375,0.8975000000000001,0.02125,0.0216666666666666
+903,00269.txt,1,0.759375,0.6983333333333334,0.01625,0.02
+904,00270.txt,4,0.8225,0.5616666666666666,0.05,0.06
+905,00270.txt,1,0.720625,0.9025,0.01875,0.0183333333333333
+906,00271.txt,2,0.394375,0.6925,0.04125,0.065
+907,00272.txt,1,0.363125,0.3483333333333333,0.03125,0.0466666666666666
+908,00272.txt,1,0.05125,0.28,0.04,0.0333333333333333
+909,00273.txt,0,0.665,0.8158333333333334,0.0425,0.0516666666666666
+910,00274.txt,2,0.20625,0.7775000000000001,0.0575,0.0616666666666666
+911,00275.txt,1,0.02625,0.2325,0.0325,0.0416666666666666
+912,00275.txt,1,0.5181250000000001,0.8158333333333334,0.02375,0.0316666666666666
+913,00276.txt,2,0.715,0.3141666666666667,0.0575,0.0683333333333333
+914,00276.txt,1,0.566875,0.9383333333333334,0.02125,0.0233333333333333
+915,00277.txt,1,0.455625,0.8583333333333334,0.02125,0.0266666666666666
+916,00277.txt,1,0.96,0.5133333333333334,0.0275,0.0266666666666666
+917,00277.txt,1,0.52375,0.345,0.0175,0.0233333333333333
+918,00278.txt,5,0.310625,0.2,0.09625,0.1233333333333333
+919,00278.txt,1,0.221875,0.5908333333333333,0.02875,0.0383333333333333
+920,00278.txt,4,0.066875,0.5125000000000001,0.04875,0.0616666666666666
+921,00279.txt,0,0.62,0.4583333333333333,0.0425,0.0533333333333333
+922,00280.txt,0,0.2175,0.6050000000000001,0.0525,0.09
+923,00280.txt,1,0.54125,0.3641666666666667,0.0275,0.0316666666666666
+924,00281.txt,2,0.093125,0.7766666666666667,0.04625,0.07
+925,00282.txt,4,0.780625,0.7741666666666667,0.04625,0.0616666666666666
+926,00282.txt,4,0.134375,0.9325,0.02375,0.0283333333333333
+927,00283.txt,1,0.38125,0.1766666666666666,0.015,0.02
+928,00283.txt,1,0.00625,0.1216666666666666,0.0125,0.0233333333333333
+929,00283.txt,1,0.24,0.9366666666666668,0.0175,0.0233333333333333
+930,00284.txt,2,0.47375,0.3008333333333333,0.0375,0.0616666666666666
+931,00284.txt,4,0.16875,0.4458333333333333,0.05,0.0616666666666666
+932,00285.txt,4,0.86375,0.5425,0.0475,0.065
+933,00285.txt,1,0.5700000000000001,0.935,0.02,0.0233333333333333
+934,00285.txt,1,0.416875,0.5375000000000001,0.01375,0.0183333333333333
+935,00286.txt,1,0.13875,0.3283333333333333,0.03,0.0433333333333333
+936,00286.txt,1,0.673125,0.9383333333333334,0.01625,0.0233333333333333
+937,00287.txt,1,0.240625,0.8366666666666667,0.02125,0.0333333333333333
+938,00287.txt,1,0.78,0.9358333333333334,0.0175,0.0216666666666666
+939,00288.txt,3,0.123125,0.7058333333333334,0.07125,0.075
+940,00288.txt,3,0.656875,0.7358333333333333,0.05375,0.085
+941,00288.txt,4,0.69625,0.7525000000000001,0.0375,0.0516666666666666
+942,00289.txt,1,0.7325,0.6166666666666667,0.0175,0.0266666666666666
+943,00289.txt,1,0.965,0.8433333333333334,0.0275,0.0266666666666666
+944,00289.txt,1,0.888125,0.9341666666666668,0.02125,0.0283333333333333
+945,00290.txt,0,0.476875,0.5466666666666667,0.03625,0.0466666666666666
+946,00290.txt,1,0.174375,0.0883333333333333,0.03125,0.04
+947,00290.txt,0,0.974375,0.915,0.03625,0.0533333333333333
+948,00291.txt,1,0.51125,0.6025,0.02,0.0283333333333333
+949,00291.txt,1,0.040625,0.1308333333333333,0.01625,0.0216666666666666
+950,00292.txt,1,0.765625,0.6508333333333334,0.01875,0.0283333333333333
+951,00292.txt,1,0.321875,0.9391666666666668,0.02125,0.0283333333333333
+952,00293.txt,2,0.5856250000000001,0.3975,0.04125,0.055
+953,00293.txt,1,0.7775,0.9408333333333334,0.0225,0.0283333333333333
+954,00294.txt,2,0.060625,0.1483333333333333,0.05875,0.0666666666666666
+955,00294.txt,4,0.18125,0.4008333333333334,0.0525,0.0683333333333333
+956,00294.txt,1,0.34375,0.6533333333333333,0.0175,0.0266666666666666
+957,00295.txt,2,0.81625,0.15,0.065,0.0466666666666666
+958,00295.txt,1,0.091875,0.2883333333333333,0.02125,0.0266666666666666
+959,00296.txt,5,0.63,0.7666666666666667,0.165,0.2133333333333333
+960,00297.txt,0,0.615625,0.5308333333333334,0.06625,0.085
+961,00297.txt,3,0.541875,0.5483333333333333,0.04875,0.0766666666666666
+962,00297.txt,1,0.093125,0.16,0.01875,0.0233333333333333
+963,00298.txt,2,0.083125,0.3216666666666667,0.05375,0.0533333333333333
+964,00298.txt,4,0.925625,0.3541666666666667,0.04875,0.0583333333333333
+965,00299.txt,5,0.188125,0.7333333333333334,0.07875,0.1033333333333333
+966,00300.txt,4,0.95875,0.4391666666666667,0.05,0.0683333333333333
+967,00300.txt,3,0.0475,0.6783333333333333,0.05,0.0666666666666666
+968,00301.txt,3,0.888125,0.68,0.05875,0.0666666666666666
+969,00301.txt,1,0.27625,0.8158333333333334,0.02,0.025
+970,00302.txt,1,0.82625,0.37,0.025,0.0333333333333333
+971,00303.txt,1,0.18,0.3916666666666667,0.025,0.03
+972,00304.txt,3,0.603125,0.6058333333333333,0.06125,0.075
+973,00305.txt,1,0.07625,0.6158333333333333,0.025,0.0416666666666666
+974,00306.txt,2,0.13,0.7125,0.0475,0.065
+975,00306.txt,4,0.6012500000000001,0.6933333333333334,0.05,0.0666666666666666
+976,00306.txt,4,0.23,0.175,0.0525,0.0633333333333333
+977,00307.txt,1,0.331875,0.8108333333333334,0.03125,0.0383333333333333
+978,00308.txt,1,0.870625,0.1191666666666666,0.02375,0.0316666666666666
+979,00309.txt,4,0.3475,0.7150000000000001,0.045,0.0566666666666666
+980,00309.txt,1,0.436875,0.5658333333333334,0.02125,0.025
+981,00310.txt,0,0.474375,0.6091666666666667,0.06875,0.0883333333333333
+982,00310.txt,1,0.335625,0.165,0.02375,0.0333333333333333
+983,00310.txt,1,0.98,0.5283333333333333,0.025,0.0333333333333333
+984,00310.txt,3,0.228125,0.7241666666666667,0.06625,0.0716666666666666
+985,00311.txt,1,0.05125,0.7441666666666668,0.025,0.0283333333333333
+986,00311.txt,1,0.321875,0.6358333333333334,0.02375,0.025
+987,00312.txt,4,0.24,0.44,0.05,0.06
+988,00312.txt,1,0.93125,0.7475,0.0275,0.0283333333333333
+989,00313.txt,0,0.093125,0.4616666666666666,0.06375,0.0866666666666666
+990,00313.txt,1,0.461875,0.4233333333333333,0.02125,0.0266666666666666
+991,00313.txt,1,0.43625,0.4525,0.0225,0.0283333333333333
+992,00313.txt,1,0.919375,0.4066666666666667,0.02125,0.0266666666666666
+993,00313.txt,4,0.459375,0.5175000000000001,0.04875,0.0683333333333333
+994,00313.txt,4,0.36,0.6716666666666667,0.0475,0.0566666666666666
+995,00314.txt,2,0.49125,0.1891666666666666,0.05,0.0616666666666666
+996,00314.txt,2,0.0275,0.2091666666666666,0.0475,0.065
+997,00314.txt,1,0.821875,0.4283333333333333,0.01875,0.0266666666666666
+998,00315.txt,4,0.8325,0.2508333333333333,0.0475,0.0583333333333333
+999,00315.txt,1,0.263125,0.3108333333333333,0.01625,0.0216666666666666
+1000,00316.txt,3,0.213125,0.5516666666666667,0.05875,0.0633333333333333
+1001,00317.txt,2,0.09,0.1725,0.035,0.055
+1002,00317.txt,1,0.1375,0.5341666666666667,0.0325,0.035
+1003,00317.txt,1,0.499375,0.5683333333333334,0.02625,0.0333333333333333
+1004,00317.txt,1,0.0125,0.9225,0.025,0.035
+1005,00318.txt,2,0.724375,0.17,0.03625,0.0566666666666666
+1006,00318.txt,1,0.35375,0.9216666666666667,0.0225,0.03
+1007,00318.txt,1,0.368125,0.1366666666666667,0.01875,0.0233333333333333
+1008,00319.txt,1,0.704375,0.9258333333333334,0.02125,0.0283333333333333
+1009,00319.txt,1,0.93625,0.1333333333333333,0.02,0.0233333333333333
+1010,00320.txt,0,0.668125,0.615,0.08875,0.0833333333333333
+1011,00321.txt,0,0.204375,0.2733333333333334,0.08875,0.0866666666666666
+1012,00322.txt,2,0.509375,0.7608333333333334,0.04375,0.045
+1013,00322.txt,1,0.04875,0.3425,0.0175,0.0216666666666666
+1014,00323.txt,5,0.699375,0.795,0.10625,0.13
+1015,00324.txt,4,0.88,0.3658333333333333,0.0475,0.0616666666666666
+1016,00325.txt,3,0.618125,0.7391666666666667,0.06125,0.0816666666666666
+1017,00326.txt,2,0.36375,0.7633333333333334,0.035,0.0633333333333333
+1018,00326.txt,1,0.135625,0.1025,0.01875,0.025
+1019,00327.txt,0,0.73625,0.4716666666666667,0.065,0.1266666666666666
+1020,00327.txt,1,0.32625,0.9025,0.0225,0.0283333333333333
+1021,00328.txt,3,0.409375,0.1133333333333333,0.05375,0.0666666666666666
+1022,00329.txt,4,0.4375,0.5108333333333334,0.05,0.0683333333333333
+1023,00330.txt,0,0.0125,0.6241666666666668,0.025,0.0716666666666666
+1024,00330.txt,1,0.363125,0.8650000000000001,0.02125,0.0266666666666666
+1025,00330.txt,4,0.1275,0.6991666666666667,0.02,0.0283333333333333
+1026,00330.txt,1,0.4525,0.2975,0.0225,0.0283333333333333
+1027,00331.txt,3,0.980625,0.6275000000000001,0.03625,0.085
+1028,00332.txt,3,0.6575,0.4725,0.06,0.0783333333333333
+1029,00332.txt,1,0.324375,0.2925,0.03125,0.035
+1030,00332.txt,1,0.95625,0.4575,0.02,0.025
+1031,00333.txt,3,0.8250000000000001,0.1091666666666666,0.0575,0.0716666666666666
+1032,00333.txt,1,0.189375,0.54,0.02375,0.0333333333333333
+1033,00334.txt,4,0.253125,0.2158333333333333,0.03875,0.0483333333333333
+1034,00335.txt,4,0.753125,0.3,0.05375,0.0733333333333333
+1035,00335.txt,1,0.16625,0.41,0.0225,0.0266666666666666
+1036,00336.txt,1,0.378125,0.6058333333333333,0.02375,0.035
+1037,00337.txt,0,0.475,0.4866666666666667,0.0525,0.0633333333333333
+1038,00338.txt,3,0.885625,0.6341666666666667,0.06375,0.0816666666666666
+1039,00338.txt,1,0.03125,0.3725,0.02,0.0283333333333333
+1040,00338.txt,1,0.288125,0.9025,0.03375,0.045
+1041,00339.txt,1,0.7675000000000001,0.8991666666666667,0.03,0.0416666666666666
+1042,00340.txt,4,0.4425,0.5266666666666667,0.0525,0.0666666666666666
+1043,00341.txt,5,0.131875,0.8558333333333333,0.07375,0.1016666666666666
+1044,00341.txt,1,0.330625,0.12,0.01875,0.0233333333333333
+1045,00342.txt,4,0.42375,0.37,0.055,0.07
+1046,00343.txt,0,0.131875,0.6258333333333334,0.07125,0.0916666666666666
+1047,00344.txt,1,0.895625,0.8400000000000001,0.01875,0.0233333333333333
+1048,00345.txt,5,0.84,0.5633333333333334,0.1,0.11
+1049,00345.txt,1,0.02375,0.42,0.0225,0.0266666666666666
+1050,00345.txt,2,0.47875,0.2466666666666666,0.0375,0.0366666666666666
+1051,00346.txt,1,0.225,0.7483333333333334,0.0225,0.0266666666666666
+1052,00347.txt,4,0.760625,0.6066666666666667,0.03875,0.0566666666666666
+1053,00348.txt,0,0.64,0.5425,0.06,0.0783333333333333
+1054,00349.txt,2,0.913125,0.4441666666666667,0.06125,0.0516666666666666
+1055,00349.txt,1,0.008125,0.8500000000000001,0.01625,0.03
+1056,00350.txt,1,0.180625,0.6616666666666667,0.02125,0.03
+1057,00350.txt,1,0.25625,0.1525,0.0175,0.025
+1058,00350.txt,1,0.8150000000000001,0.4625,0.0175,0.0216666666666666
+1059,00351.txt,0,0.18875,0.6716666666666667,0.06,0.1
+1060,00351.txt,3,0.134375,0.6733333333333333,0.05125,0.0666666666666666
+1061,00351.txt,3,0.016875,0.7433333333333334,0.03375,0.0633333333333333
+1062,00351.txt,3,0.14125,0.7691666666666667,0.0775,0.095
+1063,00352.txt,3,0.4175,0.7591666666666668,0.0375,0.0516666666666666
+1064,00352.txt,1,0.326875,0.6141666666666667,0.02125,0.025
+1065,00352.txt,1,0.19875,0.625,0.025,0.0266666666666666
+1066,00353.txt,1,0.114375,0.5850000000000001,0.01875,0.0233333333333333
+1067,00354.txt,5,0.49875,0.19,0.1075,0.14
+1068,00354.txt,1,0.6587500000000001,0.5833333333333334,0.025,0.0266666666666666
+1069,00355.txt,3,0.14875,0.3516666666666667,0.045,0.07
+1070,00356.txt,3,0.87375,0.3508333333333333,0.0525,0.0616666666666666
+1071,00356.txt,1,0.6431250000000001,0.2225,0.02125,0.025
+1072,00357.txt,1,0.284375,0.145,0.02625,0.0366666666666666
+1073,00357.txt,1,0.37625,0.7041666666666667,0.0325,0.035
+1074,00358.txt,1,0.11625,0.885,0.02,0.0233333333333333
+1075,00358.txt,1,0.98875,0.1416666666666666,0.02,0.0366666666666666
+1076,00359.txt,1,0.459375,0.8875000000000001,0.02125,0.0283333333333333
+1077,00359.txt,1,0.491875,0.7941666666666667,0.01875,0.025
+1078,00360.txt,1,0.575625,0.7050000000000001,0.02625,0.0333333333333333
+1079,00360.txt,1,0.8675,0.8891666666666668,0.025,0.0216666666666666
+1080,00361.txt,2,0.235625,0.5733333333333334,0.03625,0.0533333333333333
+1081,00362.txt,2,0.345,0.4841666666666667,0.0575,0.0483333333333333
+1082,00363.txt,1,0.633125,0.8016666666666667,0.02875,0.0333333333333333
+1083,00364.txt,2,0.0425,0.7091666666666667,0.0475,0.065
+1084,00364.txt,1,0.24125,0.3625,0.02,0.0283333333333333
+1085,00365.txt,1,0.4275,0.4658333333333334,0.02,0.0283333333333333
+1086,00366.txt,1,0.8225,0.5800000000000001,0.025,0.03
+1087,00366.txt,1,0.41625,0.5033333333333334,0.02,0.0266666666666666
+1088,00367.txt,4,0.543125,0.5308333333333334,0.04375,0.0583333333333333
+1089,00367.txt,1,0.860625,0.505,0.02125,0.0266666666666666
+1090,00368.txt,4,0.383125,0.4358333333333333,0.04125,0.0583333333333333
+1091,00368.txt,1,0.525,0.7791666666666667,0.0225,0.025
+1092,00368.txt,1,0.54125,0.7658333333333334,0.02,0.0216666666666666
+1093,00369.txt,2,0.785625,0.5733333333333334,0.04625,0.0433333333333333
+1094,00369.txt,4,0.213125,0.6991666666666667,0.04375,0.055
+1095,00369.txt,1,0.20625,0.8316666666666667,0.02,0.0266666666666666
+1096,00369.txt,1,0.5125,0.1516666666666666,0.02,0.0266666666666666
+1097,00369.txt,1,0.53125,0.1591666666666666,0.0175,0.025
+1098,00370.txt,5,0.203125,0.2816666666666667,0.09625,0.1266666666666666
+1099,00370.txt,4,0.874375,0.5041666666666667,0.05625,0.0716666666666666
+1100,00370.txt,1,0.4975,0.3591666666666667,0.025,0.035
+1101,00371.txt,4,0.476875,0.32,0.04875,0.0633333333333333
+1102,00372.txt,4,0.938125,0.3483333333333333,0.04875,0.0533333333333333
+1103,00372.txt,4,0.08375,0.7341666666666667,0.025,0.0283333333333333
+1104,00373.txt,2,0.910625,0.4883333333333333,0.04375,0.0733333333333333
+1105,00373.txt,1,0.655,0.5766666666666667,0.0225,0.0266666666666666
+1106,00374.txt,1,0.779375,0.495,0.03875,0.0533333333333333
+1107,00375.txt,1,0.309375,0.78,0.03375,0.04
+1108,00376.txt,1,0.55375,0.5766666666666667,0.02,0.0266666666666666
+1109,00377.txt,4,0.285,0.3383333333333334,0.0475,0.0633333333333333
+1110,00377.txt,4,0.13375,0.6616666666666667,0.0425,0.0633333333333333
+1111,00378.txt,3,0.7775,0.3616666666666667,0.06,0.08
+1112,00379.txt,2,0.8668750000000001,0.4533333333333333,0.05625,0.05
+1113,00379.txt,1,0.933125,0.8191666666666667,0.02125,0.0283333333333333
+1114,00379.txt,1,0.5475,0.4791666666666667,0.03,0.035
+1115,00379.txt,4,0.63,0.5125000000000001,0.035,0.045
+1116,00379.txt,3,0.171875,0.1933333333333333,0.06125,0.07
+1117,00380.txt,4,0.156875,0.4583333333333333,0.04875,0.0633333333333333
+1118,00380.txt,1,0.81625,0.675,0.025,0.0233333333333333
+1119,00381.txt,5,0.315,0.3475,0.115,0.1483333333333333
+1120,00382.txt,2,0.241875,0.5783333333333334,0.04125,0.0566666666666666
+1121,00382.txt,1,0.5175,0.5425,0.0275,0.035
+1122,00382.txt,1,0.67,0.4633333333333334,0.0225,0.03
+1123,00382.txt,1,0.7125,0.63,0.025,0.03
+1124,00383.txt,0,0.948125,0.495,0.05625,0.08
+1125,00383.txt,0,0.98125,0.4525,0.035,0.0683333333333333
+1126,00384.txt,1,0.436875,0.7391666666666667,0.03375,0.0383333333333333
+1127,00385.txt,1,0.265625,0.3208333333333333,0.02625,0.0283333333333333
+1128,00386.txt,0,0.458125,0.8450000000000001,0.03625,0.04
+1129,00386.txt,0,0.454375,0.8908333333333334,0.04625,0.0583333333333333
+1130,00386.txt,0,0.691875,0.2358333333333333,0.03125,0.0416666666666666
+1131,00387.txt,4,0.069375,0.1633333333333333,0.03375,0.04
+1132,00388.txt,4,0.53125,0.64,0.0525,0.07
+1133,00388.txt,2,0.58875,0.245,0.045,0.05
+1134,00389.txt,4,0.63375,0.16,0.0375,0.0466666666666666
+1135,00389.txt,1,0.069375,0.9141666666666668,0.02875,0.0316666666666666
+1136,00389.txt,1,0.261875,0.6266666666666667,0.01375,0.02
+1137,00390.txt,2,0.73,0.6191666666666668,0.0325,0.0583333333333333
+1138,00390.txt,4,0.195625,0.6116666666666667,0.03625,0.05
+1139,00390.txt,1,0.019375,0.8416666666666667,0.02375,0.03
+1140,00391.txt,2,0.7106250000000001,0.1216666666666666,0.05125,0.05
+1141,00392.txt,5,0.51875,0.6141666666666667,0.1,0.1183333333333333
+1142,00392.txt,1,0.270625,0.5158333333333334,0.03375,0.0416666666666666
+1143,00392.txt,1,0.556875,0.3841666666666667,0.02375,0.0283333333333333
+1144,00393.txt,0,0.6075,0.7150000000000001,0.0875,0.09
+1145,00394.txt,2,0.14375,0.6766666666666667,0.055,0.0466666666666666
+1146,00394.txt,1,0.0925,0.3558333333333333,0.02,0.025
+1147,00395.txt,2,0.496875,0.3658333333333333,0.03875,0.0416666666666666
+1148,00395.txt,1,0.34,0.4341666666666667,0.0225,0.0283333333333333
+1149,00395.txt,1,0.689375,0.6416666666666667,0.02125,0.0266666666666666
+1150,00396.txt,2,0.4575,0.1258333333333333,0.0575,0.045
+1151,00396.txt,2,0.493125,0.1525,0.06125,0.0516666666666666
+1152,00397.txt,4,0.323125,0.4725,0.05625,0.0716666666666666
+1153,00397.txt,1,0.301875,0.7708333333333334,0.02625,0.0316666666666666
+1154,00398.txt,2,0.095625,0.1233333333333333,0.05125,0.0433333333333333
+1155,00399.txt,0,0.96625,0.2141666666666666,0.065,0.1216666666666666
+1156,00400.txt,5,0.221875,0.5641666666666667,0.13875,0.1683333333333333
+1157,00401.txt,5,0.615,0.6516666666666667,0.125,0.15
+1158,00402.txt,3,0.48125,0.8125,0.07,0.075
+1159,00403.txt,2,0.516875,0.1191666666666666,0.03875,0.0616666666666666
+1160,00403.txt,1,0.300625,0.4941666666666667,0.02125,0.025
+1161,00404.txt,3,0.94,0.65,0.065,0.0866666666666666
+1162,00404.txt,1,0.78,0.4016666666666666,0.025,0.03
+1163,00405.txt,2,0.43625,0.4233333333333333,0.065,0.06
+1164,00405.txt,2,0.58875,0.3983333333333334,0.06,0.0533333333333333
+1165,00405.txt,3,0.253125,0.3441666666666667,0.05625,0.0816666666666666
+1166,00405.txt,3,0.3775,0.5116666666666667,0.055,0.0833333333333333
+1167,00405.txt,0,0.315,0.2641666666666666,0.0725,0.1116666666666666
+1168,00405.txt,1,0.131875,0.7158333333333334,0.01375,0.0183333333333333
+1169,00406.txt,1,0.66,0.7816666666666667,0.025,0.0333333333333333
+1170,00406.txt,1,0.649375,0.9258333333333334,0.02875,0.0383333333333333
+1171,00407.txt,0,0.10875,0.7583333333333334,0.05,0.0866666666666666
+1172,00407.txt,0,0.15125,0.785,0.05,0.0733333333333333
+1173,00407.txt,3,0.28875,0.7441666666666668,0.0475,0.0783333333333333
+1174,00407.txt,3,0.334375,0.7958333333333334,0.03875,0.0616666666666666
+1175,00407.txt,1,0.55375,0.7783333333333334,0.0275,0.0433333333333333
+1176,00407.txt,1,0.206875,0.8041666666666667,0.01875,0.025
+1177,00408.txt,5,0.969375,0.5950000000000001,0.05875,0.07
+1178,00408.txt,1,0.7781250000000001,0.6566666666666667,0.02125,0.0366666666666666
+1179,00409.txt,5,0.813125,0.61,0.07875,0.0833333333333333
+1180,00410.txt,0,0.6325000000000001,0.7083333333333334,0.06,0.09
+1181,00411.txt,4,0.154375,0.7683333333333334,0.04375,0.0566666666666666
+1182,00412.txt,2,0.868125,0.4616666666666666,0.04875,0.0633333333333333
+1183,00412.txt,4,0.1,0.6191666666666668,0.055,0.075
+1184,00412.txt,3,0.235,0.9083333333333334,0.025,0.0333333333333333
+1185,00412.txt,1,0.1325,0.9333333333333332,0.015,0.02
+1186,00413.txt,1,0.429375,0.2733333333333334,0.02625,0.03
+1187,00413.txt,1,0.245625,0.8408333333333334,0.02375,0.035
+1188,00413.txt,2,0.681875,0.495,0.05625,0.04
+1189,00413.txt,2,0.92875,0.12,0.045,0.0666666666666666
+1190,00414.txt,4,0.319375,0.1883333333333333,0.04875,0.0633333333333333
+1191,00414.txt,1,0.664375,0.8600000000000001,0.03875,0.0433333333333333
+1192,00415.txt,4,0.980625,0.19,0.03625,0.0533333333333333
+1193,00416.txt,0,0.145,0.5483333333333333,0.085,0.0933333333333333
+1194,00416.txt,1,0.328125,0.0966666666666666,0.01625,0.0233333333333333
+1195,00417.txt,4,0.0275,0.2533333333333333,0.04,0.05
+1196,00417.txt,1,0.764375,0.1758333333333333,0.02375,0.0283333333333333
+1197,00418.txt,4,0.92,0.2525,0.0425,0.0583333333333333
+1198,00419.txt,0,0.193125,0.6808333333333334,0.06375,0.085
+1199,00419.txt,1,0.3075,0.4683333333333334,0.03,0.04
+1200,00419.txt,1,0.93,0.4341666666666667,0.0275,0.0316666666666666
+1201,00420.txt,0,0.31625,0.9,0.0675,0.0733333333333333
+1202,00420.txt,4,0.48625,0.3483333333333333,0.0325,0.04
+1203,00420.txt,1,0.9475,0.6566666666666667,0.025,0.0333333333333333
+1204,00421.txt,2,0.041875,0.7741666666666667,0.05375,0.055
+1205,00421.txt,1,0.496875,0.4066666666666667,0.02625,0.0333333333333333
+1206,00421.txt,1,0.90125,0.2775,0.015,0.0183333333333333
+1207,00421.txt,1,0.9475,0.8325,0.0225,0.025
+1208,00422.txt,0,0.42375,0.3741666666666667,0.0625,0.0816666666666666
+1209,00423.txt,2,0.21625,0.4983333333333333,0.0475,0.04
+1210,00423.txt,1,0.164375,0.515,0.03875,0.0533333333333333
+1211,00424.txt,5,0.63875,0.7058333333333334,0.1125,0.145
+1212,00424.txt,1,0.2725,0.9125,0.025,0.0316666666666666
+1213,00425.txt,0,0.334375,0.3275,0.07375,0.075
+1214,00425.txt,1,0.378125,0.3541666666666667,0.02375,0.0316666666666666
+1215,00426.txt,4,0.6775,0.44,0.0425,0.0566666666666666
+1216,00427.txt,4,0.63875,0.8125,0.05,0.065
+1217,00428.txt,4,0.191875,0.2033333333333333,0.04625,0.06
+1218,00429.txt,3,0.228125,0.7150000000000001,0.05625,0.07
+1219,00430.txt,3,0.3975,0.6508333333333334,0.06,0.075
+1220,00431.txt,5,0.7725,0.28,0.115,0.1466666666666666
+1221,00432.txt,0,0.27375,0.1333333333333333,0.085,0.1
+1222,00432.txt,1,0.20875,0.6858333333333334,0.02,0.0283333333333333
+1223,00433.txt,0,0.788125,0.1366666666666667,0.08375,0.1
+1224,00433.txt,1,0.87875,0.6950000000000001,0.0225,0.0266666666666666
+1225,00434.txt,0,0.8612500000000001,0.6675000000000001,0.08,0.0783333333333333
+1226,00434.txt,1,0.7275,0.795,0.025,0.0333333333333333
+1227,00434.txt,3,0.903125,0.6266666666666667,0.05375,0.0466666666666666
+1228,00435.txt,4,0.298125,0.6908333333333334,0.05625,0.0683333333333333
+1229,00435.txt,1,0.03125,0.4216666666666667,0.02,0.0266666666666666
+1230,00435.txt,1,0.588125,0.8441666666666667,0.02375,0.0316666666666666
+1231,00436.txt,2,0.233125,0.3675,0.05625,0.0416666666666666
+1232,00437.txt,5,0.425625,0.7366666666666667,0.10125,0.1166666666666666
+1233,00437.txt,1,0.645,0.3641666666666667,0.03,0.0416666666666666
+1234,00438.txt,1,0.595625,0.6108333333333333,0.02375,0.035
+1235,00439.txt,3,0.77125,0.5875,0.0675,0.0783333333333333
+1236,00440.txt,4,0.529375,0.2233333333333333,0.04625,0.06
+1237,00441.txt,0,0.35125,0.5958333333333333,0.065,0.1016666666666666
+1238,00441.txt,1,0.75875,0.7250000000000001,0.0325,0.04
+1239,00442.txt,0,0.06,0.7708333333333334,0.065,0.0883333333333333
+1240,00443.txt,0,0.385625,0.3,0.09125,0.0966666666666666
+1241,00444.txt,0,0.379375,0.365,0.09375,0.0633333333333333
+1242,00444.txt,1,0.873125,0.3216666666666667,0.02375,0.03
+1243,00444.txt,1,0.891875,0.2916666666666667,0.02625,0.03
+1244,00444.txt,1,0.903125,0.3241666666666667,0.02125,0.0283333333333333
+1245,00445.txt,1,0.381875,0.2608333333333333,0.02125,0.025
+1246,00445.txt,0,0.87,0.7741666666666667,0.065,0.085
+1247,00446.txt,3,0.244375,0.5375000000000001,0.04125,0.045
+1248,00446.txt,1,0.514375,0.6275000000000001,0.02125,0.0283333333333333
+1249,00447.txt,0,0.2775,0.1841666666666666,0.08,0.0816666666666666
+1250,00447.txt,1,0.215,0.1608333333333333,0.03,0.025
+1251,00448.txt,1,0.48125,0.7025,0.025,0.035
+1252,00448.txt,1,0.63375,0.2633333333333333,0.025,0.0333333333333333
+1253,00449.txt,4,0.12625,0.7725000000000001,0.035,0.0516666666666666
+1254,00449.txt,1,0.079375,0.34,0.02125,0.0233333333333333
+1255,00450.txt,0,0.0725,0.3341666666666666,0.0675,0.0983333333333333
+1256,00450.txt,4,0.195625,0.5891666666666667,0.05125,0.0616666666666666
+1257,00450.txt,1,0.013125,0.8650000000000001,0.02625,0.0333333333333333
+1258,00451.txt,2,0.921875,0.5191666666666667,0.05625,0.075
+1259,00451.txt,2,0.6531250000000001,0.5875,0.04125,0.045
+1260,00452.txt,1,0.73875,0.4875,0.02,0.025
+1261,00452.txt,4,0.936875,0.5691666666666667,0.05375,0.0716666666666666
+1262,00453.txt,3,0.486875,0.6858333333333334,0.05375,0.0716666666666666
+1263,00454.txt,2,0.610625,0.8175,0.03875,0.075
+1264,00454.txt,1,0.53625,0.27,0.015,0.02
+1265,00455.txt,0,0.769375,0.3183333333333333,0.08875,0.07
+1266,00456.txt,1,0.288125,0.3216666666666667,0.02125,0.0266666666666666
+1267,00456.txt,1,0.505625,0.4433333333333333,0.03375,0.0466666666666666
+1268,00456.txt,1,0.515625,0.4841666666666667,0.02375,0.0383333333333333
+1269,00456.txt,3,0.56875,0.4791666666666667,0.0625,0.0916666666666666
+1270,00457.txt,0,0.475,0.2816666666666667,0.0625,0.0766666666666666
+1271,00458.txt,1,0.67,0.1441666666666666,0.03,0.0416666666666666
+1272,00458.txt,1,0.399375,0.7675000000000001,0.01875,0.0216666666666666
+1273,00459.txt,1,0.645625,0.1833333333333333,0.03125,0.0433333333333333
+1274,00459.txt,1,0.7987500000000001,0.31,0.0275,0.0333333333333333
+1275,00460.txt,4,0.09875,0.1808333333333333,0.05,0.0583333333333333
+1276,00461.txt,4,0.84125,0.1675,0.05,0.065
+1277,00462.txt,2,0.27125,0.75,0.04,0.0533333333333333
+1278,00463.txt,2,0.974375,0.7558333333333334,0.04625,0.0516666666666666
+1279,00464.txt,3,0.143125,0.7275,0.05125,0.065
+1280,00464.txt,1,0.279375,0.89,0.02125,0.03
+1281,00465.txt,4,0.9075,0.305,0.055,0.07
+1282,00465.txt,1,0.343125,0.5066666666666667,0.02625,0.0333333333333333
+1283,00466.txt,2,0.820625,0.6366666666666667,0.04125,0.0466666666666666
+1284,00466.txt,2,0.5325,0.2558333333333333,0.0475,0.0416666666666666
+1285,00466.txt,1,0.369375,0.5191666666666667,0.02125,0.0283333333333333
+1286,00467.txt,4,0.94875,0.5416666666666667,0.0575,0.0733333333333333
+1287,00467.txt,1,0.694375,0.3033333333333333,0.02625,0.0366666666666666
+1288,00468.txt,5,0.5437500000000001,0.44,0.0975,0.1133333333333333
+1289,00469.txt,4,0.275625,0.4891666666666667,0.05375,0.0716666666666666
+1290,00470.txt,0,0.79125,0.4433333333333333,0.05,0.0633333333333333
+1291,00470.txt,1,0.051875,0.5066666666666667,0.02375,0.0233333333333333
+1292,00470.txt,1,0.056875,0.5383333333333333,0.02875,0.0333333333333333
+1293,00470.txt,1,0.054375,0.5591666666666667,0.03125,0.0283333333333333
+1294,00471.txt,0,0.509375,0.4508333333333333,0.06875,0.085
+1295,00471.txt,1,0.044375,0.76,0.01875,0.02
+1296,00472.txt,4,0.286875,0.6516666666666667,0.03375,0.0433333333333333
+1297,00473.txt,3,0.2925,0.2075,0.065,0.0616666666666666
+1298,00473.txt,0,0.336875,0.7383333333333334,0.06125,0.1033333333333333
+1299,00474.txt,3,0.910625,0.2058333333333333,0.06125,0.0683333333333333
+1300,00474.txt,1,0.24375,0.8408333333333334,0.02,0.025
+1301,00474.txt,0,0.968125,0.7358333333333333,0.06125,0.0816666666666666
+1302,00475.txt,5,0.20875,0.7958333333333334,0.0925,0.0916666666666666
+1303,00476.txt,2,0.591875,0.5041666666666667,0.03875,0.055
+1304,00476.txt,1,0.723125,0.5525,0.03125,0.0383333333333333
+1305,00476.txt,2,0.811875,0.5525,0.03375,0.0516666666666666
+1306,00477.txt,0,0.504375,0.62,0.03625,0.05
+1307,00478.txt,0,0.076875,0.4666666666666667,0.08625,0.0766666666666666
+1308,00478.txt,1,0.048125,0.7933333333333333,0.02875,0.0366666666666666
+1309,00479.txt,2,0.47125,0.7641666666666667,0.0425,0.0483333333333333
+1310,00479.txt,1,0.663125,0.8875000000000001,0.01625,0.025
+1311,00479.txt,1,0.14,0.6625000000000001,0.02,0.025
+1312,00479.txt,1,0.258125,0.0808333333333333,0.01375,0.015
+1313,00480.txt,3,0.295,0.5041666666666667,0.055,0.075
+1314,00480.txt,3,0.245,0.5,0.055,0.0733333333333333
+1315,00480.txt,2,0.6875,0.2358333333333333,0.04,0.0616666666666666
+1316,00481.txt,0,0.963125,0.2533333333333333,0.05625,0.0633333333333333
+1317,00482.txt,0,0.865625,0.3633333333333333,0.08875,0.07
+1318,00482.txt,2,0.405,0.2066666666666667,0.06,0.0466666666666666
+1319,00482.txt,3,0.87875,0.9233333333333332,0.0625,0.0666666666666666
+1320,00483.txt,4,0.25625,0.4308333333333333,0.0525,0.065
+1321,00484.txt,4,0.18375,0.8766666666666667,0.0525,0.07
+1322,00485.txt,4,0.875625,0.5291666666666667,0.05625,0.0683333333333333
+1323,00485.txt,4,0.604375,0.88,0.05375,0.0666666666666666
+1324,00485.txt,1,0.20625,0.3258333333333333,0.0175,0.0216666666666666
+1325,00486.txt,5,0.4825,0.4783333333333334,0.0925,0.1133333333333333
+1326,00486.txt,1,0.5806250000000001,0.2658333333333333,0.02625,0.035
+1327,00487.txt,0,0.295,0.4625,0.075,0.075
+1328,00488.txt,0,0.5025000000000001,0.2841666666666667,0.055,0.0916666666666666
+1329,00488.txt,1,0.66125,0.0733333333333333,0.02,0.0266666666666666
+1330,00489.txt,2,0.93625,0.4283333333333333,0.0375,0.0666666666666666
+1331,00489.txt,1,0.735,0.1433333333333333,0.015,0.02
+1332,00489.txt,3,0.144375,0.1333333333333333,0.06625,0.0966666666666666
+1333,00490.txt,0,0.950625,0.515,0.04625,0.0566666666666666
+1334,00491.txt,2,0.165625,0.7925000000000001,0.03875,0.045
+1335,00492.txt,3,0.5962500000000001,0.45,0.0575,0.07
+1336,00493.txt,3,0.376875,0.4758333333333334,0.05125,0.065
+1337,00493.txt,4,0.100625,0.3308333333333333,0.04375,0.0483333333333333
+1338,00493.txt,1,0.955625,0.6983333333333334,0.02375,0.03
+1339,00494.txt,3,0.0375,0.5091666666666667,0.0675,0.0883333333333333
+1340,00495.txt,1,0.8625,0.29,0.02,0.0266666666666666
+1341,00496.txt,0,0.25375,0.3816666666666667,0.075,0.0766666666666666
+1342,00497.txt,2,0.923125,0.4233333333333333,0.07625,0.0633333333333333
+1343,00497.txt,4,0.050625,0.8225,0.04625,0.0616666666666666
+1344,00498.txt,2,0.6675,0.4491666666666667,0.05,0.055
+1345,00499.txt,4,0.0225,0.5416666666666667,0.045,0.0766666666666666
+1346,00499.txt,1,0.354375,0.54,0.02375,0.03
+1347,00500.txt,4,0.984375,0.5483333333333333,0.02875,0.07
+1348,00501.txt,2,0.52875,0.3791666666666667,0.055,0.0516666666666666
+1349,00501.txt,1,0.794375,0.7833333333333334,0.01625,0.02
+1350,00502.txt,1,0.180625,0.755,0.02875,0.04
+1351,00503.txt,4,0.34625,0.5866666666666667,0.0475,0.0633333333333333
+1352,00503.txt,4,0.755,0.4266666666666667,0.0575,0.0733333333333333
+1353,00504.txt,0,0.65125,0.455,0.0575,0.0933333333333333
+1354,00504.txt,0,0.698125,0.4533333333333333,0.05625,0.0766666666666666
+1355,00505.txt,0,0.05625,0.5516666666666667,0.0825,0.1133333333333333
+1356,00505.txt,3,0.8250000000000001,0.6766666666666667,0.0525,0.07
+1357,00506.txt,1,0.874375,0.3308333333333333,0.03125,0.0383333333333333
+1358,00507.txt,5,0.286875,0.4358333333333333,0.08125,0.105
+1359,00507.txt,1,0.92,0.4258333333333333,0.0325,0.045
+1360,00508.txt,2,0.424375,0.1925,0.04125,0.045
+1361,00508.txt,1,0.028125,0.1683333333333333,0.02375,0.0266666666666666
+1362,00509.txt,2,0.37375,0.1725,0.05,0.0483333333333333
+1363,00509.txt,1,0.704375,0.09,0.02375,0.0333333333333333
+1364,00510.txt,4,0.57125,0.4991666666666667,0.05,0.065
+1365,00510.txt,1,0.879375,0.5325000000000001,0.03125,0.0416666666666666
+1366,00511.txt,2,0.370625,0.5058333333333334,0.06125,0.0583333333333333
+1367,00511.txt,4,0.908125,0.3216666666666667,0.05125,0.0666666666666666
+1368,00512.txt,2,0.389375,0.7333333333333334,0.05625,0.05
+1369,00512.txt,3,0.914375,0.235,0.04875,0.0633333333333333
+1370,00513.txt,3,0.348125,0.7541666666666668,0.05375,0.085
+1371,00514.txt,2,0.04,0.5141666666666667,0.055,0.0616666666666666
+1372,00514.txt,4,0.738125,0.4058333333333334,0.05375,0.065
+1373,00514.txt,1,0.56,0.5433333333333333,0.0225,0.03
+1374,00514.txt,1,0.5387500000000001,0.5408333333333334,0.0175,0.025
+1375,00514.txt,1,0.944375,0.5733333333333334,0.01875,0.0233333333333333
+1376,00515.txt,1,0.1125,0.4808333333333334,0.0375,0.035
+1377,00515.txt,1,0.088125,0.4625,0.02375,0.0283333333333333
+1378,00516.txt,1,0.11,0.75,0.0225,0.03
+1379,00516.txt,1,0.7262500000000001,0.4625,0.03,0.0316666666666666
+1380,00516.txt,1,0.13125,0.7491666666666668,0.02,0.025
+1381,00517.txt,3,0.658125,0.475,0.05375,0.07
+1382,00518.txt,0,0.529375,0.2083333333333333,0.06875,0.09
+1383,00518.txt,1,0.790625,0.4958333333333333,0.02375,0.0383333333333333
+1384,00519.txt,5,0.386875,0.8716666666666667,0.11375,0.1066666666666666
+1385,00520.txt,2,0.10875,0.9058333333333334,0.0475,0.0416666666666666
+1386,00520.txt,1,0.475,0.4441666666666667,0.015,0.0216666666666666
+1387,00521.txt,5,0.031875,0.8325,0.06375,0.1083333333333333
+1388,00522.txt,1,0.174375,0.6233333333333334,0.03375,0.04
+1389,00522.txt,1,0.8675,0.5883333333333334,0.02,0.0266666666666666
+1390,00523.txt,0,0.330625,0.6375000000000001,0.05625,0.0683333333333333
+1391,00523.txt,1,0.104375,0.4733333333333334,0.03625,0.05
+1392,00524.txt,0,0.4275,0.6816666666666668,0.075,0.09
+1393,00525.txt,2,0.1375,0.8141666666666667,0.0425,0.0483333333333333
+1394,00525.txt,4,0.0275,0.5366666666666667,0.0525,0.0666666666666666
+1395,00526.txt,2,0.8718750000000001,0.4175,0.03125,0.0416666666666666
+1396,00527.txt,2,0.151875,0.7391666666666667,0.04375,0.0383333333333333
+1397,00528.txt,2,0.415625,0.2758333333333334,0.05125,0.045
+1398,00529.txt,1,0.061875,0.5583333333333333,0.02875,0.0366666666666666
+1399,00530.txt,5,0.10125,0.7141666666666667,0.0925,0.1083333333333333
+1400,00531.txt,4,0.790625,0.6533333333333333,0.05625,0.0666666666666666
+1401,00532.txt,2,0.4875,0.4358333333333333,0.07,0.0483333333333333
+1402,00533.txt,0,0.2725,0.6283333333333334,0.03,0.0433333333333333
+1403,00534.txt,2,0.4025,0.8758333333333334,0.0425,0.0483333333333333
+1404,00535.txt,2,0.215625,0.5316666666666667,0.05125,0.0433333333333333
+1405,00536.txt,0,0.263125,0.5391666666666667,0.06625,0.0816666666666666
+1406,00536.txt,1,0.82375,0.7408333333333333,0.0175,0.0316666666666666
+1407,00536.txt,1,0.1775,0.7941666666666667,0.02,0.025
+1408,00537.txt,0,0.115625,0.3416666666666667,0.03625,0.0366666666666666
+1409,00538.txt,2,0.365,0.7666666666666667,0.065,0.0566666666666666
+1410,00539.txt,4,0.9275,0.3616666666666667,0.0425,0.0566666666666666
+1411,00540.txt,5,0.645625,0.4858333333333333,0.12125,0.1483333333333333
+1412,00540.txt,3,0.106875,0.6166666666666667,0.05625,0.0733333333333333
+1413,00541.txt,3,0.355625,0.5583333333333333,0.05125,0.07
+1414,00542.txt,2,0.97125,0.8125,0.055,0.0583333333333333
+1415,00542.txt,4,0.58,0.7008333333333334,0.0475,0.065
+1416,00542.txt,3,0.349375,0.3558333333333333,0.05625,0.085
+1417,00543.txt,2,0.029375,0.6916666666666668,0.04875,0.0666666666666666
+1418,00544.txt,1,0.324375,0.6283333333333334,0.03625,0.04
+1419,00545.txt,2,0.47125,0.7033333333333334,0.025,0.0533333333333333
+1420,00546.txt,5,0.21875,0.44,0.1425,0.18
+1421,00547.txt,2,0.34375,0.4691666666666667,0.0575,0.0783333333333333
+1422,00547.txt,1,0.62875,0.1316666666666666,0.0225,0.0233333333333333
+1423,00548.txt,5,0.689375,0.43,0.07875,0.1033333333333333
+1424,00549.txt,2,0.2975,0.345,0.0325,0.0633333333333333
+1425,00549.txt,4,0.224375,0.8625,0.05125,0.0683333333333333
+1426,00549.txt,1,0.870625,0.4583333333333333,0.02375,0.0266666666666666
+1427,00550.txt,0,0.54875,0.6966666666666667,0.0775,0.0833333333333333
+1428,00551.txt,0,0.858125,0.6208333333333333,0.09375,0.0916666666666666
+1429,00552.txt,3,0.6012500000000001,0.4683333333333334,0.06,0.0866666666666666
+1430,00552.txt,1,0.5593750000000001,0.4516666666666667,0.02375,0.04
+1431,00553.txt,4,0.32,0.5333333333333333,0.055,0.0633333333333333
+1432,00554.txt,5,0.426875,0.7125,0.06875,0.0916666666666666
+1433,00554.txt,1,0.776875,0.5841666666666667,0.01875,0.0283333333333333
+1434,00555.txt,0,0.5375,0.1591666666666666,0.085,0.105
+1435,00556.txt,0,0.854375,0.7400000000000001,0.04375,0.0433333333333333
+1436,00557.txt,0,0.57125,0.4958333333333333,0.065,0.0716666666666666
+1437,00557.txt,3,0.61625,0.5458333333333334,0.0575,0.065
+1438,00557.txt,1,0.18,0.4291666666666667,0.025,0.035
+1439,00558.txt,3,0.5725,0.5941666666666667,0.045,0.0583333333333333
+1440,00558.txt,1,0.7925,0.5033333333333334,0.0275,0.03
+1441,00558.txt,1,0.77875,0.5375000000000001,0.0225,0.0283333333333333
+1442,00559.txt,1,0.74875,0.6091666666666667,0.035,0.035
+1443,00559.txt,4,0.69375,0.2391666666666667,0.0225,0.0316666666666666
+1444,00560.txt,0,0.18875,0.645,0.06,0.0933333333333333
+1445,00561.txt,2,0.296875,0.3691666666666667,0.04125,0.0583333333333333
+1446,00562.txt,3,0.420625,0.215,0.05625,0.0666666666666666
+1447,00563.txt,3,0.726875,0.3891666666666667,0.06375,0.0816666666666666
+1448,00564.txt,5,0.044375,0.4441666666666667,0.08875,0.185
+1449,00565.txt,2,0.605625,0.1016666666666666,0.05375,0.0466666666666666
+1450,00565.txt,1,0.195625,0.3991666666666666,0.02625,0.0383333333333333
+1451,00566.txt,2,0.363125,0.2316666666666667,0.03625,0.0733333333333333
+1452,00567.txt,1,0.250625,0.1808333333333333,0.02125,0.025
+1453,00568.txt,3,0.015,0.225,0.03,0.0633333333333333
+1454,00568.txt,1,0.015,0.1891666666666666,0.0275,0.0283333333333333
+1455,00569.txt,4,0.3275,0.6858333333333334,0.0475,0.0583333333333333
+1456,00569.txt,1,0.56125,0.3708333333333333,0.02,0.0216666666666666
+1457,00570.txt,0,0.290625,0.4025,0.07125,0.0816666666666666
+1458,00570.txt,0,0.365,0.4908333333333333,0.0625,0.0683333333333333
+1459,00571.txt,2,0.771875,0.5691666666666667,0.04125,0.0483333333333333
+1460,00571.txt,1,0.255625,0.15,0.02875,0.0333333333333333
+1461,00572.txt,3,0.8275,0.2291666666666666,0.0425,0.055
+1462,00572.txt,1,0.824375,0.1891666666666666,0.03625,0.045
+1463,00573.txt,2,0.793125,0.4108333333333334,0.03625,0.055
+1464,00574.txt,3,0.4125,0.915,0.04,0.05
+1465,00574.txt,1,0.351875,0.5291666666666667,0.02875,0.0316666666666666
+1466,00574.txt,1,0.24,0.4675,0.0175,0.0216666666666666
+1467,00575.txt,3,0.056875,0.7266666666666667,0.06375,0.0966666666666666
+1468,00576.txt,5,0.52375,0.625,0.1175,0.1466666666666666
+1469,00576.txt,1,0.105,0.76,0.02,0.03
+1470,00576.txt,1,0.869375,0.2241666666666666,0.01875,0.0283333333333333
+1471,00577.txt,1,0.589375,0.5633333333333334,0.01875,0.0233333333333333
+1472,00577.txt,4,0.399375,0.6491666666666667,0.04625,0.0616666666666666
+1473,00578.txt,1,0.21625,0.765,0.0325,0.0433333333333333
+1474,00578.txt,3,0.421875,0.8866666666666667,0.02375,0.0333333333333333
+1475,00579.txt,3,0.8725,0.3258333333333333,0.065,0.075
+1476,00579.txt,1,0.833125,0.3383333333333334,0.02125,0.03
+1477,00580.txt,4,0.685625,0.5575,0.03625,0.055
+1478,00581.txt,4,0.21375,0.55,0.05,0.06
+1479,00581.txt,1,0.1325,0.8158333333333334,0.025,0.0316666666666666
+1480,00582.txt,1,0.325625,0.0858333333333333,0.02875,0.0383333333333333
+1481,00582.txt,4,0.655,0.3933333333333333,0.0525,0.07
+1482,00582.txt,1,0.701875,0.8300000000000001,0.02875,0.0433333333333333
+1483,00583.txt,1,0.9725,0.0841666666666666,0.0275,0.0316666666666666
+1484,00584.txt,2,0.62125,0.2491666666666666,0.0375,0.055
+1485,00584.txt,1,0.90625,0.5216666666666667,0.0325,0.04
+1486,00585.txt,4,0.67375,0.5733333333333334,0.0525,0.0666666666666666
+1487,00585.txt,1,0.98875,0.2225,0.0125,0.015
+1488,00586.txt,4,0.235,0.3458333333333334,0.04,0.0483333333333333
+1489,00587.txt,4,0.33125,0.2233333333333333,0.035,0.0433333333333333
+1490,00587.txt,1,0.764375,0.7716666666666667,0.02125,0.0266666666666666
+1491,00588.txt,3,0.490625,0.6466666666666667,0.04125,0.06
+1492,00589.txt,3,0.975625,0.535,0.04625,0.0833333333333333
+1493,00589.txt,4,0.98,0.6308333333333334,0.0375,0.0716666666666666
+1494,00590.txt,2,0.636875,0.2083333333333333,0.04125,0.06
+1495,00591.txt,4,0.568125,0.55,0.04625,0.0633333333333333
+1496,00591.txt,1,0.681875,0.8600000000000001,0.03375,0.0433333333333333
+1497,00592.txt,3,0.8225,0.325,0.0775,0.0866666666666666
+1498,00593.txt,0,0.308125,0.4191666666666667,0.07875,0.1016666666666666
+1499,00594.txt,4,0.305625,0.2325,0.05125,0.065
+1500,00594.txt,1,0.8306250000000001,0.9325,0.02125,0.0283333333333333
+1501,00595.txt,2,0.424375,0.4391666666666667,0.03375,0.0383333333333333
+1502,00595.txt,4,0.210625,0.5141666666666667,0.05125,0.065
+1503,00596.txt,3,0.5075000000000001,0.6708333333333334,0.0575,0.075
+1504,00597.txt,1,0.395,0.56,0.0275,0.0333333333333333
+1505,00597.txt,3,0.344375,0.5883333333333334,0.07625,0.0866666666666666
+1506,00598.txt,3,0.49,0.8608333333333333,0.0625,0.0783333333333333
+1507,00598.txt,4,0.628125,0.5683333333333334,0.05125,0.0666666666666666
+1508,00599.txt,4,0.7887500000000001,0.7591666666666668,0.0475,0.0683333333333333
+1509,00599.txt,1,0.210625,0.7708333333333334,0.02125,0.025
+1510,00600.txt,0,0.36125,0.7516666666666667,0.07,0.1033333333333333
+1511,00601.txt,3,0.6385416666666667,0.6075,0.0541666666666666,0.0816666666666666
+1512,00601.txt,3,0.5921875,0.6483333333333334,0.065625,0.1066666666666666
+1513,00601.txt,1,0.93125,0.25,0.03125,0.0466666666666666
+1514,00601.txt,0,0.9265625,0.2041666666666667,0.046875,0.0583333333333333
+1515,00602.txt,5,0.6692708333333334,0.3433333333333334,0.1302083333333333,0.1933333333333333
+1516,00602.txt,4,0.6708333333333333,0.8958333333333334,0.0458333333333333,0.075
+1517,00603.txt,4,0.0973958333333333,0.56,0.0364583333333333,0.0566666666666666
+1518,00603.txt,1,0.775,0.5425,0.01875,0.0283333333333333
+1519,00604.txt,5,0.3729166666666667,0.4483333333333333,0.075,0.1033333333333333
+1520,00604.txt,3,0.8151041666666666,0.6758333333333334,0.0635416666666666,0.085
+1521,00605.txt,2,0.034375,0.0933333333333333,0.0520833333333333,0.08
+1522,00605.txt,3,0.3145833333333333,0.8158333333333334,0.0645833333333333,0.0916666666666666
+1523,00605.txt,0,0.5723958333333333,0.5341666666666667,0.0572916666666666,0.085
+1524,00606.txt,5,0.69375,0.1983333333333333,0.11875,0.17
+1525,00606.txt,1,0.1890625,0.135,0.0302083333333333,0.0433333333333333
+1526,00607.txt,5,0.9473958333333332,0.2033333333333333,0.084375,0.1433333333333333
+1527,00607.txt,1,0.8755208333333333,0.7575000000000001,0.0260416666666666,0.0383333333333333
+1528,00607.txt,4,0.2427083333333333,0.6808333333333334,0.0416666666666666,0.0683333333333333
+1529,00607.txt,1,0.6432291666666666,0.5025000000000001,0.015625,0.025
+1530,00607.txt,2,0.8494791666666667,0.5641666666666667,0.0322916666666666,0.0216666666666666
+1531,00608.txt,2,0.8390624999999999,0.4708333333333334,0.0552083333333333,0.055
+1532,00608.txt,1,0.9411458333333332,0.5908333333333333,0.0239583333333333,0.0383333333333333
+1533,00609.txt,1,0.6963541666666666,0.6433333333333334,0.021875,0.0333333333333333
+1534,00609.txt,4,0.2536458333333333,0.2625,0.0385416666666666,0.0583333333333333
+1535,00610.txt,0,0.3536458333333333,0.4858333333333333,0.0447916666666666,0.0683333333333333
+1536,00610.txt,1,0.3588541666666666,0.2233333333333333,0.0197916666666666,0.03
+1537,00611.txt,2,0.6416666666666666,0.2891666666666667,0.0395833333333333,0.0783333333333333
+1538,00611.txt,1,0.7369791666666666,0.2216666666666666,0.0239583333333333,0.0366666666666666
+1539,00612.txt,1,0.8192708333333333,0.8650000000000001,0.021875,0.0366666666666666
+1540,00612.txt,3,0.65625,0.0783333333333333,0.0479166666666666,0.07
+1541,00613.txt,3,0.9359375,0.0775,0.0447916666666666,0.065
+1542,00613.txt,1,0.1671875,0.2858333333333333,0.0260416666666666,0.0483333333333333
+1543,00614.txt,1,0.5880208333333333,0.5825,0.0322916666666666,0.0516666666666666
+1544,00614.txt,1,0.5489583333333333,0.8366666666666667,0.0166666666666666,0.0266666666666666
+1545,00614.txt,0,0.4041666666666667,0.6141666666666667,0.0520833333333333,0.0683333333333333
+1546,00615.txt,2,0.04375,0.5800000000000001,0.0541666666666666,0.0566666666666666
+1547,00615.txt,3,0.1,0.5833333333333334,0.0520833333333333,0.0833333333333333
+1548,00615.txt,4,0.1010416666666666,0.4575,0.0375,0.0583333333333333
+1549,00616.txt,1,0.5567708333333333,0.6841666666666667,0.0302083333333333,0.0483333333333333
+1550,00616.txt,1,0.3020833333333333,0.8758333333333334,0.0208333333333333,0.0316666666666666
+1551,00617.txt,5,0.9125,0.2408333333333333,0.1145833333333333,0.1583333333333333
+1552,00617.txt,4,0.8020833333333334,0.275,0.0458333333333333,0.07
+1553,00617.txt,1,0.3333333333333333,0.9191666666666668,0.0145833333333333,0.0216666666666666
+1554,00618.txt,2,0.4848958333333333,0.6383333333333334,0.0552083333333333,0.05
+1555,00618.txt,3,0.1890625,0.5475,0.0510416666666666,0.0683333333333333
+1556,00618.txt,4,0.2312499999999999,0.3816666666666667,0.0395833333333333,0.06
+1557,00618.txt,1,0.953125,0.9258333333333334,0.0166666666666666,0.0283333333333333
+1558,00619.txt,0,0.2880208333333333,0.3633333333333333,0.059375,0.09
+1559,00619.txt,1,0.9901041666666668,0.1358333333333333,0.0177083333333333,0.0316666666666666
+1560,00620.txt,2,0.6036458333333333,0.8133333333333334,0.065625,0.05
+1561,00620.txt,4,0.4317708333333333,0.6733333333333333,0.0385416666666666,0.06
+1562,00620.txt,1,0.825,0.1183333333333333,0.01875,0.0266666666666666
+1563,00620.txt,1,0.0635416666666666,0.6916666666666668,0.0166666666666666,0.0266666666666666
+1564,00621.txt,4,0.9786458333333332,0.1816666666666666,0.040625,0.0733333333333333
+1565,00621.txt,4,0.5296875,0.44,0.0427083333333333,0.0666666666666666
+1566,00621.txt,3,0.4312499999999999,0.4075,0.0291666666666666,0.0483333333333333
+1567,00622.txt,0,0.4098958333333333,0.8550000000000001,0.065625,0.0766666666666666
+1568,00622.txt,3,0.1953125,0.1316666666666666,0.0447916666666666,0.08
+1569,00623.txt,5,0.6765625,0.2825,0.0927083333333333,0.155
+1570,00624.txt,1,0.4359375,0.305,0.0177083333333333,0.0266666666666666
+1571,00624.txt,2,0.2807291666666666,0.7241666666666667,0.0489583333333333,0.055
+1572,00625.txt,5,0.3979166666666666,0.365,0.11875,0.1733333333333333
+1573,00626.txt,4,0.9145833333333332,0.6891666666666667,0.05,0.075
+1574,00626.txt,3,0.5614583333333333,0.8916666666666667,0.0625,0.0833333333333333
+1575,00626.txt,3,0.4708333333333333,0.8925000000000001,0.0645833333333333,0.1016666666666666
+1576,00626.txt,1,0.2166666666666666,0.3475,0.01875,0.0316666666666666
+1577,00626.txt,1,0.2083333333333333,0.3308333333333333,0.0166666666666666,0.025
+1578,00627.txt,0,0.5015625,0.6975,0.0552083333333333,0.0983333333333333
+1579,00627.txt,0,0.4713541666666667,0.6383333333333334,0.0572916666666666,0.09
+1580,00627.txt,0,0.359375,0.6925,0.0520833333333333,0.0916666666666666
+1581,00627.txt,4,0.2932291666666666,0.675,0.046875,0.0666666666666666
+1582,00627.txt,3,0.1994791666666666,0.6108333333333333,0.0489583333333333,0.0783333333333333
+1583,00628.txt,2,0.1635416666666666,0.2333333333333333,0.05,0.0566666666666666
+1584,00629.txt,5,0.4338541666666666,0.4008333333333334,0.1072916666666666,0.175
+1585,00629.txt,0,0.0359375,0.1575,0.065625,0.115
+1586,00630.txt,2,0.5088541666666666,0.5083333333333334,0.0552083333333333,0.0433333333333333
+1587,00630.txt,1,0.0453125,0.5591666666666667,0.021875,0.035
+1588,00631.txt,0,0.1390625,0.6433333333333334,0.0572916666666666,0.0766666666666666
+1589,00631.txt,3,0.2307291666666666,0.8191666666666667,0.0635416666666666,0.0916666666666666
+1590,00632.txt,0,0.596875,0.81,0.06875,0.11
+1591,00633.txt,2,0.6348958333333333,0.8883333333333334,0.0572916666666666,0.0766666666666666
+1592,00633.txt,1,0.7135416666666666,0.7916666666666667,0.01875,0.0266666666666666
+1593,00633.txt,3,0.0411458333333333,0.7691666666666667,0.0552083333333333,0.085
+1594,00634.txt,2,0.2270833333333333,0.2766666666666666,0.0416666666666666,0.0633333333333333
+1595,00634.txt,0,0.121875,0.22,0.0604166666666666,0.1033333333333333
+1596,00634.txt,1,0.3255208333333333,0.0858333333333333,0.0197916666666666,0.035
+1597,00634.txt,2,0.9390625,0.8350000000000001,0.0489583333333333,0.0533333333333333
+1598,00635.txt,5,0.8270833333333333,0.1333333333333333,0.125,0.19
+1599,00635.txt,1,0.7661458333333333,0.8650000000000001,0.0239583333333333,0.0433333333333333
+1600,00636.txt,2,0.9359375,0.8341666666666667,0.0510416666666666,0.045
+1601,00636.txt,1,0.4744791666666667,0.7150000000000001,0.0177083333333333,0.0266666666666666
+1602,00637.txt,0,0.121875,0.6066666666666667,0.0625,0.0833333333333333
+1603,00637.txt,1,0.196875,0.0833333333333333,0.025,0.04
+1604,00637.txt,3,0.884375,0.7583333333333334,0.0541666666666666,0.0833333333333333
+1605,00638.txt,3,0.1666666666666666,0.6725000000000001,0.0541666666666666,0.085
+1606,00638.txt,0,0.521875,0.2916666666666667,0.0625,0.08
+1607,00638.txt,4,0.6302083333333334,0.3058333333333333,0.0333333333333333,0.055
+1608,00638.txt,3,0.5838541666666667,0.3366666666666666,0.0760416666666666,0.1233333333333333
+1609,00639.txt,2,0.6916666666666667,0.5483333333333333,0.0604166666666666,0.0566666666666666
+1610,00639.txt,4,0.3453125,0.1775,0.0385416666666666,0.0616666666666666
+1611,00640.txt,4,0.8916666666666666,0.4858333333333333,0.0458333333333333,0.0683333333333333
+1612,00640.txt,1,0.3385416666666667,0.2133333333333333,0.01875,0.03
+1613,00641.txt,1,0.3520833333333333,0.5875,0.01875,0.0316666666666666
+1614,00641.txt,4,0.18125,0.7358333333333333,0.0479166666666666,0.075
+1615,00642.txt,2,0.7635416666666667,0.9116666666666668,0.0541666666666666,0.0533333333333333
+1616,00643.txt,3,0.4151041666666666,0.4741666666666667,0.046875,0.0783333333333333
+1617,00643.txt,5,0.0567708333333333,0.4841666666666667,0.0989583333333333,0.1283333333333333
+1618,00644.txt,2,0.0651041666666666,0.7816666666666667,0.0489583333333333,0.0733333333333333
+1619,00644.txt,1,0.0755208333333333,0.6816666666666668,0.028125,0.04
+1620,00645.txt,5,0.7098958333333333,0.4516666666666667,0.1197916666666666,0.22
+1621,00645.txt,0,0.0692708333333333,0.5641666666666667,0.0635416666666666,0.105
+1622,00645.txt,0,0.0255208333333333,0.545,0.0510416666666666,0.1
+1623,00645.txt,1,0.3036458333333333,0.1716666666666667,0.021875,0.0366666666666666
+1624,00646.txt,5,0.0515625,0.3983333333333334,0.103125,0.1933333333333333
+1625,00647.txt,1,0.7520833333333333,0.5141666666666667,0.0208333333333333,0.035
+1626,00647.txt,4,0.7067708333333333,0.5633333333333334,0.0385416666666666,0.06
+1627,00647.txt,0,0.5260416666666666,0.5166666666666667,0.0583333333333333,0.0766666666666666
+1628,00648.txt,3,0.7598958333333333,0.4041666666666667,0.053125,0.0783333333333333
+1629,00648.txt,5,0.7234375,0.195,0.1260416666666666,0.1833333333333333
+1630,00649.txt,2,0.2463541666666666,0.6341666666666667,0.0302083333333333,0.065
+1631,00649.txt,1,0.9411458333333332,0.5666666666666667,0.0260416666666666,0.0433333333333333
+1632,00650.txt,5,0.5640625,0.3483333333333333,0.0885416666666666,0.1766666666666666
+1633,00651.txt,2,0.6869791666666667,0.5866666666666667,0.0572916666666666,0.0533333333333333
+1634,00651.txt,4,0.0338541666666666,0.535,0.046875,0.07
+1635,00651.txt,0,0.028125,0.32,0.05625,0.09
+1636,00651.txt,0,0.8692708333333333,0.0908333333333333,0.059375,0.085
+1637,00651.txt,3,0.9661458333333334,0.255,0.0489583333333333,0.0833333333333333
+1638,00652.txt,2,0.6317708333333333,0.7775000000000001,0.053125,0.0516666666666666
+1639,00653.txt,2,0.0859375,0.4883333333333333,0.046875,0.08
+1640,00653.txt,2,0.4994791666666666,0.17,0.0427083333333333,0.06
+1641,00654.txt,2,0.7734375,0.4766666666666667,0.0364583333333333,0.0433333333333333
+1642,00654.txt,1,0.7645833333333333,0.2083333333333333,0.0229166666666666,0.0366666666666666
+1643,00655.txt,2,0.4572916666666666,0.3716666666666667,0.0604166666666666,0.06
+1644,00656.txt,4,0.9244791666666666,0.355,0.0385416666666666,0.06
+1645,00656.txt,0,0.4083333333333333,0.3108333333333333,0.0729166666666666,0.1083333333333333
+1646,00656.txt,4,0.2114583333333333,0.5583333333333333,0.0395833333333333,0.0633333333333333
+1647,00657.txt,5,0.9104166666666668,0.2158333333333333,0.0979166666666666,0.1383333333333333
+1648,00658.txt,2,0.3541666666666667,0.7116666666666667,0.0416666666666666,0.0766666666666666
+1649,00659.txt,3,0.1921875,0.4,0.0572916666666666,0.0966666666666666
+1650,00659.txt,1,0.2598958333333333,0.1175,0.0177083333333333,0.0283333333333333
+1651,00660.txt,1,0.8515625,0.8025000000000001,0.0197916666666666,0.0316666666666666
+1652,00660.txt,1,0.8666666666666667,0.4066666666666667,0.0166666666666666,0.0266666666666666
+1653,00660.txt,1,0.1802083333333333,0.2375,0.0145833333333333,0.0216666666666666
+1654,00660.txt,1,0.0270833333333333,0.1358333333333333,0.0166666666666666,0.025
+1655,00660.txt,4,0.19375,0.5475,0.0395833333333333,0.0616666666666666
+1656,00660.txt,0,0.3630208333333333,0.5833333333333334,0.0614583333333333,0.0933333333333333
+1657,00661.txt,2,0.7052083333333333,0.5841666666666667,0.0416666666666666,0.0416666666666666
+1658,00661.txt,1,0.8541666666666666,0.2366666666666667,0.0166666666666666,0.0266666666666666
+1659,00661.txt,1,0.5864583333333333,0.1391666666666667,0.0166666666666666,0.025
+1660,00662.txt,4,0.4822916666666667,0.8025000000000001,0.04375,0.0683333333333333
+1661,00662.txt,1,0.0807291666666666,0.4616666666666666,0.028125,0.0433333333333333
+1662,00662.txt,3,0.5666666666666667,0.0875,0.0479166666666666,0.075
+1663,00663.txt,1,0.840625,0.1708333333333333,0.0208333333333333,0.0316666666666666
+1664,00663.txt,1,0.5072916666666667,0.7341666666666667,0.025,0.0383333333333333
+1665,00664.txt,5,0.3041666666666666,0.8108333333333334,0.1083333333333333,0.1483333333333333
+1666,00665.txt,0,0.5963541666666666,0.1625,0.0510416666666666,0.0916666666666666
+1667,00665.txt,4,0.9213541666666668,0.8458333333333334,0.0427083333333333,0.0683333333333333
+1668,00666.txt,4,0.8713541666666667,0.4291666666666667,0.0385416666666666,0.0616666666666666
+1669,00666.txt,1,0.9734375,0.3691666666666667,0.015625,0.025
+1670,00666.txt,1,0.6609375,0.66,0.0177083333333333,0.0266666666666666
+1671,00666.txt,1,0.2057291666666666,0.4141666666666667,0.0239583333333333,0.0383333333333333
+1672,00666.txt,3,0.3817708333333333,0.2875,0.0510416666666666,0.0783333333333333
+1673,00667.txt,5,0.1020833333333333,0.6483333333333334,0.0854166666666666,0.13
+1674,00668.txt,4,0.075,0.3516666666666667,0.0395833333333333,0.0566666666666666
+1675,00668.txt,3,0.8276041666666667,0.2608333333333333,0.0572916666666666,0.0783333333333333
+1676,00668.txt,1,0.4786458333333333,0.2925,0.0177083333333333,0.025
+1677,00668.txt,5,0.2822916666666666,0.8775000000000001,0.13125,0.1683333333333333
+1678,00669.txt,5,0.1776041666666666,0.8866666666666667,0.0927083333333333,0.14
+1679,00669.txt,3,0.5864583333333333,0.5,0.0395833333333333,0.0566666666666666
+1680,00670.txt,4,0.9713541666666666,0.8741666666666668,0.0510416666666666,0.0816666666666666
+1681,00670.txt,0,0.703125,0.3783333333333333,0.0625,0.07
+1682,00670.txt,4,0.6015625,0.1566666666666666,0.0239583333333333,0.04
+1683,00671.txt,1,0.134375,0.9116666666666668,0.0208333333333333,0.0333333333333333
+1684,00671.txt,1,0.7161458333333334,0.5691666666666667,0.0177083333333333,0.0283333333333333
+1685,00671.txt,3,0.8354166666666667,0.4366666666666667,0.0541666666666666,0.07
+1686,00671.txt,1,0.6994791666666667,0.3066666666666667,0.0260416666666666,0.04
+1687,00672.txt,1,0.709375,0.9116666666666668,0.01875,0.03
+1688,00672.txt,3,0.4708333333333333,0.9016666666666668,0.0625,0.0833333333333333
+1689,00672.txt,4,0.4515625,0.3758333333333333,0.0385416666666666,0.0616666666666666
+1690,00673.txt,5,0.2828125,0.1441666666666666,0.0989583333333333,0.1216666666666666
+1691,00673.txt,4,0.9328125,0.5666666666666667,0.0322916666666666,0.0566666666666666
+1692,00674.txt,5,0.2744791666666666,0.1616666666666666,0.1260416666666666,0.2066666666666667
+1693,00674.txt,1,0.5244791666666666,0.5941666666666667,0.0177083333333333,0.025
+1694,00674.txt,1,0.8828125,0.3425,0.015625,0.025
+1695,00675.txt,2,0.2614583333333333,0.7225,0.0395833333333333,0.045
+1696,00675.txt,3,0.746875,0.4041666666666667,0.0645833333333333,0.095
+1697,00676.txt,4,0.0953125,0.5541666666666667,0.040625,0.065
+1698,00676.txt,1,0.1177083333333333,0.9133333333333334,0.0270833333333333,0.0433333333333333
+1699,00676.txt,5,0.5291666666666667,0.3633333333333333,0.10625,0.1733333333333333
+1700,00677.txt,5,0.2770833333333333,0.1208333333333333,0.0604166666666666,0.0916666666666666
+1701,00678.txt,3,0.2104166666666666,0.8233333333333334,0.0625,0.0966666666666666
+1702,00679.txt,1,0.9005208333333333,0.8008333333333334,0.015625,0.025
+1703,00679.txt,2,0.5880208333333333,0.8741666666666668,0.0510416666666666,0.0616666666666666
+1704,00680.txt,1,0.2171875,0.115,0.0177083333333333,0.0266666666666666
+1705,00680.txt,5,0.9333333333333332,0.8266666666666668,0.1083333333333333,0.18
+1706,00681.txt,0,0.9208333333333332,0.165,0.0645833333333333,0.09
+1707,00681.txt,3,0.7916666666666666,0.1958333333333333,0.05,0.0916666666666666
+1708,00682.txt,2,0.178125,0.3808333333333333,0.0479166666666666,0.0516666666666666
+1709,00682.txt,2,0.1458333333333333,0.8175,0.05,0.045
+1710,00683.txt,5,0.2270833333333333,0.36,0.0833333333333333,0.12
+1711,00683.txt,3,0.6171875,0.4825,0.0552083333333333,0.0716666666666666
+1712,00684.txt,2,0.6666666666666666,0.8391666666666667,0.0625,0.0416666666666666
+1713,00684.txt,1,0.8645833333333334,0.7258333333333333,0.0208333333333333,0.035
+1714,00684.txt,4,0.5182291666666666,0.3625,0.0385416666666666,0.0583333333333333
+1715,00684.txt,1,0.2026041666666666,0.43,0.0177083333333333,0.0266666666666666
+1716,00685.txt,1,0.7067708333333333,0.4875,0.021875,0.035
+1717,00685.txt,3,0.1989583333333333,0.3866666666666667,0.0625,0.1
+1718,00686.txt,3,0.8744791666666667,0.3683333333333333,0.065625,0.09
+1719,00687.txt,3,0.4885416666666666,0.7783333333333334,0.0583333333333333,0.1066666666666666
+1720,00687.txt,4,0.4447916666666666,0.8991666666666667,0.0375,0.065
+1721,00688.txt,5,0.3390625,0.5575,0.0864583333333333,0.1083333333333333
+1722,00688.txt,1,0.7505208333333333,0.4441666666666667,0.028125,0.0416666666666666
+1723,00688.txt,4,0.7541666666666667,0.1958333333333333,0.0416666666666666,0.0616666666666666
+1724,00689.txt,5,0.3114583333333333,0.4425,0.0958333333333333,0.0983333333333333
+1725,00689.txt,3,0.0421875,0.9166666666666669,0.0677083333333333,0.0966666666666666
+1726,00690.txt,3,0.4546874999999999,0.9166666666666669,0.0635416666666666,0.0966666666666666
+1727,00690.txt,1,0.4057291666666666,0.1175,0.0177083333333333,0.025
+1728,00690.txt,1,0.4140625,0.1391666666666667,0.015625,0.025
+1729,00690.txt,1,0.4010416666666667,0.1458333333333333,0.01875,0.0283333333333333
+1730,00690.txt,2,0.1916666666666666,0.5075000000000001,0.0375,0.0483333333333333
+1731,00691.txt,5,0.553125,0.8141666666666667,0.1,0.1383333333333333
+1732,00691.txt,4,0.6796875,0.8841666666666668,0.0447916666666666,0.0683333333333333
+1733,00692.txt,5,0.4411458333333333,0.7233333333333334,0.134375,0.1733333333333333
+1734,00693.txt,2,0.4651041666666666,0.5891666666666667,0.0427083333333333,0.0416666666666666
+1735,00693.txt,5,0.5625,0.53,0.0958333333333333,0.12
+1736,00693.txt,4,0.2671875,0.4141666666666667,0.0385416666666666,0.0583333333333333
+1737,00693.txt,1,0.784375,0.5325000000000001,0.0208333333333333,0.0283333333333333
+1738,00694.txt,1,0.7348958333333333,0.1516666666666666,0.0177083333333333,0.0266666666666666
+1739,00694.txt,1,0.2984375,0.5766666666666667,0.0239583333333333,0.04
+1740,00694.txt,4,0.3234375,0.4208333333333333,0.0447916666666666,0.0683333333333333
+1741,00694.txt,3,0.5807291666666666,0.785,0.0510416666666666,0.0833333333333333
+1742,00695.txt,5,0.421875,0.89,0.08125,0.11
+1743,00695.txt,4,0.0130208333333333,0.1183333333333333,0.0260416666666666,0.0466666666666666
+1744,00696.txt,5,0.1932291666666666,0.375,0.1010416666666666,0.15
+1745,00696.txt,3,0.4989583333333333,0.3775,0.0666666666666666,0.0916666666666666
+1746,00697.txt,1,0.9421875,0.7091666666666667,0.0197916666666666,0.0316666666666666
+1747,00697.txt,0,0.9026041666666668,0.8016666666666667,0.0385416666666666,0.0566666666666666
+1748,00697.txt,0,0.0953125,0.14,0.0677083333333333,0.0866666666666666
+1749,00697.txt,1,0.9901041666666668,0.2025,0.0177083333333333,0.0316666666666666
+1750,00698.txt,3,0.2354166666666666,0.2891666666666667,0.0541666666666666,0.075
+1751,00698.txt,4,0.6380208333333334,0.5225000000000001,0.0364583333333333,0.0583333333333333
+1752,00699.txt,0,0.7692708333333333,0.7675000000000001,0.0677083333333333,0.085
+1753,00699.txt,3,0.4624999999999999,0.9066666666666668,0.0541666666666666,0.1033333333333333
+1754,00699.txt,4,0.3052083333333333,0.7708333333333334,0.0354166666666666,0.055
+1755,00700.txt,0,0.0385416666666666,0.6208333333333333,0.0708333333333333,0.075
+1756,00700.txt,0,0.0359375,0.1825,0.0635416666666666,0.105
+1757,00700.txt,4,0.5328125,0.1825,0.0447916666666666,0.065
diff --git a/High Throughput Algae Cell Detection/Images/NON_YOLO_RESULTS.png b/High Throughput Algae Cell Detection/Images/NON_YOLO_RESULTS.png
new file mode 100644
index 000000000..bf7fee23c
Binary files /dev/null and b/High Throughput Algae Cell Detection/Images/NON_YOLO_RESULTS.png differ
diff --git a/High Throughput Algae Cell Detection/Images/PR_curve.png b/High Throughput Algae Cell Detection/Images/PR_curve.png
new file mode 100644
index 000000000..6563254fb
Binary files /dev/null and b/High Throughput Algae Cell Detection/Images/PR_curve.png differ
diff --git a/High Throughput Algae Cell Detection/Images/P_curve.png b/High Throughput Algae Cell Detection/Images/P_curve.png
new file mode 100644
index 000000000..474fb2837
Binary files /dev/null and b/High Throughput Algae Cell Detection/Images/P_curve.png differ
diff --git a/High Throughput Algae Cell Detection/Images/R_curve.png b/High Throughput Algae Cell Detection/Images/R_curve.png
new file mode 100644
index 000000000..c706fea09
Binary files /dev/null and b/High Throughput Algae Cell Detection/Images/R_curve.png differ
diff --git a/High Throughput Algae Cell Detection/Images/confusion_matrix.png b/High Throughput Algae Cell Detection/Images/confusion_matrix.png
new file mode 100644
index 000000000..d66d8f540
Binary files /dev/null and b/High Throughput Algae Cell Detection/Images/confusion_matrix.png differ
diff --git a/High Throughput Algae Cell Detection/Images/labels.jpg b/High Throughput Algae Cell Detection/Images/labels.jpg
new file mode 100644
index 000000000..6df865fb2
Binary files /dev/null and b/High Throughput Algae Cell Detection/Images/labels.jpg differ
diff --git a/High Throughput Algae Cell Detection/Images/results.png b/High Throughput Algae Cell Detection/Images/results.png
new file mode 100644
index 000000000..b17f7629e
Binary files /dev/null and b/High Throughput Algae Cell Detection/Images/results.png differ
diff --git a/High Throughput Algae Cell Detection/Images/val_batch2_pred.jpg b/High Throughput Algae Cell Detection/Images/val_batch2_pred.jpg
new file mode 100644
index 000000000..1701d8416
Binary files /dev/null and b/High Throughput Algae Cell Detection/Images/val_batch2_pred.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/ConvNeXtTiny.ipynb b/High Throughput Algae Cell Detection/Model/ConvNeXtTiny.ipynb
new file mode 100644
index 000000000..6b6779405
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/ConvNeXtTiny.ipynb	
@@ -0,0 +1,679 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# ConvNeXtTiny Model Transfer Learning"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import tensorflow as tf\n",
+    "from tensorflow import keras\n",
+    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+    "import matplotlib.pyplot as plt\n",
+    "from tensorflow.keras import layers, models\n",
+    "from tensorflow.keras.applications import ConvNeXtTiny\n",
+    "from tensorflow.keras.optimizers import Adam\n",
+    "import seaborn as sns\n",
+    "import numpy as np\n",
+    "from sklearn.utils.class_weight import compute_class_weight\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found 1758 images belonging to 6 classes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "train_datagen = ImageDataGenerator(\n",
+    "        rescale=1./255)\n",
+    "train_generator = train_datagen.flow_from_directory(\n",
+    "    directory=r\"D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\non_yolo\",\n",
+    "    target_size=(71,71),\n",
+    "    color_mode=\"rgb\",\n",
+    "    batch_size=64,\n",
+    "    class_mode=\"categorical\",\n",
+    "    shuffle=True,\n",
+    "    seed=42\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Class Distribution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "class_indices = train_generator.class_indices\n",
+    "\n",
+    "class_names = {v: k for k, v in class_indices.items()}\n",
+    "\n",
+    "class_distribution = train_generator.classes\n",
+    "\n",
+    "class_names_list = [class_names[class_idx] for class_idx in class_distribution]\n",
+    "\n",
+    "# Plot the class distribution using Seaborn\n",
+    "plt.figure(figsize=(10, 5))\n",
+    "sns.countplot(x=class_names_list, palette='viridis')\n",
+    "plt.title('Class Distribution in the Training Dataset')\n",
+    "plt.xlabel('Class')\n",
+    "plt.ylabel('Number of Samples')\n",
+    "plt.xticks(rotation='vertical')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Class Weights: [1.5923913  0.40581717 1.25213675 1.2907489  1.07720588 2.46218487]\n"
+     ]
+    }
+   ],
+   "source": [
+    "class_labels = train_generator.classes\n",
+    "class_weights = compute_class_weight(class_weight='balanced', classes=np.unique(class_labels), y=class_labels)\n",
+    "\n",
+    "print(\"Class Weights:\", class_weights)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{0: 1.5923913043478262,\n",
+       " 1: 0.40581717451523547,\n",
+       " 2: 1.2521367521367521,\n",
+       " 3: 1.2907488986784141,\n",
+       " 4: 1.0772058823529411,\n",
+       " 5: 2.46218487394958}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "class_weight_dict = {i: class_weights[i] for i in range(len(class_weights))}\n",
+    "class_weight_dict"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "- ##### This inverse proportion from our original distribution indicates Class_weight multiple requires for all class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "class_weights = [1.5923913, 0.40581717, 1.25213675, 1.2907489, 1.07720588, 2.46218487]\n",
+    "class_names_list = ['Class 0', 'Class 1', 'Class 2', 'Class 3', 'Class 4', 'Class 5']\n",
+    "\n",
+    "# Create a DataFrame for Seaborn\n",
+    "data = {'Class': class_names_list, 'Weight': class_weights}\n",
+    "df = pd.DataFrame(data)\n",
+    "# Plot the class distribution using Seaborn\n",
+    "plt.figure(figsize=(10, 5))\n",
+    "sns.barplot(x='Class', y='Weight', data=df, palette='viridis')\n",
+    "plt.title('Class Weight Distribution')\n",
+    "plt.xlabel('Class')\n",
+    "plt.ylabel('Class Weight')\n",
+    "plt.xticks(rotation='vertical')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "- Ploting from majority classes which have relatively poor resolution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAacAAAGgCAYAAAAO6qggAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAAAoR0lEQVR4nO3df3Ac9X3/8dfeSTqbSDphY0tWkYySGGR+mB8yyMKkaUGNx2Uo1IISxpmYQMvgCgfb7YSoDTh0UuQm09ihg02h1CaTuG6ciR2cBlxHgJg0so0FDhhqYYInVmNLJm11J7vxSb79fP8wvnC2BNx9dr/6nPx8zOyMtXf70eezt3cv7fmz+/aMMUYAADgkMtYdAADgdIQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOaGF02OPPaYLLrhAEyZMUGNjo3bt2hXWrwIAjDNeGPfW+9d//Vd9/vOf1+OPP67GxkatXr1amzZtUk9Pj6ZOnfqB2/q+r0OHDqmsrEye5wXdNQBAyIwxGhwcVHV1tSKRPM+BTAiuueYa09ramvk5nU6b6upq097e/qHb9vb2GkksLCwsLAW+9Pb25p0jRQrY0NCQuru71dbWllkXiUTU3Nysrq6uM56fSqWUSqUyP5v3TuR27d6p0tLSwPrlRfz8N46eCKwfp0QidmeFYdxL/sSJ/PdRxAT/DXEkYnl4WrzkowphnJ5Fm74J/thM+6kPf9IHCOMbj+KSCXlv6/vBHwi+5RvQC+E/VFz6puno4FHNvmqOysrK8m4j8HD69a9/rXQ6rcrKyqz1lZWV2rdv3xnPb29v18MPP3zG+tLSUquBnc65cIpahlMIH7yE00dwVoRTsdX24YTTxLy3JZzGjk2fxny2XltbmxKJRGbp7e0d6y4BAMZY4GdO5513nqLRqPr7+7PW9/f3q6qq6oznx2IxxWKxoLsBAChggZ85lZSUqKGhQR0dHZl1vu+ro6NDTU1NQf86AMA4FPiZkyQtX75cixYt0uzZs3XNNddo9erVOnbsmL7whS+E8esAAONMKOF0++23691339VDDz2kvr4+XXHFFXruuefOmCQBAMBIQrkI10YymVQ8Hteb+95gtt4HYLbeR8Bsvbyk/eNW2zNb78ON99l6g4ODqp9xqRKJhMrLy/NqY8xn6wEAcDrCCQDgHMIJAOAcwgkA4BzCCQDgHMIJAOCcUK5zcpHNdFJP6QB7clJaltM+TfDTRm2uKghluq4/ZNlACNPbveDfMlGLbnoK/kqQvOvvvCeMKc3pdP7vQceulpEk+X4Ir5vNZ4pllYTTBbHPOXMCADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOMfZkhkRzyjiBXdb+bRFU2Hcct+z6ZAkzwuhHITyL3sRRlUC49vdxj/AwyfD13DgbXqK5r3tiRMh9CdiVyImGs1/PKNJp0/kvW006t7HnGdbMmcEViUzAu5PJIDzHs6cAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOyTmcXnrpJd10002qrq6W53nasmVL1uPGGD300EOaNm2aJk6cqObmZu3fvz+o/gIAzgJFuW5w7NgxXX755brrrru0YMGCMx7/+te/rkcffVRPP/206urq9OCDD2revHl68803NWHChEA6nQ/P+Hlva4wJsCcn+V7aanvPy/ml+1A24wxhF8k3dvsoomhAPXkfE/yXDcZ4eW+b9ocD7MlJUS///pyU/3ttNOl0/sdCJBL8a+Z5lm2GcRxF8n8T2r7iYcj5E27+/PmaP3/+iI8ZY7R69Wp95Stf0c033yxJ+va3v63Kykpt2bJFn/3sZ+16CwA4KwQa3wcOHFBfX5+am5sz6+LxuBobG9XV1TXiNqlUSslkMmsBAJzdAg2nvr4+SVJlZWXW+srKysxjp2tvb1c8Hs8sNTU1QXYJAFCAxny2XltbmxKJRGbp7e0d6y4BAMZYoOFUVVUlServ789a39/fn3nsdLFYTOXl5VkLAODsFmg41dXVqaqqSh0dHZl1yWRSO3fuVFNTU5C/CgAwjuU8W+/o0aN6++23Mz8fOHBAe/bs0aRJk1RbW6ulS5fqa1/7mmbMmJGZSl5dXa1bbrklyH4DAMaxnMNp9+7d+v3f//3Mz8uXL5ckLVq0SOvXr9eXvvQlHTt2TPfcc48GBgZ03XXX6bnnnhvTa5wAAIXFM2FcYWohmUwqHo9rX89elZWVBdaub3GxolHwFzqa8XYRrt1wRuT7dhdzFspFuNFo/v0cGj4eYE9OikbtLsksKgp+Hw0N539sFhfHAuzJSS5ehOvZXIRrfeF1tsHBQV104SVKJBJ5zyMY89l6AACcjnACADiHcAIAOIdwAgA4h3ACADiHcAIAOCf4+cgBSQ+fUHr4RGDt+cp/rrOx2HZUllPJFcIFAHZXFYRR58hukL4J7vg5xfOCn57uWdQbsp32PRLr8kde8AenVd2q4K8EkRcptmwh+PdLxGJ6eiQS7HGUDqCkF2dOAADnEE4AAOcQTgAA5xBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOc4WzLDGGNdMiG7wfxvCW9CKAFgrG8pH8A96QMVQg0PBxkTfPmUEyfy33fpdPD1IHzLlzL4Ih6SzfGVtn+zncH4dseBF8JOili8bpGA99GJAMrVcOYEAHAO4QQAcA7hBABwDuEEAHAO4QQAcA7hBABwDuEEAHAO4QQAcA7hBABwDuEEAHAO4QQAcA7hBABwDuEEAHAO4QQAcA7hBABwjrP1nDwvKs+LBtiiW/WGbGtVWZSn+oBGbf5WcWv/SlIkhDpcvh98bSCbek6+ZV2hEds8YVeLJ1oU/MdKJFKc97ZhVD7zLI9344VQY8riMyHo3vgBtMiZEwDAOYQTAMA5hBMAwDk5hVN7e7uuvvpqlZWVaerUqbrlllvU09OT9Zzjx4+rtbVVkydPVmlpqVpaWtTf3x9opwEA41tO4dTZ2anW1lbt2LFD27dv1/DwsD7zmc/o2LFjmecsW7ZMW7du1aZNm9TZ2alDhw5pwYIFgXccADB+ecZi2ti7776rqVOnqrOzU7/7u7+rRCKhKVOmaMOGDbr11lslSfv27dPMmTPV1dWlOXPmfGibyWRS8Xhcb+x9TWVlZfl27QzG5D8DKa3jgfXjFNtZVsYLYbqe1Ww99xTKbD2bmZuhzNazeK9ILs7WC74/nixnEkeCf69FLNoM+uNkcHBQV8y8UolEQuXl5Xm1YbWHEomEJGnSpEmSpO7ubg0PD6u5uTnznPr6etXW1qqrq2vENlKplJLJZNYCADi75R1Ovu9r6dKlmjt3ri699FJJUl9fn0pKSlRRUZH13MrKSvX19Y3YTnt7u+LxeGapqanJt0sAgHEi73BqbW3V3r17tXHjRqsOtLW1KZFIZJbe3l6r9gAAhS+vL2Pvu+8+/ehHP9JLL72k888/P7O+qqpKQ0NDGhgYyDp76u/vV1VV1YhtxWIxxWKxfLoBABincjpzMsbovvvu0+bNm/X888+rrq4u6/GGhgYVFxero6Mjs66np0cHDx5UU1NTMD0GAIx7OZ05tba2asOGDfrhD3+osrKyzP8jxeNxTZw4UfF4XHfffbeWL1+uSZMmqby8XEuWLFFTU9NHmqkHAICUYzitXbtWkvR7v/d7WevXrVunO++8U5K0atUqRSIRtbS0KJVKad68eVqzZk0gnQUAnB2srnMKA9c5fTRc5/ThuM4pzza5zulDcZ3TBxvz65wAAAgD4QQAcA7hBABwDuEEAHAO4QQAcA7hBABwTvBzLAPieZ68AOc3+sq/LeMHP207bTmD3wQ/g1iel/806TCuSLCdth0tkD+9bPadCeOKAtnt9xOym4o+kmKvJO9tjR/8sWn70eSF8H6xaTPome1BXMZRIG9fAMDZhHACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADjH2ZIZaf/kEhTf5N+Yp2hwHXmPbTmHE5blJEZiU4UjWhT8oRS1LN3ghVFXJATRSP71F4aHUwH25CTbUjVFxcUB9eR9LA6F4uLg378Ry1olAVSUOLNNWTQa8OdJJID2OHMCADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4x9l6TsYYGRNc0RNjkcNeJPjaSb6x+7vAWNbcGbnR/Pe3H0J9KWNZjykaRtEcm5o5o7VocSzY1l4aUTT4+ke2bMonhXJspk9YbR8J4TjyvPxfNy/g94rt/pE4cwIAOIhwAgA4h3ACADgnp3Bau3atZs2apfLycpWXl6upqUnPPvts5vHjx4+rtbVVkydPVmlpqVpaWtTf3x94pwEA41tO4XT++edr5cqV6u7u1u7du3X99dfr5ptv1htvvCFJWrZsmbZu3apNmzaps7NThw4d0oIFC0LpOABg/PKM5ZS4SZMm6Rvf+IZuvfVWTZkyRRs2bNCtt94qSdq3b59mzpyprq4uzZkz5yO1l0wmFY/H9dprr6msrMyma1l85T/zy4vYzzw53QljN4MofSKMWWP5t+lFwujP2TFbLxLJ/9v1dHo4wJ6cZKJ2Y4yGMNvPmOK8t40o+P54abv373ifrTc4eFSXXTZHiURC5eXlebWR97sinU5r48aNOnbsmJqamtTd3a3h4WE1NzdnnlNfX6/a2lp1dXWN2k4qlVIymcxaAABnt5zD6fXXX1dpaalisZjuvfdebd68WRdffLH6+vpUUlKiioqKrOdXVlaqr69v1Pba29sVj8czS01NTc6DAACMLzmH00UXXaQ9e/Zo586dWrx4sRYtWqQ333wz7w60tbUpkUhklt7e3rzbAgCMDznfIaKkpESf/OQnJUkNDQ16+eWX9a1vfUu33367hoaGNDAwkHX21N/fr6qqqlHbi8ViisViufccADBuWV/n5Pu+UqmUGhoaVFxcrI6OjsxjPT09OnjwoJqammx/DQDgLJLTmVNbW5vmz5+v2tpaDQ4OasOGDXrxxRe1bds2xeNx3X333Vq+fLkmTZqk8vJyLVmyRE1NTR95ph4AAFKO4XTkyBF9/vOf1+HDhxWPxzVr1ixt27ZNf/AHfyBJWrVqlSKRiFpaWpRKpTRv3jytWbMmlI4DAMYv6+ucgsZ1Th8N1zl9OK5zyg/XOX04rnP6YGN6nRMAAGFxt56TZ1fD5cwGA2wrALZ1eMIo4+Nb7CQTwg72Lc8uw/hSIBINfsfbjDNSHHx/PMvX0rEvY0Kp51RkeTLmKYTXzaLJoOuCeQG8TzhzAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADjH2ZIZvu8HfKv7/G/jb1NKYjSulRWwFcZ4bNu0LbkxEs+xP+e8EDpkWz4hnbYrEjmSqMUwTQj1ZYzlseWHUPImYtGnoN8p6QDee4691QAAIJwAAA4inAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4pGusOjM5/bwmGMen8N04H149TjGe3ve+bYDryfsamzeD7Y9InrLaPWO7jEds0Ifw95+V/fEVCOAzsjgPJWG4fNM8L/kBIW77/PAXfJ2PxHgz648R2/0icOQEAHEQ4AQCcQzgBAJxjFU4rV66U53launRpZt3x48fV2tqqyZMnq7S0VC0tLerv77ftJwDgLJJ3OL388sv6x3/8R82aNStr/bJly7R161Zt2rRJnZ2dOnTokBYsWGDdUQDA2SOvcDp69KgWLlyoJ598Uueee25mfSKR0FNPPaVvfvObuv7669XQ0KB169bpZz/7mXbs2BFYpwEA41te4dTa2qobb7xRzc3NWeu7u7s1PDyctb6+vl61tbXq6uqy6ykA4KyR83VOGzdu1CuvvKKXX375jMf6+vpUUlKiioqKrPWVlZXq6+sbsb1UKqVUKpX5OZlM5tolAMA4k9OZU29vr+6//35997vf1YQJEwLpQHt7u+LxeGapqakJpF0AQOHKKZy6u7t15MgRXXXVVSoqKlJRUZE6Ozv16KOPqqioSJWVlRoaGtLAwEDWdv39/aqqqhqxzba2NiUSiczS29ub92AAAONDTl/r3XDDDXr99dez1n3hC19QfX29HnjgAdXU1Ki4uFgdHR1qaWmRJPX09OjgwYNqamoasc1YLKZYLJZn9wEA41FO4VRWVqZLL700a93HPvYxTZ48ObP+7rvv1vLlyzVp0iSVl5dryZIlampq0pw5c4LrNQBgXAv8xq+rVq1SJBJRS0uLUqmU5s2bpzVr1gT9awAA45hnHLuFcDKZVDwe16s/f0VlZWWBtWt1V3LPYttR+JY3JU6fCOEu4BaHglHw+yidTn34kz5ANIS7khcVuXVX8lD6Y3mH+WE/+Lv4F0XPyX9jEw2uI+/xfbs75odxp3SbIyHoV+zo4FFdddm1SiQSKi8vz6sN7q0HAHCOs/WcIpGIIpHgstO3+WsujL9ybM7kJKW9UAr5WGwa/F/L9oLvkx/COG3qToVS18viTE6SoiH8zetZjNMPodaY7WeTa2dOQfMC+Ox2aTwAAEginAAADiKcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAznG3ZIZnFAmwLISxuG2+CaH0gq2ogr/lvm9VbDD4fWTzmkmSF8brFkaJCou/EdN+8EUebasdBFEu4XQ2JW9MCGVOPM/yozOEQpg2pX2C7o5nW01VnDkBABxEOAEAnEM4AQCcQzgBAJxDOAEAnEM4AQCcQzgBAJxDOAEAnEM4AQCcQzgBAJxDOAEAnEM4AQCcQzgBAJxDOAEAnEM4AQCc42w9Jz99cgmsPYsyPBZljj6gTbsaM8aEURAmfyaA+i2BiwTfJ2NRVygMfjqM+lJ2+60oGvzfvOm0TT2nADvyHi8Sxn63Y9Uji1pQYeHMCQDgHMIJAOAcwgkA4BzCCQDgHMIJAOAcwgkA4BzCCQDgHMIJAOCcnMLpq1/9qjzPy1rq6+szjx8/flytra2aPHmySktL1dLSov7+/sA7DQAY33I+c7rkkkt0+PDhzPLTn/4089iyZcu0detWbdq0SZ2dnTp06JAWLFgQaIcBAONfzrcvKioqUlVV1RnrE4mEnnrqKW3YsEHXX3+9JGndunWaOXOmduzYoTlz5tj3FgBwVsj5zGn//v2qrq7Wxz/+cS1cuFAHDx6UJHV3d2t4eFjNzc2Z59bX16u2tlZdXV3B9RgAMO7ldObU2Nio9evX66KLLtLhw4f18MMP61Of+pT27t2rvr4+lZSUqKKiImubyspK9fX1jdpmKpVSKpXK/JxMJnMbAQBg3MkpnObPn5/596xZs9TY2Kjp06fre9/7niZOnJhXB9rb2/Xwww/ntS0AYHyymkpeUVGhCy+8UG+//baqqqo0NDSkgYGBrOf09/eP+H9Up7S1tSmRSGSW3t5emy4BAMYBq3A6evSofvGLX2jatGlqaGhQcXGxOjo6Mo/39PTo4MGDampqGrWNWCym8vLyrAUAcHbL6Wu9v/zLv9RNN92k6dOn69ChQ1qxYoWi0ajuuOMOxeNx3X333Vq+fLkmTZqk8vJyLVmyRE1NTczUAwDkJKdw+q//+i/dcccd+u///m9NmTJF1113nXbs2KEpU6ZIklatWqVIJKKWlhalUinNmzdPa9asCaXjAIDxyzMmjCLG+Usmk4rH4/r5z19VWVlZYO2mzYm8tzXKf9tR2zR2NejDKNNucyj4fvD7yDfDVttHoiGUVPftXreRRKPRvLdNp4PvTyRqWaa9uCSgnvxW+kT++yiMT7hopNhqey+EsugRmzYD7s/g4FFdcVmjEolE3v9Vw731AADOyfkOEf+/GC8i4wWYnSb/tsI4Sznhu/h3gcU4o8EfSp7lfj/hDwXUk98qtjyrGFEk/2PBM/mfUYwmYnlWoEjwx4Jv8e3FiXQIZ/WWf9dHQthHxRafl0F/x+DbfJa8x8VPSADAWY5wAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADjH2XpO0WjUqkLo6TzPpsprCNVGrVtwqxJuGP2xbTLI4+cUP/DKN3b1wkwIFVVlWTnWouj06G1aHJthHAcRixpcUjiVcNM2L1zA1YKDKLDOmRMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOc6WzFD0vSUgxuKe8J5FSYPRRGzHFkKfbGpUBHGL/DPatL6Pf/CHt2+CL59iJ/j9bsv3wygrkv84i4uLA+zJSZ5n9wa2KZNytuDMCQDgHMIJAOAcwgkA4BzCCQDgHMIJAOAcwgkA4BzCCQDgHMIJAOCcnMPpV7/6lT73uc9p8uTJmjhxoi677DLt3r0787gxRg899JCmTZumiRMnqrm5Wfv37w+00wCA8S2ncPrf//1fzZ07V8XFxXr22Wf15ptv6u///u917rnnZp7z9a9/XY8++qgef/xx7dy5Ux/72Mc0b948HT9+PPDOAwDGp5zu7/J3f/d3qqmp0bp16zLr6urqMv82xmj16tX6yle+optvvlmS9O1vf1uVlZXasmWLPvvZzwbUbQDAeJbTmdMzzzyj2bNn67bbbtPUqVN15ZVX6sknn8w8fuDAAfX19am5uTmzLh6Pq7GxUV1dXcH1GgAwruUUTu+8847Wrl2rGTNmaNu2bVq8eLG++MUv6umnn5Yk9fX1SZIqKyuztqusrMw8drpUKqVkMpm1AADObjl9ref7vmbPnq1HHnlEknTllVdq7969evzxx7Vo0aK8OtDe3q6HH344r20BAONTTmdO06ZN08UXX5y1bubMmTp48KAkqaqqSpLU39+f9Zz+/v7MY6dra2tTIpHILL29vbl0CQAwDuV05jR37lz19PRkrXvrrbc0ffp0SScnR1RVVamjo0NXXHGFJCmZTGrnzp1avHjxiG3GYjHFYrERHvHfW4LhWZRP8SIh1MyxrOcSQvkkK57NDh61TbvL8EKpmRPGoWB1mIcwRsv9HsaxEInm36bNtqOyPraC71MYNdXGUk7htGzZMl177bV65JFH9Cd/8ifatWuXnnjiCT3xxBOSTh6US5cu1de+9jXNmDFDdXV1evDBB1VdXa1bbrkljP4DAMahnMLp6quv1ubNm9XW1qa/+Zu/UV1dnVavXq2FCxdmnvOlL31Jx44d0z333KOBgQFdd911eu655zRhwoTAOw8AGJ8849i5YDKZVDwe1+v7XlNZWVlg7fp+/uW10/5wYP04xXa3G/8sKPPs2X2ta0zwr1vaPxF4m3Zf6wUvErErbx/G13pG+e/3MMq0y7hXpt2lj/Kjg0fVMKtRiURC5eXlebXBvfUAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAzrEreRki309bVa8NkucFX2HSWJY/DaXmpcn/bxXPC/7vHE921UZ9L4TjJ4Rx2hRFDaP6aSRiV6U1ErV73UbiW7xf/BDeLZ71fg+hTw4Vxw7iM5MzJwCAcwgnAIBzCCcAgHMIJwCAcwgnAIBzCCcAgHMIJwCAcwgnAIBzCCcAgHMIJwCAcwgnAIBzCCcAgHMIJwCAcwgnAIBznC2ZETgv/1vue3LoXvTvCaNUgvEt9lEIu8i2dIMJ5XULoTSIRXmBMI4Dz7MreRENoWSGLMrnhLKPZFfyxnYfj9ymO59TXsT+fcKZEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5OYXTBRdcIM/zzlhaW1slScePH1dra6smT56s0tJStbS0qL+/P5SOAwDGr5zC6eWXX9bhw4czy/bt2yVJt912myRp2bJl2rp1qzZt2qTOzk4dOnRICxYsCL7XAIBxLafbF02ZMiXr55UrV+oTn/iEPv3pTyuRSOipp57Shg0bdP3110uS1q1bp5kzZ2rHjh2aM2dOcL0GAIxref+f09DQkL7zne/orrvukud56u7u1vDwsJqbmzPPqa+vV21trbq6ugLpLADg7JD3jV+3bNmigYEB3XnnnZKkvr4+lZSUqKKiIut5lZWV6uvrG7WdVCqlVCqV+TmZTObbJQDAOJH3mdNTTz2l+fPnq7q62qoD7e3tisfjmaWmpsaqPQBA4cvrzOmXv/ylfvKTn+gHP/hBZl1VVZWGhoY0MDCQdfbU39+vqqqqUdtqa2vT8uXLMz8nEgnV1tbq6NGj+XRtdFZlCfK/Xf9o/LRdm+l0GCUz8r/lvucFf1WCbcmMtE4E1JPfCuNYsCnp4Bu70g0jKS4attq+qDj4chC+P5T3tmGUzIgYy+N9nJfMOPX5bbXvTR5WrFhhqqqqzPDwcGbdwMCAKS4uNt///vcz6/bt22ckma6uro/cdm9vr5HEwsLCwlLgS29vbz4RY4wxxjMmt2jzfV91dXW64447tHLlyqzHFi9erB//+Mdav369ysvLtWTJEknSz372s5zaP3TokMrKyjQ4OKiamhr19vaqvLw8l246KZlMMh6HMR63MR63vX88pz6/q6urFcmz8GDOX+v95Cc/0cGDB3XXXXed8diqVasUiUTU0tKiVCqlefPmac2aNTm1H4lEdP7550v67WlqeXn5uHjxTmE8bmM8bmM8bjs1nng8btVOzuH0mc98ZtTvESdMmKDHHntMjz32mFWnAABnN+6tBwBwjtPhFIvFtGLFCsVisbHuSiAYj9sYj9sYj9uCHk/OEyIAAAib02dOAICzE+EEAHAO4QQAcA7hBABwjrPh9Nhjj+mCCy7QhAkT1NjYqF27do11lz6yl156STfddJOqq6vleZ62bNmS9bgxRg899JCmTZumiRMnqrm5Wfv37x+bzn6I9vZ2XX311SorK9PUqVN1yy23qKenJ+s5hVQBee3atZo1a1bmQsGmpiY9++yzmccLaSwjWblypTzP09KlSzPrCm1MX/3qV8+otl1fX595vNDG86tf/Uqf+9znNHnyZE2cOFGXXXaZdu/enXm8kD4PpP+PFdHzvvFRiDZu3GhKSkrMP//zP5s33njD/Nmf/ZmpqKgw/f39Y921j+THP/6x+eu//mvzgx/8wEgymzdvznp85cqVJh6Pmy1btpif//zn5o/+6I9MXV2d+c1vfjM2Hf4A8+bNM+vWrTN79+41e/bsMX/4h39oamtrzdGjRzPPuffee01NTY3p6Ogwu3fvNnPmzDHXXnvtGPZ6dM8884z5t3/7N/PWW2+Znp4e81d/9VemuLjY7N271xhTWGM53a5du8wFF1xgZs2aZe6///7M+kIb04oVK8wll1xiDh8+nFnefffdzOOFNJ7/+Z//MdOnTzd33nmn2blzp3nnnXfMtm3bzNtvv515TiF9HhhjzJEjR7Jem+3btxtJ5oUXXjDGBPf6OBlO11xzjWltbc38nE6nTXV1tWlvbx/DXuXn9HDyfd9UVVWZb3zjG5l1AwMDJhaLmX/5l38Zgx7m5siRI0aS6ezsNMb89oa/mzZtyjznP//zP42U2w1/x9K5555r/umf/qmgxzI4OGhmzJhhtm/fbj796U9nwqkQx7RixQpz+eWXj/hYoY3ngQceMNddd92ojxf654Exxtx///3mE5/4hPF9P9DXx7mv9YaGhtTd3Z1VUTcSiai5uXlcVNQ9cOCA+vr6ssYXj8fV2NhYEONLJBKSpEmTJklSQVdATqfT2rhxo44dO6ampqaCHktra6tuvPHGrL5Lhfv67N+/X9XV1fr4xz+uhQsX6uDBg5IKbzzPPPOMZs+erdtuu01Tp07VlVdeqSeffDLzeKF/HoRZEd25cPr1r3+tdDqtysrKrPUfVlG3UJwaQyGOz/d9LV26VHPnztWll14qKf8KyGPp9ddfV2lpqWKxmO69915t3rxZF198cUGORZI2btyoV155Re3t7Wc8Vohjamxs1Pr16/Xcc89p7dq1OnDggD71qU9pcHCw4MbzzjvvaO3atZoxY4a2bdumxYsX64tf/KKefvppSYX9eSAFVxF9JHmXacfZp7W1VXv37tVPf/rTse6KlYsuukh79uxRIpHQ97//fS1atEidnZ1j3a289Pb26v7779f27ds1YcKEse5OIObPn5/596xZs9TY2Kjp06fre9/7niZOnDiGPcud7/uaPXu2HnnkEUnSlVdeqb179+rxxx/XokWLxrh39oKqiD4S586czjvvPEWj0TNmd3xYRd1CcWoMhTa+++67Tz/60Y/0wgsvZEqaSNkVkN/P5fGUlJTok5/8pBoaGtTe3q7LL79c3/rWtwpyLN3d3Tpy5IiuuuoqFRUVqaioSJ2dnXr00UdVVFSkysrKghvT6SoqKnThhRfq7bffLrjXaNq0abr44ouz1s2cOTPzNWWhfh5Iv62I/qd/+qeZdUG+Ps6FU0lJiRoaGtTR0ZFZ5/u+Ojo61NTUNIY9C0ZdXZ2qqqqyxpdMJrVz504nx2eM0X333afNmzfr+eefV11dXdbjDQ0NKi4uzhpPT0+PDh486OR4RuL7vlKpVEGO5YYbbtDrr7+uPXv2ZJbZs2dr4cKFmX8X2phOd/ToUf3iF7/QtGnTCu41mjt37hmXXrz11luaPn26pML7PHi/devWaerUqbrxxhsz6wJ9fQKeuBGIjRs3mlgsZtavX2/efPNNc88995iKigrT19c31l37SAYHB82rr75qXn31VSPJfPOb3zSvvvqq+eUvf2mMOTl1tKKiwvzwhz80r732mrn55pudnTq6ePFiE4/HzYsvvpg1ffT//u//Ms+59957TW1trXn++efN7t27TVNTk2lqahrDXo/uy1/+suns7DQHDhwwr732mvnyl79sPM8z//7v/26MKayxjOb9s/WMKbwx/cVf/IV58cUXzYEDB8x//Md/mObmZnPeeeeZI0eOGGMKazy7du0yRUVF5m//9m/N/v37zXe/+11zzjnnmO985zuZ5xTS58Ep6XTa1NbWmgceeOCMx4J6fZwMJ2OM+Yd/+AdTW1trSkpKzDXXXGN27Ngx1l36yF544QUj6Yxl0aJFxpiT00cffPBBU1lZaWKxmLnhhhtMT0/P2HZ6FCONQ5JZt25d5jm/+c1vzJ//+Z+bc88915xzzjnmj//4j83hw4fHrtMf4K677jLTp083JSUlZsqUKeaGG27IBJMxhTWW0ZweToU2pttvv91MmzbNlJSUmN/5nd8xt99+e9Z1QYU2nq1bt5pLL73UxGIxU19fb5544omsxwvp8+CUbdu2GUkj9jOo14eSGQAA5zj3f04AABBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOf8P/uOP6ie8bJ2AAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "for _ in range(10):\n",
+    "    img, label = train_generator.next()\n",
+    "    if (label[0][1]==1):\n",
+    "        plt.imshow(img[0])\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_model=ConvNeXtTiny(\n",
+    "    model_name=\"convnext_tiny\",\n",
+    "    include_top=False,\n",
+    "    include_preprocessing=False,\n",
+    "    weights=\"imagenet\",\n",
+    "    input_tensor=None,\n",
+    "    input_shape=(71, 71, 3),\n",
+    "    pooling=None,\n",
+    "    classes=6,\n",
+    "    classifier_activation=\"softmax\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for layer in base_model.layers:\n",
+    "    layer.trainable = False"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ConvNeXtTiny_learner=models.Sequential([\n",
+    "    base_model,\n",
+    "    layers.GlobalAveragePooling2D(),\n",
+    "    layers.Dense(256, activation='relu'),\n",
+    "    layers.Dropout(0.2),\n",
+    "    layers.Dense(6, activation='softmax')\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " convnext_tiny (Functional)  (None, 2, 2, 768)         27820128  \n",
+      "                                                                 \n",
+      " global_average_pooling2d (G  (None, 768)              0         \n",
+      " lobalAveragePooling2D)                                          \n",
+      "                                                                 \n",
+      " dense (Dense)               (None, 256)               196864    \n",
+      "                                                                 \n",
+      " dropout (Dropout)           (None, 256)               0         \n",
+      "                                                                 \n",
+      " dense_1 (Dense)             (None, 6)                 1542      \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 28,018,534\n",
+      "Trainable params: 198,406\n",
+      "Non-trainable params: 27,820,128\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "ConvNeXtTiny_learner.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "METRICS = [\n",
+    "      keras.metrics.Precision(name='precision'),\n",
+    "      keras.metrics.Recall(name='recall'),\n",
+    "      keras.metrics.AUC(name='auc'),\n",
+    "      keras.metrics.AUC(name='prc', curve='PR'), # precision-recall curve\n",
+    "]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\arpit\\anaconda3\\envs\\tf\\lib\\site-packages\\keras\\optimizers\\optimizer_v2\\adam.py:114: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.\n",
+      "  super().__init__(name, **kwargs)\n"
+     ]
+    }
+   ],
+   "source": [
+    "ConvNeXtTiny_learner.compile(\n",
+    "    optimizer=Adam(lr=0.0001),\n",
+    "    loss='categorical_crossentropy',\n",
+    "    metrics=['accuracy', METRICS],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/100\n",
+      "28/28 [==============================] - 10s 76ms/step - loss: 1.3943 - accuracy: 0.4937 - precision: 0.6587 - recall: 0.3151 - auc: 0.7886 - prc: 0.5201\n",
+      "Epoch 2/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.6697 - accuracy: 0.8180 - precision: 0.8833 - recall: 0.7452 - auc: 0.9627 - prc: 0.8800\n",
+      "Epoch 3/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.4903 - accuracy: 0.8680 - precision: 0.9031 - recall: 0.8214 - auc: 0.9752 - prc: 0.9188\n",
+      "Epoch 4/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.4255 - accuracy: 0.8879 - precision: 0.9121 - recall: 0.8555 - auc: 0.9789 - prc: 0.9293\n",
+      "Epoch 5/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.3947 - accuracy: 0.8982 - precision: 0.9138 - recall: 0.8686 - auc: 0.9815 - prc: 0.9381\n",
+      "Epoch 6/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.3537 - accuracy: 0.9050 - precision: 0.9184 - recall: 0.8840 - auc: 0.9837 - prc: 0.9434\n",
+      "Epoch 7/100\n",
+      "28/28 [==============================] - 2s 59ms/step - loss: 0.3332 - accuracy: 0.9164 - precision: 0.9304 - recall: 0.8896 - auc: 0.9855 - prc: 0.9481\n",
+      "Epoch 8/100\n",
+      "28/28 [==============================] - 2s 59ms/step - loss: 0.3099 - accuracy: 0.9170 - precision: 0.9284 - recall: 0.8999 - auc: 0.9862 - prc: 0.9507\n",
+      "Epoch 9/100\n",
+      "28/28 [==============================] - 2s 59ms/step - loss: 0.2809 - accuracy: 0.9249 - precision: 0.9347 - recall: 0.9044 - auc: 0.9891 - prc: 0.9617\n",
+      "Epoch 10/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.2816 - accuracy: 0.9187 - precision: 0.9330 - recall: 0.9033 - auc: 0.9886 - prc: 0.9595\n",
+      "Epoch 11/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.2498 - accuracy: 0.9317 - precision: 0.9362 - recall: 0.9187 - auc: 0.9910 - prc: 0.9664\n",
+      "Epoch 12/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.2507 - accuracy: 0.9272 - precision: 0.9383 - recall: 0.9170 - auc: 0.9916 - prc: 0.9678\n",
+      "Epoch 13/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.2299 - accuracy: 0.9403 - precision: 0.9482 - recall: 0.9272 - auc: 0.9926 - prc: 0.9724\n",
+      "Epoch 14/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.2262 - accuracy: 0.9329 - precision: 0.9447 - recall: 0.9226 - auc: 0.9927 - prc: 0.9720\n",
+      "Epoch 15/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.2180 - accuracy: 0.9397 - precision: 0.9483 - recall: 0.9278 - auc: 0.9923 - prc: 0.9707\n",
+      "Epoch 16/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.2075 - accuracy: 0.9408 - precision: 0.9463 - recall: 0.9329 - auc: 0.9935 - prc: 0.9752\n",
+      "Epoch 17/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.2073 - accuracy: 0.9374 - precision: 0.9440 - recall: 0.9295 - auc: 0.9938 - prc: 0.9763\n",
+      "Epoch 18/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.2075 - accuracy: 0.9403 - precision: 0.9464 - recall: 0.9334 - auc: 0.9933 - prc: 0.9736\n",
+      "Epoch 19/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.1914 - accuracy: 0.9443 - precision: 0.9519 - recall: 0.9352 - auc: 0.9946 - prc: 0.9788\n",
+      "Epoch 20/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.1770 - accuracy: 0.9499 - precision: 0.9571 - recall: 0.9397 - auc: 0.9950 - prc: 0.9804\n",
+      "Epoch 21/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.1790 - accuracy: 0.9465 - precision: 0.9506 - recall: 0.9414 - auc: 0.9940 - prc: 0.9791\n",
+      "Epoch 22/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.1676 - accuracy: 0.9505 - precision: 0.9583 - recall: 0.9420 - auc: 0.9955 - prc: 0.9833\n",
+      "Epoch 23/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.1636 - accuracy: 0.9477 - precision: 0.9587 - recall: 0.9380 - auc: 0.9957 - prc: 0.9838\n",
+      "Epoch 24/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.1688 - accuracy: 0.9465 - precision: 0.9532 - recall: 0.9391 - auc: 0.9956 - prc: 0.9825\n",
+      "Epoch 25/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.1518 - accuracy: 0.9494 - precision: 0.9550 - recall: 0.9425 - auc: 0.9953 - prc: 0.9829\n",
+      "Epoch 26/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.1558 - accuracy: 0.9499 - precision: 0.9556 - recall: 0.9425 - auc: 0.9955 - prc: 0.9833\n",
+      "Epoch 27/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.1531 - accuracy: 0.9534 - precision: 0.9579 - recall: 0.9454 - auc: 0.9958 - prc: 0.9849\n",
+      "Epoch 28/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.1390 - accuracy: 0.9556 - precision: 0.9597 - recall: 0.9477 - auc: 0.9959 - prc: 0.9856\n",
+      "Epoch 29/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.1424 - accuracy: 0.9545 - precision: 0.9608 - recall: 0.9482 - auc: 0.9966 - prc: 0.9853\n",
+      "Epoch 30/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.1488 - accuracy: 0.9608 - precision: 0.9645 - recall: 0.9573 - auc: 0.9960 - prc: 0.9856\n",
+      "Epoch 31/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.1411 - accuracy: 0.9585 - precision: 0.9636 - recall: 0.9477 - auc: 0.9963 - prc: 0.9864\n",
+      "Epoch 32/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.1337 - accuracy: 0.9562 - precision: 0.9620 - recall: 0.9516 - auc: 0.9957 - prc: 0.9851\n",
+      "Epoch 33/100\n",
+      "28/28 [==============================] - 2s 63ms/step - loss: 0.1337 - accuracy: 0.9596 - precision: 0.9643 - recall: 0.9522 - auc: 0.9966 - prc: 0.9882\n",
+      "Epoch 34/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.1254 - accuracy: 0.9647 - precision: 0.9672 - recall: 0.9556 - auc: 0.9965 - prc: 0.9870\n",
+      "Epoch 35/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.1240 - accuracy: 0.9630 - precision: 0.9651 - recall: 0.9596 - auc: 0.9962 - prc: 0.9876\n",
+      "Epoch 36/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.1262 - accuracy: 0.9613 - precision: 0.9677 - recall: 0.9551 - auc: 0.9972 - prc: 0.9892\n",
+      "Epoch 37/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.1185 - accuracy: 0.9653 - precision: 0.9690 - recall: 0.9608 - auc: 0.9974 - prc: 0.9902\n",
+      "Epoch 38/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.1228 - accuracy: 0.9590 - precision: 0.9615 - recall: 0.9522 - auc: 0.9968 - prc: 0.9881\n",
+      "Epoch 39/100\n",
+      "28/28 [==============================] - 2s 63ms/step - loss: 0.1226 - accuracy: 0.9630 - precision: 0.9678 - recall: 0.9573 - auc: 0.9971 - prc: 0.9888\n",
+      "Epoch 40/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.1118 - accuracy: 0.9664 - precision: 0.9702 - recall: 0.9625 - auc: 0.9976 - prc: 0.9908\n",
+      "Epoch 41/100\n",
+      "28/28 [==============================] - 2s 63ms/step - loss: 0.1008 - accuracy: 0.9750 - precision: 0.9782 - recall: 0.9704 - auc: 0.9982 - prc: 0.9924\n",
+      "Epoch 42/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.1105 - accuracy: 0.9653 - precision: 0.9706 - recall: 0.9573 - auc: 0.9973 - prc: 0.9897\n",
+      "Epoch 43/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.1034 - accuracy: 0.9704 - precision: 0.9731 - recall: 0.9653 - auc: 0.9978 - prc: 0.9915\n",
+      "Epoch 44/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.1090 - accuracy: 0.9676 - precision: 0.9697 - recall: 0.9659 - auc: 0.9972 - prc: 0.9893\n",
+      "Epoch 45/100\n",
+      "28/28 [==============================] - 2s 68ms/step - loss: 0.1034 - accuracy: 0.9716 - precision: 0.9736 - recall: 0.9664 - auc: 0.9980 - prc: 0.9918\n",
+      "Epoch 46/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0987 - accuracy: 0.9681 - precision: 0.9736 - recall: 0.9647 - auc: 0.9977 - prc: 0.9921\n",
+      "Epoch 47/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0982 - accuracy: 0.9693 - precision: 0.9724 - recall: 0.9630 - auc: 0.9972 - prc: 0.9907\n",
+      "Epoch 48/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0955 - accuracy: 0.9721 - precision: 0.9753 - recall: 0.9670 - auc: 0.9979 - prc: 0.9923\n",
+      "Epoch 49/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0949 - accuracy: 0.9716 - precision: 0.9771 - recall: 0.9693 - auc: 0.9977 - prc: 0.9924\n",
+      "Epoch 50/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.0948 - accuracy: 0.9727 - precision: 0.9764 - recall: 0.9659 - auc: 0.9980 - prc: 0.9921\n",
+      "Epoch 51/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.0915 - accuracy: 0.9767 - precision: 0.9777 - recall: 0.9716 - auc: 0.9987 - prc: 0.9943\n",
+      "Epoch 52/100\n",
+      "28/28 [==============================] - 2s 67ms/step - loss: 0.0934 - accuracy: 0.9750 - precision: 0.9754 - recall: 0.9710 - auc: 0.9982 - prc: 0.9933\n",
+      "Epoch 53/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.0897 - accuracy: 0.9699 - precision: 0.9748 - recall: 0.9687 - auc: 0.9980 - prc: 0.9926\n",
+      "Epoch 54/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.0875 - accuracy: 0.9778 - precision: 0.9799 - recall: 0.9727 - auc: 0.9985 - prc: 0.9943\n",
+      "Epoch 55/100\n",
+      "28/28 [==============================] - 2s 67ms/step - loss: 0.0839 - accuracy: 0.9761 - precision: 0.9810 - recall: 0.9716 - auc: 0.9983 - prc: 0.9942\n",
+      "Epoch 56/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.0826 - accuracy: 0.9772 - precision: 0.9789 - recall: 0.9755 - auc: 0.9984 - prc: 0.9943\n",
+      "Epoch 57/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.0821 - accuracy: 0.9755 - precision: 0.9794 - recall: 0.9733 - auc: 0.9981 - prc: 0.9932\n",
+      "Epoch 58/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.0765 - accuracy: 0.9755 - precision: 0.9783 - recall: 0.9755 - auc: 0.9984 - prc: 0.9951\n",
+      "Epoch 59/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0772 - accuracy: 0.9795 - precision: 0.9823 - recall: 0.9772 - auc: 0.9984 - prc: 0.9947\n",
+      "Epoch 60/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0813 - accuracy: 0.9755 - precision: 0.9777 - recall: 0.9721 - auc: 0.9983 - prc: 0.9947\n",
+      "Epoch 61/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0760 - accuracy: 0.9818 - precision: 0.9839 - recall: 0.9755 - auc: 0.9983 - prc: 0.9941\n",
+      "Epoch 62/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0713 - accuracy: 0.9795 - precision: 0.9817 - recall: 0.9738 - auc: 0.9991 - prc: 0.9962\n",
+      "Epoch 63/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0728 - accuracy: 0.9784 - precision: 0.9805 - recall: 0.9744 - auc: 0.9987 - prc: 0.9953\n",
+      "Epoch 64/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0694 - accuracy: 0.9807 - precision: 0.9818 - recall: 0.9795 - auc: 0.9988 - prc: 0.9957\n",
+      "Epoch 65/100\n",
+      "28/28 [==============================] - 2s 65ms/step - loss: 0.0638 - accuracy: 0.9835 - precision: 0.9851 - recall: 0.9795 - auc: 0.9984 - prc: 0.9959\n",
+      "Epoch 66/100\n",
+      "28/28 [==============================] - 2s 68ms/step - loss: 0.0738 - accuracy: 0.9772 - precision: 0.9822 - recall: 0.9716 - auc: 0.9985 - prc: 0.9952\n",
+      "Epoch 67/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.0669 - accuracy: 0.9801 - precision: 0.9822 - recall: 0.9744 - auc: 0.9989 - prc: 0.9961\n",
+      "Epoch 68/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.0645 - accuracy: 0.9795 - precision: 0.9829 - recall: 0.9784 - auc: 0.9992 - prc: 0.9963\n",
+      "Epoch 69/100\n",
+      "28/28 [==============================] - 2s 68ms/step - loss: 0.0651 - accuracy: 0.9818 - precision: 0.9829 - recall: 0.9801 - auc: 0.9986 - prc: 0.9958\n",
+      "Epoch 70/100\n",
+      "28/28 [==============================] - 2s 66ms/step - loss: 0.0662 - accuracy: 0.9818 - precision: 0.9834 - recall: 0.9784 - auc: 0.9989 - prc: 0.9963\n",
+      "Epoch 71/100\n",
+      "28/28 [==============================] - 2s 64ms/step - loss: 0.0632 - accuracy: 0.9801 - precision: 0.9828 - recall: 0.9778 - auc: 0.9994 - prc: 0.9971\n",
+      "Epoch 72/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0664 - accuracy: 0.9812 - precision: 0.9845 - recall: 0.9784 - auc: 0.9992 - prc: 0.9966\n",
+      "Epoch 73/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.0665 - accuracy: 0.9824 - precision: 0.9845 - recall: 0.9784 - auc: 0.9990 - prc: 0.9964\n",
+      "Epoch 74/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0615 - accuracy: 0.9795 - precision: 0.9806 - recall: 0.9790 - auc: 0.9991 - prc: 0.9971\n",
+      "Epoch 75/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0637 - accuracy: 0.9812 - precision: 0.9840 - recall: 0.9784 - auc: 0.9992 - prc: 0.9966\n",
+      "Epoch 76/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0599 - accuracy: 0.9795 - precision: 0.9829 - recall: 0.9790 - auc: 0.9992 - prc: 0.9966\n",
+      "Epoch 77/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0590 - accuracy: 0.9835 - precision: 0.9846 - recall: 0.9829 - auc: 0.9991 - prc: 0.9970\n",
+      "Epoch 78/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0581 - accuracy: 0.9829 - precision: 0.9829 - recall: 0.9795 - auc: 0.9991 - prc: 0.9970\n",
+      "Epoch 79/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0568 - accuracy: 0.9852 - precision: 0.9868 - recall: 0.9818 - auc: 0.9994 - prc: 0.9974\n",
+      "Epoch 80/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0564 - accuracy: 0.9841 - precision: 0.9869 - recall: 0.9829 - auc: 0.9994 - prc: 0.9974\n",
+      "Epoch 81/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0595 - accuracy: 0.9835 - precision: 0.9857 - recall: 0.9807 - auc: 0.9987 - prc: 0.9959\n",
+      "Epoch 82/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0575 - accuracy: 0.9852 - precision: 0.9863 - recall: 0.9824 - auc: 0.9994 - prc: 0.9972\n",
+      "Epoch 83/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0529 - accuracy: 0.9869 - precision: 0.9880 - recall: 0.9852 - auc: 0.9994 - prc: 0.9974\n",
+      "Epoch 84/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0523 - accuracy: 0.9852 - precision: 0.9891 - recall: 0.9841 - auc: 0.9996 - prc: 0.9979\n",
+      "Epoch 85/100\n",
+      "28/28 [==============================] - 2s 64ms/step - loss: 0.0522 - accuracy: 0.9858 - precision: 0.9886 - recall: 0.9846 - auc: 0.9996 - prc: 0.9982\n",
+      "Epoch 86/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0522 - accuracy: 0.9824 - precision: 0.9829 - recall: 0.9795 - auc: 0.9994 - prc: 0.9975\n",
+      "Epoch 87/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0556 - accuracy: 0.9818 - precision: 0.9823 - recall: 0.9801 - auc: 0.9995 - prc: 0.9977\n",
+      "Epoch 88/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0515 - accuracy: 0.9835 - precision: 0.9846 - recall: 0.9807 - auc: 0.9996 - prc: 0.9982\n",
+      "Epoch 89/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0496 - accuracy: 0.9852 - precision: 0.9858 - recall: 0.9841 - auc: 0.9996 - prc: 0.9983\n",
+      "Epoch 90/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0492 - accuracy: 0.9875 - precision: 0.9892 - recall: 0.9858 - auc: 0.9996 - prc: 0.9983\n",
+      "Epoch 91/100\n",
+      "28/28 [==============================] - 2s 63ms/step - loss: 0.0478 - accuracy: 0.9863 - precision: 0.9880 - recall: 0.9829 - auc: 0.9997 - prc: 0.9985\n",
+      "Epoch 92/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0483 - accuracy: 0.9858 - precision: 0.9874 - recall: 0.9841 - auc: 0.9996 - prc: 0.9981\n",
+      "Epoch 93/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0460 - accuracy: 0.9858 - precision: 0.9863 - recall: 0.9858 - auc: 0.9996 - prc: 0.9982\n",
+      "Epoch 94/100\n",
+      "28/28 [==============================] - 2s 63ms/step - loss: 0.0465 - accuracy: 0.9846 - precision: 0.9886 - recall: 0.9835 - auc: 0.9996 - prc: 0.9980\n",
+      "Epoch 95/100\n",
+      "28/28 [==============================] - 2s 63ms/step - loss: 0.0436 - accuracy: 0.9881 - precision: 0.9897 - recall: 0.9863 - auc: 0.9997 - prc: 0.9987\n",
+      "Epoch 96/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0450 - accuracy: 0.9852 - precision: 0.9874 - recall: 0.9824 - auc: 0.9996 - prc: 0.9983\n",
+      "Epoch 97/100\n",
+      "28/28 [==============================] - 2s 61ms/step - loss: 0.0475 - accuracy: 0.9846 - precision: 0.9869 - recall: 0.9846 - auc: 0.9995 - prc: 0.9977\n",
+      "Epoch 98/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.0474 - accuracy: 0.9869 - precision: 0.9886 - recall: 0.9858 - auc: 0.9997 - prc: 0.9986\n",
+      "Epoch 99/100\n",
+      "28/28 [==============================] - 2s 62ms/step - loss: 0.0412 - accuracy: 0.9892 - precision: 0.9909 - recall: 0.9886 - auc: 0.9997 - prc: 0.9987\n",
+      "Epoch 100/100\n",
+      "28/28 [==============================] - 2s 60ms/step - loss: 0.0448 - accuracy: 0.9875 - precision: 0.9892 - recall: 0.9858 - auc: 0.9996 - prc: 0.9983\n"
+     ]
+    }
+   ],
+   "source": [
+    "ConvNeXtTiny_history=ConvNeXtTiny_learner.fit(train_generator,epochs=100,class_weight=class_weight_dict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.DataFrame(ConvNeXtTiny_history.history)\n",
+    "df.to_csv(\"ConvNeXtTiny_plot.csv\",index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1600x800 with 6 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot training history for multiple metrics\n",
+    "plt.figure(figsize=(16, 8))\n",
+    "\n",
+    "# Plot training & validation accuracy values\n",
+    "plt.subplot(2, 3, 1)\n",
+    "plt.plot(ConvNeXtTiny_history.history['accuracy'])\n",
+    "plt.title('Model Accuracy')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation loss values\n",
+    "plt.subplot(2, 3, 2)\n",
+    "plt.plot(ConvNeXtTiny_history.history['loss'])\n",
+    "plt.title('Model Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation precision values\n",
+    "plt.subplot(2, 3, 3)\n",
+    "plt.plot(ConvNeXtTiny_history.history['precision'])\n",
+    "plt.title('Model Precision')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Precision')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation recall values\n",
+    "plt.subplot(2, 3, 4)\n",
+    "plt.plot(ConvNeXtTiny_history.history['recall'])\n",
+    "plt.title('Model Recall')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Recall')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation AUC values\n",
+    "plt.subplot(2, 3, 5)\n",
+    "plt.plot(ConvNeXtTiny_history.history['auc'])\n",
+    "plt.title('Model AUC')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('AUC')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation PRC values\n",
+    "plt.subplot(2, 3, 6)\n",
+    "plt.plot(ConvNeXtTiny_history.history['prc'])\n",
+    "plt.title('Model PRC')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('PRC')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "tf",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.17"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/High Throughput Algae Cell Detection/Model/InceptionV3.ipynb b/High Throughput Algae Cell Detection/Model/InceptionV3.ipynb
new file mode 100644
index 000000000..83e4a21c4
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/InceptionV3.ipynb	
@@ -0,0 +1,704 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# InceptionV3 Model Transfer Learning"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import tensorflow as tf\n",
+    "from tensorflow import keras\n",
+    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+    "import matplotlib.pyplot as plt\n",
+    "from tensorflow.keras import layers, models\n",
+    "from tensorflow.keras.applications import InceptionV3\n",
+    "from tensorflow.keras.optimizers import Adam\n",
+    "import seaborn as sns\n",
+    "import numpy as np\n",
+    "from sklearn.utils.class_weight import compute_class_weight\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Input size must be at least 75x75; for InceptionV3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found 1758 images belonging to 6 classes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "train_datagen = ImageDataGenerator(\n",
+    "        rescale=1./255)\n",
+    "train_generator = train_datagen.flow_from_directory(\n",
+    "    directory=r\"D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\non_yolo\",\n",
+    "    target_size=(75,75),\n",
+    "    color_mode=\"rgb\",\n",
+    "    batch_size=64,\n",
+    "    class_mode=\"categorical\",\n",
+    "    shuffle=True,\n",
+    "    seed=42\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Class Distribution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "class_indices = train_generator.class_indices\n",
+    "\n",
+    "class_names = {v: k for k, v in class_indices.items()}\n",
+    "\n",
+    "class_distribution = train_generator.classes\n",
+    "\n",
+    "class_names_list = [class_names[class_idx] for class_idx in class_distribution]\n",
+    "\n",
+    "# Plot the class distribution using Seaborn\n",
+    "plt.figure(figsize=(10, 5))\n",
+    "sns.countplot(x=class_names_list, palette='viridis')\n",
+    "plt.title('Class Distribution in the Training Dataset')\n",
+    "plt.xlabel('Class')\n",
+    "plt.ylabel('Number of Samples')\n",
+    "plt.xticks(rotation='vertical')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Class Weights: [1.5923913  0.40581717 1.25213675 1.2907489  1.07720588 2.46218487]\n"
+     ]
+    }
+   ],
+   "source": [
+    "class_labels = train_generator.classes\n",
+    "class_weights = compute_class_weight(class_weight='balanced', classes=np.unique(class_labels), y=class_labels)\n",
+    "\n",
+    "print(\"Class Weights:\", class_weights)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{0: 1.5923913043478262,\n",
+       " 1: 0.40581717451523547,\n",
+       " 2: 1.2521367521367521,\n",
+       " 3: 1.2907488986784141,\n",
+       " 4: 1.0772058823529411,\n",
+       " 5: 2.46218487394958}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "class_weight_dict = {i: class_weights[i] for i in range(len(class_weights))}\n",
+    "class_weight_dict"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "- ##### This inverse proportion from our original distribution indicates Class_weight multiple requires for all class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA04AAAH6CAYAAAAwZBzLAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAABAO0lEQVR4nO3deXhOd/7/8dedRO4gqy0JYk8RfBNrK1FLR8VaUe2gvSbUMNWhrcbSaq1tNfNrS7QorS6mi7HTfimqFIPYizDFILZWgiKpLdLk/P7o5f72bhInN0lOJM/Hdd3XuD/nc+77feI9M3k553yOzTAMQwAAAACAPLlZXQAAAAAAFHcEJwAAAAAwQXACAAAAABMEJwAAAAAwQXACAAAAABMEJwAAAAAwQXACAAAAABMEJwAAAAAwQXACAAAAABMEJwAoRmrVqqUBAwZYXYYlBgwYoFq1at3xvt7e3gVb0B2aO3eubDabTpw4Uejf9cef2YkTJ2Sz2fT2228X+ndL0sSJE2Wz2YrkuwDAagQnACgCx44d09NPP606derIy8tLvr6+ioqK0jvvvKPr169bXV6eFi5cKJvNpmXLluXYFh4eLpvNpu+++y7Htho1aigyMrIoSnTJtWvXNHHiRG3YsCFf8zds2CCbzeZ42e12BQYGqn379nrjjTd0/vx5S+oqSsW5NgAoSgQnAChkK1euVJMmTbRw4UL16NFD06dPV3x8vGrUqKFRo0bp+eeft7rEPLVp00aStHnzZqfx9PR0HThwQB4eHtqyZYvTttOnT+v06dOOffNrzpw5Onz48N0VbOLatWuaNGmSyyHgueee02effaYPPvhAo0aNUoUKFTRhwgQ1bNhQ69evd5r7l7/8RdevX1fNmjULvS6rf2Zjx44t1sEfAAqSh9UFAEBJlpycrL59+6pmzZpav369goODHduGDh2qo0ePauXKlRZWeHtVq1ZV7dq1cwSnxMREGYahxx9/PMe2W+9dDU5lypS5u2IL0YMPPqjHHnvMaWzfvn3q1KmTevfurf/85z+Ov1t3d3e5u7sXaj1Xr15V+fLlLf+ZeXh4yMODXyUAlA6ccQKAQvTmm2/qypUr+uijj5xC0y316tW77RmnixcvauTIkWrSpIm8vb3l6+urLl26aN++fTnmTp8+XY0aNVK5cuUUEBCgFi1aaN68eY7tv/zyi4YPH65atWrJbrerSpUqevjhh7Vnz57bHkObNm30/fffO51Z2LJlixo1aqQuXbpo27Ztys7Odtpms9kUFRXlGPv888/VvHlzlS1bVhUqVFDfvn11+vRpp+/J7R6nn3/+WX/5y1/k6+srf39/9e/fX/v27ZPNZtPcuXNz1Prjjz8qJiZG3t7eqly5skaOHKmsrCxJv93/U7lyZUnSpEmTHJffTZw48bbHn5fw8HBNmzZNly9f1owZMxzjud3jtGvXLkVHR6tSpUoqW7asateurYEDB+arrlv3bx07dkxdu3aVj4+PnnzyyTx/ZrckJCSoZs2aKlu2rNq1a6cDBw44bW/fvr3at2+fY7/ff6ZZbbnd4/Trr7/qtddeU926dWW321WrVi29/PLLysjIcJpXq1Ytde/eXZs3b1arVq3k5eWlOnXq6NNPP839Bw4AFiM4AUAh+t///V/VqVPnju/3OX78uJYvX67u3btr6tSpGjVqlJKSktSuXTv99NNPjnlz5szRc889p7CwME2bNk2TJk1SRESEtm/f7pgzZMgQzZo1S71799Z7772nkSNHqmzZsvrhhx9uW0ObNm2UmZnp9FlbtmxRZGSkIiMjlZaW5vRL+ZYtW9SgQQNVrFhRkjR58mTFxsYqNDRUU6dO1fDhw7Vu3Tq1bdtWly9fzvN7s7Oz1aNHD/3rX/9S//79NXnyZJ09e1b9+/fPdX5WVpaio6NVsWJFvf3222rXrp2mTJmiDz74QJJUuXJlzZo1S5LUq1cvffbZZ/rss8/06KOP3vb4b+exxx5T2bJl9c033+Q559y5c+rUqZNOnDihl156SdOnT9eTTz6pbdu25buuX3/9VdHR0apSpYrefvtt9e7d+7Z1ffrpp3r33Xc1dOhQjRkzRgcOHNBDDz2k1NRUl47vTn5mgwYN0vjx49WsWTMlJCSoXbt2io+PV9++fXPMPXr0qB577DE9/PDDmjJligICAjRgwAAdPHjQpToBoEgYAIBCkZaWZkgyevbsme99atasafTv39/x/saNG0ZWVpbTnOTkZMNutxuvvvqqY6xnz55Go0aNbvvZfn5+xtChQ/Ndyy0HDx40JBmvvfaaYRiGkZmZaZQvX9745z//aRiGYQQGBhozZ840DMMw0tPTDXd3d2Pw4MGGYRjGiRMnDHd3d2Py5MlOn5mUlGR4eHg4jffv39+oWbOm4/2SJUsMSca0adMcY1lZWcZDDz1kSDI++eQTp30lOf1MDMMwmjZtajRv3tzx/vz584YkY8KECfk69u+++86QZCxatCjPOeHh4UZAQIDj/SeffGJIMpKTkw3DMIxly5YZkoydO3fm+Rm3q+vWsb300ku5bvv9zyw5OdmQZJQtW9Y4c+aMY3z79u2GJOOFF15wjLVr185o166d6WferrYJEyYYv/9VYu/evYYkY9CgQU7zRo4caUgy1q9f7xirWbOmIcnYtGmTY+zcuXOG3W43RowYkeO7AMBqnHECgEKSnp4uSfLx8bnjz7Db7XJz++1/qrOysvTzzz/L29tb9evXd7rEzt/fX2fOnNHOnTvz/Cx/f39t377d6UxVfjRs2FAVK1Z03Lu0b98+Xb161XEWLTIy0rFARGJiorKyshz3Ny1dulTZ2dn685//rAsXLjheQUFBCg0NzXVFvltWr16tMmXKaPDgwY4xNzc3DR06NM99hgwZ4vT+wQcf1PHjx106Xld5e3vrl19+yXO7v7+/JGnFihXKzMy84+955pln8j03JiZG1apVc7xv1aqV7r//fn399dd3/P35cevz4+LinMZHjBghSTnu5wsLC9ODDz7oeF+5cmXVr1+/0P/OAOBOEJwAoJD4+vpK0m1/qTaTnZ2thIQEhYaGym63q1KlSqpcubL279+vtLQ0x7wXX3xR3t7eatWqlUJDQzV06NAcq929+eabOnDggEJCQtSqVStNnDgxX7+g2mw2RUZGOu5l2rJli6pUqaJ69epJcg5Ot/7zVnD673//K8MwFBoaqsqVKzu9fvjhB507dy7P7z158qSCg4NVrlw5p/Fb3/tHXl5ejvtxbgkICNClS5dMj/FuXLly5bbhuF27durdu7cmTZqkSpUqqWfPnvrkk09y3PNzOx4eHqpevXq+54eGhuYYu++++wr92VInT56Um5tbjr+joKAg+fv76+TJk07jNWrUyPEZRfF3BgB3guAEAIXE19dXVatWzXFTviveeOMNxcXFqW3btvr888+1Zs0arV27Vo0aNXJakKFhw4Y6fPiw5s+frzZt2mjJkiVq06aNJkyY4Jjz5z//WcePH9f06dNVtWpVvfXWW2rUqJFWrVplWkebNm2UlpampKQkx/1Nt0RGRurkyZP68ccftXnzZlWtWlV16tSR9Fvws9lsWr16tdauXZvj9f7779/xz+aPCnslu9xkZmbqyJEjeYY56bfguXjxYiUmJmrYsGH68ccfNXDgQDVv3lxXrlzJ1/f8/sxjQcnrwbW3FtMojM/+o7z+zgzDuOsaAKCgEZwAoBB1795dx44dU2Ji4h3tv3jxYnXo0EEfffSR+vbtq06dOqljx465LqpQvnx59enTR5988olOnTqlbt26afLkybpx44ZjTnBwsP7+979r+fLlSk5OVsWKFTV58mTTOn7/PKctW7Y4rZjXvHlz2e12bdiwQdu3b3faVrduXRmGodq1a6tjx445Xg888ECe31mzZk2dPXtW165dcxo/evSoab15ye8v9Pm1ePFiXb9+XdHR0aZzH3jgAU2ePFm7du3SF198oYMHD2r+/PmFUtd///vfHGNHjhxxWoEvICAg1z7641khV2qrWbOmsrOzc3x/amqqLl++7NKzrQCguCE4AUAhGj16tMqXL69BgwbluqLZsWPH9M477+S5v7u7e45/fV+0aJF+/PFHp7Gff/7Z6b2np6fCwsJkGIYyMzOVlZXldGmfJFWpUkVVq1bN1yVjLVq0kJeXl7744gv9+OOPTmec7Ha7mjVrppkzZ+rq1atOz2969NFH5e7urkmTJuU4DsMwctT9e9HR0crMzNScOXMcY9nZ2Zo5c6ZpvXm5ddnf7Vbzy699+/Zp+PDhCggIuO19V5cuXcpx7BEREZLk+NkXZF2StHz5cqce2bFjh7Zv364uXbo4xurWratDhw7p/PnzjrF9+/bluMTTldq6du0qSZo2bZrT+NSpUyVJ3bp1c+k4AKA44al1AFCI6tatq3nz5qlPnz5q2LChYmNj1bhxY928eVNbt27VokWLNGDAgDz37969u1599VU99dRTioyMVFJSkr744gvHpXC3dOrUSUFBQYqKilJgYKB++OEHzZgxQ926dZOPj48uX76s6tWr67HHHlN4eLi8vb317bffaufOnZoyZYrpcXh6eqply5b697//LbvdrubNmzttj4yMdHzO74NT3bp19frrr2vMmDE6ceKEYmJi5OPjo+TkZC1btkx/+9vfNHLkyFy/MyYmRq1atdKIESN09OhRNWjQQF999ZUuXrwo6c7O0pQtW1ZhYWFasGCB7rvvPlWoUEGNGzdW48aNb7vfv//9b924ccOxQMeWLVv01Vdfyc/PT8uWLVNQUFCe+/7zn//Ue++9p169eqlu3br65ZdfNGfOHPn6+jqCxp3WlZd69eqpTZs2euaZZ5SRkaFp06apYsWKGj16tGPOwIEDNXXqVEVHR+uvf/2rzp07p9mzZ6tRo0aOhU1crS08PFz9+/fXBx98oMuXL6tdu3basWOH/vnPfyomJkYdOnS4o+MBgGLBugX9AKD0OHLkiDF48GCjVq1ahqenp+Hj42NERUUZ06dPN27cuOGYl9ty5CNGjDCCg4ONsmXLGlFRUUZiYmKOpaTff/99o23btkbFihUNu91u1K1b1xg1apSRlpZmGIZhZGRkGKNGjTLCw8MNHx8fo3z58kZ4eLjx3nvv5fsYxowZY0gyIiMjc2xbunSpIcnw8fExfv311xzblyxZYrRp08YoX768Ub58eaNBgwbG0KFDjcOHDzvm/HEZbMP4bSnsJ554wvDx8TH8/PyMAQMGGFu2bDEkGfPnz3fat3z58jm+94/LZRuGYWzdutVo3ry54enpabo0+a3lyG+9ypQpY1SuXNlo27atMXnyZOPcuXM59vnjcuR79uwx+vXrZ9SoUcOw2+1GlSpVjO7duxu7du3KV115HVtuP7Nby5G/9dZbxpQpU4yQkBDDbrcbDz74oLFv374c+3/++edGnTp1DE9PTyMiIsJYs2ZNrn8PedWW2883MzPTmDRpklG7dm2jTJkyRkhIiDFmzBinPjeM33q9W7duOWrKa5l0ALCazTC4AxMAcO9Yvny5evXqpc2bNzvdTwUAQGEiOAEAiq3r16+rbNmyjvdZWVnq1KmTdu3apZSUFKdtAAAUJu5xAgAUW88++6yuX7+u1q1bKyMjQ0uXLtXWrVv1xhtvEJoAAEWKM04AgGJr3rx5mjJlio4ePaobN26oXr16euaZZzRs2DCrSwMAlDIEJwAAAAAwwXOcAAAAAMAEwQkAAAAATJS6xSGys7P1008/ycfH544enggAAACgZDAMQ7/88ouqVq0qN7fbn1MqdcHpp59+UkhIiNVlAAAAACgmTp8+rerVq992TqkLTj4+PpJ+++H4+vpaXA0AAAAAq6SnpyskJMSREW6n1AWnW5fn+fr6EpwAAAAA5OsWHhaHAAAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMGFpcIqPj1fLli3l4+OjKlWqKCYmRocPH77tPnPnzpXNZnN6eXl5FVHFAAAAAEojS4PTxo0bNXToUG3btk1r165VZmamOnXqpKtXr952P19fX509e9bxOnnyZBFVDAAAAKA0svQBuKtXr3Z6P3fuXFWpUkW7d+9W27Zt89zPZrMpKCiosMsDAAAAAEnF7B6ntLQ0SVKFChVuO+/KlSuqWbOmQkJC1LNnTx08eDDPuRkZGUpPT3d6AQAAAIArik1wys7O1vDhwxUVFaXGjRvnOa9+/fr6+OOP9eWXX+rzzz9Xdna2IiMjdebMmVznx8fHy8/Pz/EKCQkprEMAAAAAUELZDMMwrC5Ckp555hmtWrVKmzdvVvXq1fO9X2Zmpho2bKh+/frptddey7E9IyNDGRkZjvfp6ekKCQlRWlqafH19C6R2AAAAAPee9PR0+fn55SsbWHqP0y3Dhg3TihUrtGnTJpdCkySVKVNGTZs21dGjR3PdbrfbZbfbC6JMAAAAAKWUpZfqGYahYcOGadmyZVq/fr1q167t8mdkZWUpKSlJwcHBhVAhAAAAAFh8xmno0KGaN2+evvzyS/n4+CglJUWS5Ofnp7Jly0qSYmNjVa1aNcXHx0uSXn31VT3wwAOqV6+eLl++rLfeeksnT57UoEGDLDsOAAAAACWbpcFp1qxZkqT27ds7jX/yyScaMGCAJOnUqVNyc/u/E2OXLl3S4MGDlZKSooCAADVv3lxbt25VWFhYUZUNAACAUmxO4iNWl4A8DG79VaF9drFZHKKouHIDGAAAAPBHBKfiy9Xg5Eo2KDbLkQMAAABAcUVwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMEFwAgAAAAATBCcAAAAAMGFpcIqPj1fLli3l4+OjKlWqKCYmRocPHzbdb9GiRWrQoIG8vLzUpEkTff3110VQLQAAAIDSytLgtHHjRg0dOlTbtm3T2rVrlZmZqU6dOunq1at57rN161b169dPf/3rX/X9998rJiZGMTExOnDgQBFWDgAAAKA0sRmGYVhdxC3nz59XlSpVtHHjRrVt2zbXOX369NHVq1e1YsUKx9gDDzygiIgIzZ492/Q70tPT5efnp7S0NPn6+hZY7QAAACgd5iQ+YnUJyMPg1l+5NN+VbFCs7nFKS0uTJFWoUCHPOYmJierYsaPTWHR0tBITE3Odn5GRofT0dKcXAAAAALii2ASn7OxsDR8+XFFRUWrcuHGe81JSUhQYGOg0FhgYqJSUlFznx8fHy8/Pz/EKCQkp0LoBAAAAlHzFJjgNHTpUBw4c0Pz58wv0c8eMGaO0tDTH6/Tp0wX6+QAAAABKPg+rC5CkYcOGacWKFdq0aZOqV69+27lBQUFKTU11GktNTVVQUFCu8+12u+x2e4HVCgAAAKD0sfSMk2EYGjZsmJYtW6b169erdu3apvu0bt1a69atcxpbu3atWrduXVhlAgAAACjlLD3jNHToUM2bN09ffvmlfHx8HPcp+fn5qWzZspKk2NhYVatWTfHx8ZKk559/Xu3atdOUKVPUrVs3zZ8/X7t27dIHH3xg2XEAAAAAKNksPeM0a9YspaWlqX379goODna8FixY4Jhz6tQpnT171vE+MjJS8+bN0wcffKDw8HAtXrxYy5cvv+2CEgAAAABwNyw945SfR0ht2LAhx9jjjz+uxx9/vBAqAgAAAICcis2qegAAAABQXBGcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMAEwQkAAAAATBCcAAAAAMCEh9UF3Cu6txltdQm4jRWb37S6BAAAAJRgnHECAAAAABMuByd3d3edO3cux/jPP/8sd3f3AikKAAAAAIoTl4OTYRi5jmdkZMjT0/OuCwIAAACA4ibf9zi9++67kiSbzaYPP/xQ3t7ejm1ZWVnatGmTGjRoUPAVAgAAAIDF8h2cEhISJP12xmn27NlOl+V5enqqVq1amj17dsFXCAAAAAAWy3dwSk5OliR16NBBS5cuVUBAQKEVBQAAAADFicvLkX/33XeFUQcAAAAAFFsuB6esrCzNnTtX69at07lz55Sdne20ff369QVWHAAAAAAUBy6vqvf888/r+eefV1ZWlho3bqzw8HCnlys2bdqkHj16qGrVqrLZbFq+fPlt52/YsEE2my3HKyUlxdXDAAAAAIB8c/mM0/z587Vw4UJ17dr1rr/86tWrCg8P18CBA/Xoo4/me7/Dhw/L19fX8b5KlSp3XQsAAAAA5MXl4OTp6al69eoVyJd36dJFXbp0cXm/KlWqyN/fv0BqAAAAAAAzLl+qN2LECL3zzjt5Pgi3KERERCg4OFgPP/ywtmzZYlkdAAAAAEqHfJ1x+uNldOvXr9eqVavUqFEjlSlTxmnb0qVLC666PwgODtbs2bPVokULZWRk6MMPP1T79u21fft2NWvWLNd9MjIylJGR4Xifnp5eaPUBAAAAKJnyFZz8/Pyc3vfq1atQijFTv3591a9f3/E+MjJSx44dU0JCgj777LNc94mPj9ekSZOKqkQAAAAAJVC+gtMnn3xS2HXcsVatWmnz5s15bh8zZozi4uIc79PT0xUSElIUpQEAAAAoIVxeHKK42bt3r4KDg/PcbrfbZbfbi7AiAAAAACWNy8GpadOmstlsOcZtNpu8vLxUr149DRgwQB06dDD9rCtXrujo0aOO98nJydq7d68qVKigGjVqaMyYMfrxxx/16aefSpKmTZum2rVrq1GjRrpx44Y+/PBDrV+/Xt98842rhwEAAAAA+ebyqnqdO3fW8ePHVb58eXXo0EEdOnSQt7e3jh07ppYtW+rs2bPq2LGjvvzyS9PP2rVrl5o2baqmTZtKkuLi4tS0aVONHz9eknT27FmdOnXKMf/mzZsaMWKEmjRponbt2mnfvn369ttv9ac//cnVwwAAAACAfLMZLq4rPnjwYNWoUUPjxo1zGn/99dd18uRJzZkzRxMmTNDKlSu1a9euAi22IKSnp8vPz09paWlOD9E1073N6EKsCndrxeY3rS4BAACUEnMSH7G6BORhcOuvXJrvSjZw+YzTwoUL1a9fvxzjffv21cKFCyVJ/fr10+HDh139aAAAAAAollwOTl5eXtq6dWuO8a1bt8rLy0uSlJ2d7fgzAAAAANzrXF4c4tlnn9WQIUO0e/dutWzZUpK0c+dOffjhh3r55ZclSWvWrFFERESBFgoAAAAAVnE5OI0dO1a1a9fWjBkzHA+drV+/vubMmaMnnnhCkjRkyBA988wzBVspAAAAAFjkjp7j9OSTT+rJJ5/Mc3vZsmXvuCAAAAAAKG5cvscJAAAAAEqbfJ1xqlChgo4cOaJKlSopICAg1wfg3nLx4sUCKw4AAAAAioN8BaeEhAT5+PhIkqZNm1aY9QAAAABAsZOv4NS/f/9c/wwAAAAApcEd3eN07NgxjR07Vv369dO5c+ckSatWrdLBgwcLtDgAAAAAKA5cDk4bN25UkyZNtH37di1dulRXrlyRJO3bt08TJkwo8AIBAAAAwGouB6eXXnpJr7/+utauXStPT0/H+EMPPaRt27YVaHEAAAAAUBy4HJySkpLUq1evHONVqlTRhQsXCqQoAAAAAChOXA5O/v7+Onv2bI7x77//XtWqVSuQogAAAACgOHE5OPXt21cvvviiUlJSZLPZlJ2drS1btmjkyJGKjY0tjBoBAAAAwFIuB6c33nhDDRo0UEhIiK5cuaKwsDC1bdtWkZGRGjt2bGHUCAAAAACWytdznCQpIyNDdrtdnp6emjNnjsaNG6cDBw7oypUratq0qUJDQwuzTgAAAACwTL6Dk5+fn1q3bq0OHTrooYce0v33368aNWoUZm0AAAAAUCzk+1K92bNnq2bNmvr444/Vtm1b+fv76+GHH1Z8fLy2bdumrKyswqwTAAAAACyT7+A0YMAAzZ07VydOnNDRo0c1ffp0Va1aVbNnz1ZUVJQCAgLUrVu3wqwVAAAAACyR70v1fq9OnTqqU6eOBg4cqOTkZH300UeaPn26Vq9eXdD1AQAAAIDlXA5Op06d0nfffacNGzZow4YNunDhgh544AGNHDlS7dq1K4waAQAAAMBS+Q5OAwcO1IYNG3Tx4kVFRUXpwQcf1N/+9je1bNlSHh53dOIKAAAAAO4J+U48c+fOVY0aNfTKK6/oT3/6k5o2bSqbzVaYtQEAAABAsZDv4PTDDz84LtGbMmWKMjIy1KZNG7Vr107t27dXs2bN5Obm8vN0AQAAAKDYy3dwql+/vurXr68hQ4ZIkv7zn/9o48aN+u677/T222/rxo0batOmjVasWFFoxQIAYLWIdydYXQLysPe5SVaXAKAEu+Obk8LCwlSxYkUFBAQoICBA8+fP16pVqwqyNgAAAAAoFlwKTufOndOGDRscl+wdOXJEnp6eatWqlV544QV16NChsOoEAAAAAMvkOzg1bNhQR44ckYeHh1q2bKnHHntM7du3V1RUlLy8vAqzRgAAAACwVL6DU0xMjDp06KA2bdqoXLlyhVkTAAAAABQr+Q5O8fHxhVkHAAAAABRbPLkWAFzQ8sVXrS4Bedj5/8ZbXQIAoATjwUsAAAAAYILgBAAAAAAmCE4AAAAAYMLl4LR69Wpt3rzZ8X7mzJmKiIjQE088oUuXLhVocQAAAABQHLgcnEaNGqX09HRJUlJSkkaMGKGuXbsqOTlZcXFxBV4gAAAAAFjN5VX1kpOTFRYWJklasmSJunfvrjfeeEN79uxR165dC7xAAAAAALCay2ecPD09de3aNUnSt99+q06dOkmSKlSo4DgTBQAAAAAlictnnNq0aaO4uDhFRUVpx44dWrBggSTpyJEjql69eoEXCAAAAABWc/mM04wZM+Th4aHFixdr1qxZqlatmiRp1apV6ty5c4EXCAAAAABWc/mMU40aNbRixYoc4wkJCQVSEAAAAAAUNy6fcdqzZ4+SkpIc77/88kvFxMTo5Zdf1s2bNwu0OAAAAAAoDlwOTk8//bSOHDkiSTp+/Lj69u2rcuXKadGiRRo9enSBFwgAAAAAVnM5OB05ckQRERGSpEWLFqlt27aaN2+e5s6dqyVLlhR0fQAAAABgOZeDk2EYys7OlvTbcuS3nt0UEhKiCxcuFGx1AAAAAFAMuBycWrRooddff12fffaZNm7cqG7dukn67cG4gYGBBV4gAAAAAFjN5eA0bdo07dmzR8OGDdMrr7yievXqSZIWL16syMjIAi8QAAAAAKzm8nLk//M//+O0qt4tb731ltzd3QukKAAAAAAoTlwOTnnx8vIqqI8CAAAAgGLF5eCUlZWlhIQELVy4UKdOncrx7KaLFy8WWHEAAAAAUBy4fI/TpEmTNHXqVPXp00dpaWmKi4vTo48+Kjc3N02cOLEQSgQAAAAAa7kcnL744gvNmTNHI0aMkIeHh/r166cPP/xQ48eP17Zt2wqjRgAAAACwlMvBKSUlRU2aNJEkeXt7Ky0tTZLUvXt3rVy5smCrAwAAAIBiwOXgVL16dZ09e1aSVLduXX3zzTeSpJ07d8putxdsdQAAAABQDLgcnHr16qV169ZJkp599lmNGzdOoaGhio2N1cCBAwu8QAAAAACwmsur6v3jH/9w/LlPnz6qUaOGEhMTFRoaqh49ehRocQAAAABQHNz1c5xat26t1q1bF0QtAAAAxd4T/zvS6hKQh3k93ra6BJRg+QpOX331Vb4/8JFHHrnjYgAAAACgOMpXcIqJicnXh9lsNmVlZd1NPQAAAABQ7OQrOGVnZxd2HQAAAABQbLm8qh4AAAAAlDb5Dk7r169XWFiY0tPTc2xLS0tTo0aNtGnTpgItDgAAAACKg3wHp2nTpmnw4MHy9fXNsc3Pz09PP/20EhISCrQ4AAAAACgO8h2c9u3bp86dO+e5vVOnTtq9e7dLX75p0yb16NFDVatWlc1m0/Lly0332bBhg5o1aya73a569epp7ty5Ln0nAAAAALgq38EpNTVVZcqUyXO7h4eHzp8/79KXX716VeHh4Zo5c2a+5icnJ6tbt27q0KGD9u7dq+HDh2vQoEFas2aNS98LAAAAAK7I9wNwq1WrpgMHDqhevXq5bt+/f7+Cg4Nd+vIuXbqoS5cu+Z4/e/Zs1a5dW1OmTJEkNWzYUJs3b1ZCQoKio6Nd+m4AAAAAyK98n3Hq2rWrxo0bpxs3buTYdv36dU2YMEHdu3cv0OL+KDExUR07dnQai46OVmJiYp77ZGRkKD093ekFAAAAAK7I9xmnsWPHaunSpbrvvvs0bNgw1a9fX5J06NAhzZw5U1lZWXrllVcKrVBJSklJUWBgoNNYYGCg0tPTdf36dZUtWzbHPvHx8Zo0aVKh1gUAAACgZMt3cAoMDNTWrVv1zDPPaMyYMTIMQ5Jks9kUHR2tmTNn5gg1xcGYMWMUFxfneJ+enq6QkBALKwIAAABwr8l3cJKkmjVr6uuvv9alS5d09OhRGYah0NBQBQQEFFZ9ToKCgpSamuo0lpqaKl9f31zPNkmS3W6X3W4vivIAAAAAlFAuBadbAgIC1LJly4KuxVTr1q319ddfO42tXbtWrVu3LvJaAAAAAJQe+V4cojBcuXJFe/fu1d69eyX9ttz43r17derUKUm/XWYXGxvrmD9kyBAdP35co0eP1qFDh/Tee+9p4cKFeuGFF6woHwAAAEApYWlw2rVrl5o2baqmTZtKkuLi4tS0aVONHz9eknT27FlHiJKk2rVra+XKlVq7dq3Cw8M1ZcoUffjhhyxFDgAAAKBQ3dGlegWlffv2jkUmcjN37txc9/n+++8LsSoAAAAAcGbpGScAAAAAuBcQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwQnAAAAADABMEJAAAAAEwUi+A0c+ZM1apVS15eXrr//vu1Y8eOPOfOnTtXNpvN6eXl5VWE1QIAAAAobSwPTgsWLFBcXJwmTJigPXv2KDw8XNHR0Tp37lye+/j6+urs2bOO18mTJ4uwYgAAAACljeXBaerUqRo8eLCeeuophYWFafbs2SpXrpw+/vjjPPex2WwKCgpyvAIDA4uwYgAAAACljaXB6ebNm9q9e7c6duzoGHNzc1PHjh2VmJiY535XrlxRzZo1FRISop49e+rgwYNFUS4AAACAUsrS4HThwgVlZWXlOGMUGBiolJSUXPepX7++Pv74Y3355Zf6/PPPlZ2drcjISJ05cybX+RkZGUpPT3d6AQAAAIArLL9Uz1WtW7dWbGysIiIi1K5dOy1dulSVK1fW+++/n+v8+Ph4+fn5OV4hISFFXDEAAACAe52lwalSpUpyd3dXamqq03hqaqqCgoLy9RllypRR06ZNdfTo0Vy3jxkzRmlpaY7X6dOn77puAAAAAKWLpcHJ09NTzZs317p16xxj2dnZWrdunVq3bp2vz8jKylJSUpKCg4Nz3W632+Xr6+v0AgAAAABXeFhdQFxcnPr3768WLVqoVatWmjZtmq5evaqnnnpKkhQbG6tq1aopPj5ekvTqq6/qgQceUL169XT58mW99dZbOnnypAYNGmTlYQAAAAAowSwPTn369NH58+c1fvx4paSkKCIiQqtXr3YsGHHq1Cm5uf3fibFLly5p8ODBSklJUUBAgJo3b66tW7cqLCzMqkMAAAAAUMJZHpwkadiwYRo2bFiu2zZs2OD0PiEhQQkJCUVQFQAAAAD85p5bVQ8AAAAAihrBCQAAAABMEJwAAAAAwATBCQAAAABMEJwAAAAAwATBCQAAAABMEJwAAAAAwATBCQAAAABMFIsH4AL3godiX7O6BNzG+k/HWV0CAAAowTjjBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmCE4AAAAAYILgBAAAAAAmikVwmjlzpmrVqiUvLy/df//92rFjx23nL1q0SA0aNJCXl5eaNGmir7/+uogqBQAAAFAaWR6cFixYoLi4OE2YMEF79uxReHi4oqOjde7cuVznb926Vf369dNf//pXff/994qJiVFMTIwOHDhQxJUDAAAAKC0sD05Tp07V4MGD9dRTTyksLEyzZ89WuXLl9PHHH+c6/5133lHnzp01atQoNWzYUK+99pqaNWumGTNmFHHlAAAAAEoLDyu//ObNm9q9e7fGjBnjGHNzc1PHjh2VmJiY6z6JiYmKi4tzGouOjtby5ctznZ+RkaGMjAzH+7S0NElSenq6S7Vm/pphPgmWcfXv8078evNGoX8H7lxR9IAkZWXQB8VVkfXADf7/oLgqqh7IvEYPFFdF1QPXr2YWyffAda72wK35hmGYzrU0OF24cEFZWVkKDAx0Gg8MDNShQ4dy3SclJSXX+SkpKbnOj4+P16RJk3KMh4SE3GHVKI78/N61ugRYzG/BG1aXAIv5vRNvdQmwmN+L/8/qEmCxxeIKpNLuefnd0X6//PKL/Pxuv6+lwakojBkzxukMVXZ2ti5evKiKFSvKZrNZWJl10tPTFRISotOnT8vX19fqcmABegD0AOgBSPQB6AHDMPTLL7+oatWqpnMtDU6VKlWSu7u7UlNTncZTU1MVFBSU6z5BQUEuzbfb7bLb7U5j/v7+d150CeLr61sq/wuC/0MPgB4APQCJPkDp7gGzM023WLo4hKenp5o3b65169Y5xrKzs7Vu3Tq1bt06131at27tNF+S1q5dm+d8AAAAALhbll+qFxcXp/79+6tFixZq1aqVpk2bpqtXr+qpp56SJMXGxqpatWqKj//t2vXnn39e7dq105QpU9StWzfNnz9fu3bt0gcffGDlYQAAAAAowSwPTn369NH58+c1fvx4paSkKCIiQqtXr3YsAHHq1Cm5uf3fibHIyEjNmzdPY8eO1csvv6zQ0FAtX75cjRs3tuoQ7jl2u10TJkzIcQkjSg96APQA6AFI9AHoAVfYjPysvQcAAAAApZjlD8AFAAAAgOKO4AQAAAAAJghOAAAAAGCC4AQAAAAAJghOAAAAAGDC8uXIUbhu3ryp5cuXKzExUSkpKZKkoKAgRUZGqmfPnvL09LS4QlgpNTVV77//vsaPH291KShkZ86ckb+/v7y9vZ3GMzMzlZiYqLZt21pUGYrCzz//rP379ys8PFwVKlTQhQsX9NFHHykjI0OPP/64GjZsaHWJsEidOnW0Zs0ahYaGWl0KiphhGNqwYYOOHj2q4OBgRUdHq0yZMlaXVayxHHkJdvToUUVHR+unn37S/fff73g2VmpqqrZv367q1atr1apVqlevnsWVwir79u1Ts2bNlJWVZXUpKCRnz55Vz549tXv3btlsNj3xxBN67733HAEqNTVVVatWpQdKsB07dqhTp05KT0+Xv7+/1q5dq8cff1weHh7Kzs7WTz/9pM2bN6tZs2ZWl4pC9O677+Y6HhcXp9GjRysoKEiS9NxzzxVlWShCXbt21b/+9S/5+fnp4sWL6tq1q3bs2KFKlSrp559/1n333adNmzapcuXKVpdabBGcSrCHH35Y5cuX16effipfX1+nbenp6YqNjdX169e1Zs0aiypEYdu/f/9ttx86dEj9+vXjl+YSrH///jp8+LBmzJihy5cv66WXXpLNZtM333yjgIAApaamKjg4WNnZ2VaXikLy8MMPq1atWpo6daref/99vfPOO+rcubPmzJkjSRo4cKAuXbqkZcuWWVwpCpObm5uqVasmDw/ni41OnjypqlWrqkyZMrLZbDp+/LhFFaKwubm5KSUlRVWqVNHf//53bdy4UStWrFDt2rV15swZxcTEqGXLlpo1a5bVpRZbBKcSrFy5ctqxY4caN26c6/akpCTdf//9unbtWhFXhqLi5uYmm82m3P5rfmvcZrMRnEqwatWqadmyZWrVqpUkOS7NOn36tNatW6fMzEzOOJVwFSpU0JYtW9SwYUNlZmbKy8tLiYmJjp7Ys2ePHnnkEZ05c8biSlGYhgwZou3bt2vevHlOl2aWKVNG+/btU1hYmIXVoSj8Pjg1aNBAb775ph555BHH9nXr1mnw4MGE59tgcYgSzN/fXydOnMhz+4kTJ+Tv719k9aDoVahQQXPmzFFycnKO1/Hjx7VixQqrS0QhS0tLU0BAgOO93W7X0qVLVatWLXXo0EHnzp2zsDoUhZs3b6ps2bKSfvsluVy5cqpUqZJj+63LdFCyzZ49W+PHj1d0dLRmzJhhdTmwiM1mkyRdunRJdevWddpWr149/fTTT1aUdc9gcYgSbNCgQYqNjdW4ceP0pz/9yekep3Xr1un111/Xs88+a3GVKEzNmzfXTz/9pJo1a+a6/fLly7mejULJUadOHe3fv9/pxm8PDw8tWrRIjz/+uLp3725hdSgKISEhOn78uGrVqiVJmj9/voKDgx3bz5496xSkUHL16tVLrVq1UmxsrFauXKlPPvnE6pJQxAYMGCC73a7MzEwlJyerUaNGjm0pKSn8g7oJglMJ9uqrr6p8+fJ66623NGLECMe/MhiGoaCgIL344osaPXq0xVWiMA0ZMkRXr17Nc3uNGjX4P84SrkuXLvrggw/Uu3dvp/Fb4al3795colXC9e3b1+nMYrdu3Zy2f/XVV47L9lDyVatWTd9++63+8Y9/qGnTpvzjWSnSv39/x5979uyZ41aNJUuWKCIiooirurdwj1MpkZyc7LQcee3atS2uCEBR+PXXX3Xt2rUcC8T8fvuPP/6Y51lJlHzXrl2Tu7u77Ha71aWgiO3evVubN29WbGys0yW9KJ2uXr0qd3d3eXl5WV1KsUVwAgAAAAATLA4BAAAAACYITgAAAABgguAEAAAAACYITgAAAABgguBUCqxevVqbN292vJ85c6YiIiL0xBNP6NKlSxZWhqJCD4AeAD0AiT4APXA3CE6lwKhRo5Seni5JSkpK0ogRI9S1a1clJycrLi7O4upQFOgB0AOgByDRB6AH7gYPwC0FkpOTFRYWJum3h5t1795db7zxhvbs2aOuXbtaXB2KAj0AegD0ACT6APTA3eCMUyng6enpeDr0t99+q06dOkmSKlSo4PgXB5Rs9ADoAdADkOgD0AN3gzNOpUCbNm0UFxenqKgo7dixQwsWLJAkHTlyRNWrV7e4OhQFegD0AOgBSPQB6IG7wRmnUmDGjBny8PDQ4sWLNWvWLFWrVk2StGrVKnXu3Nni6lAU6AHQA6AHINEHoAfuhs0wDMPqIgAAAACgOOOMUymwZ88eJSUlOd5/+eWXiomJ0csvv6ybN29aWBmKCj0AegD0ACT6APTA3SA4lQJPP/20jhw5Ikk6fvy4+vbtq3LlymnRokUaPXq0xdWhKNADoAdAD0CiD0AP3A2CUylw5MgRRURESJIWLVqktm3bat68eZo7d66WLFlibXEoEvQA6AHQA5DoA9ADd4PgVAoYhqHs7GxJvy07eWuN/pCQEF24cMHK0lBE6AHQA6AHINEHoAfuBsGpFGjRooVef/11ffbZZ9q4caO6desm6bcHoAUGBlpcHYoCPQB6APQAJPoA9MDdIDiVAtOmTdOePXs0bNgwvfLKK6pXr54kafHixYqMjLS4OhQFegD0AOgBSPQB6IG7wXLkpdiNGzfk7u6uMmXKWF0KLEIPgB4APQCJPgA9kB8EJwAAAAAw4WF1ASh8WVlZSkhI0MKFC3Xq1Kkca/RfvHjRospQVOgB0AOgByDRB6AH7gb3OJUCkyZN0tSpU9WnTx+lpaUpLi5Ojz76qNzc3DRx4kSry0MRoAdAD4AegEQfgB64KwZKvDp16hgrVqwwDMMwvL29jaNHjxqGYRjvvPOO0a9fPytLQxGhB0APgB6AYdAHoAfuBmecSoGUlBQ1adJEkuTt7a20tDRJUvfu3bVy5UorS0MRoQdAD4AegEQfgB64GwSnUqB69eo6e/asJKlu3br65ptvJEk7d+6U3W63sjQUEXoA9ADoAUj0AeiBu0FwKgV69eqldevWSZKeffZZjRs3TqGhoYqNjdXAgQMtrg5FgR4APQB6ABJ9AHrgbrAceSmUmJioxMREhYaGqkePHlaXAwvQA6AHQA9Aog9AD7iC4AQAAAAAJniOUwn11Vdf5XvuI488UoiVwCr0AOgB0AOQ6APQAwWFM04llJtb/m5fs9lsysrKKuRqYAV6APQA6AFI9AHogYJCcAIAAAAAE6yqBwAAAAAmCE4l2Pr16xUWFqb09PQc29LS0tSoUSNt2rTJgspQVOgB0AOgByDRB6AHCgLBqQSbNm2aBg8eLF9f3xzb/Pz89PTTTyshIcGCylBU6AHQA6AHINEHoAcKAsGpBNu3b586d+6c5/ZOnTpp9+7dRVgRiho9AHoA9AAk+gD0QEEgOJVgqampKlOmTJ7bPTw8dP78+SKsCEWNHgA9AHoAEn0AeqAgEJxKsGrVqunAgQN5bt+/f7+Cg4OLsCIUNXoA9ADoAUj0AeiBgkBwKsG6du2qcePG6caNGzm2Xb9+XRMmTFD37t0tqAxFhR4APQB6ABJ9AHqgIPAcpxIsNTVVzZo1k7u7u4YNG6b69etLkg4dOqSZM2cqKytLe/bsUWBgoMWVorDQA6AHQA9Aog9ADxQIAyXaiRMnjC5duhhubm6GzWYzbDab4ebmZnTp0sU4fvy41eWhCNADoAdAD8Aw6APQA3eLM06lxKVLl3T06FEZhqHQ0FAFBARYXRKKGD0AegD0ACT6APTAnSI4AQAAAIAJFocAAAAAABMEJwAAAAAwQXACAAAAABMEJwBAiWWz2bR8+XKrywAAlAAEJwDAPSslJUXPPvus6tSpI7vdrpCQEPXo0UPr1q2zujQAQAnjYXUBAADciRMnTigqKkr+/v5666231KRJE2VmZmrNmjUaOnSoDh06ZHWJAIAShDNOAIB70t///nfZbDbt2LFDvXv31n333adGjRopLi5O27Zty3WfF198Uffdd5/KlSunOnXqaNy4ccrMzHRs37dvnzp06CAfHx/5+vqqefPm2rVrlyTp5MmT6tGjhwICAlS+fHk1atRIX3/9dZEcKwDAepxxAgDccy5evKjVq1dr8uTJKl++fI7t/v7+ue7n4+OjuXPnqmrVqkpKStLgwYPl4+Oj0aNHS5KefPJJNW3aVLNmzZK7u7v27t2rMmXKSJKGDh2qmzdvatOmTSpfvrz+85//yNvbu9COEQBQvBCcAAD3nFtPvG/QoIFL+40dO9bx51q1amnkyJGaP3++IzidOnVKo0aNcnxuaGioY/6pU6fUu3dvNWnSRJJUp06duz0MAMA9hEv1AAD3HMMw7mi/BQsWKCoqSkFBQfL29tbYsWN16tQpx/a4uDgNGjRIHTt21D/+8Q8dO3bMse25557T66+/rqioKE2YMEH79++/6+MAANw7CE4AgHtOaGiobDabSwtAJCYm6sknn1TXrl21YsUKff/993rllVd08+ZNx5yJEyfq4MGD6tatm9avX6+wsDAtW7ZMkjRo0CAdP35cf/nLX5SUlKQWLVpo+vTpBX5sAIDiyWbc6T/bAQBgoS5duigpKUmHDx/OcZ/T5cuX5e/vL5vNpmXLlikmJkZTpkzRe++953QWadCgQVq8eLEuX76c63f069dPV69e1VdffZVj25gxY7Ry5UrOPAFAKcEZJwDAPWnmzJnKyspSq1attGTJEv33v//VDz/8oHfffVetW7fOMT80NFSnTp3S/PnzdezYMb377ruOs0mSdP36dQ0bNkwbNmzQyZMntWXLFu3cuVMNGzaUJA0fPlxr1qxRcnKy9uzZo++++86xDQBQ8rE4BADgnlSnTh3t2bNHkydP1ogRI3T27FlVrlxZzZs316xZs3LMf+SRR/TCCy9o2LBhysjIULdu3TRu3DhNnDhRkuTu7q6ff/5ZsbGxSk1NVaVKlfToo49q0qRJkqSsrCwNHTpUZ86cka+vrzp37qyEhISiPGQAgIW4VA8AAAAATHCpHgAAAACYIDgBAAAAgAmCEwAAAACYIDgBAAAAgAmCEwAAAACYIDgBAAAAgAmCEwAAAACYIDgBAAAAgAmCEwAAAACYIDgBAAAAgAmCEwAAAACYIDgBAAAAgIn/D9NgAuoDZH7kAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "class_weights = [1.5923913, 0.40581717, 1.25213675, 1.2907489, 1.07720588, 2.46218487]\n",
+    "class_names_list = ['Class 0', 'Class 1', 'Class 2', 'Class 3', 'Class 4', 'Class 5']\n",
+    "\n",
+    "# Create a DataFrame for Seaborn\n",
+    "data = {'Class': class_names_list, 'Weight': class_weights}\n",
+    "df = pd.DataFrame(data)\n",
+    "# Plot the class distribution using Seaborn\n",
+    "plt.figure(figsize=(10, 5))\n",
+    "sns.barplot(x='Class', y='Weight', data=df, palette='viridis')\n",
+    "plt.title('Class Weight Distribution')\n",
+    "plt.xlabel('Class')\n",
+    "plt.ylabel('Class Weight')\n",
+    "plt.xticks(rotation='vertical')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "- Ploting from majority classes which have relatively poor resolution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "for _ in range(10):\n",
+    "    img, label = train_generator.next()\n",
+    "    if (label[0][1]==1):\n",
+    "        plt.imshow(img[0])\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_model=InceptionV3(\n",
+    "    include_top=False,\n",
+    "    weights=\"imagenet\",\n",
+    "    input_tensor=None,\n",
+    "    input_shape=(75,75,3),\n",
+    "    pooling=None,\n",
+    "    classes=6,\n",
+    "    classifier_activation=\"softmax\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for layer in base_model.layers:\n",
+    "    layer.trainable = False"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "InceptionV3_learner=models.Sequential([\n",
+    "    base_model,\n",
+    "    layers.GlobalAveragePooling2D(),\n",
+    "    layers.Dense(256, activation='relu'),\n",
+    "    layers.Dropout(0.2),\n",
+    "    layers.Dense(6, activation='softmax')\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " inception_v3 (Functional)   (None, 1, 1, 2048)        21802784  \n",
+      "                                                                 \n",
+      " global_average_pooling2d (G  (None, 2048)             0         \n",
+      " lobalAveragePooling2D)                                          \n",
+      "                                                                 \n",
+      " dense (Dense)               (None, 256)               524544    \n",
+      "                                                                 \n",
+      " dropout (Dropout)           (None, 256)               0         \n",
+      "                                                                 \n",
+      " dense_1 (Dense)             (None, 6)                 1542      \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 22,328,870\n",
+      "Trainable params: 526,086\n",
+      "Non-trainable params: 21,802,784\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "InceptionV3_learner.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "METRICS = [\n",
+    "      keras.metrics.Precision(name='precision'),\n",
+    "      keras.metrics.Recall(name='recall'),\n",
+    "      keras.metrics.AUC(name='auc'),\n",
+    "      keras.metrics.AUC(name='prc', curve='PR'), # precision-recall curve\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\arpit\\anaconda3\\envs\\tf\\lib\\site-packages\\keras\\optimizers\\optimizer_v2\\adam.py:114: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.\n",
+      "  super().__init__(name, **kwargs)\n"
+     ]
+    }
+   ],
+   "source": [
+    "InceptionV3_learner.compile(\n",
+    "    optimizer=Adam(lr=0.0001),\n",
+    "    loss='categorical_crossentropy',\n",
+    "    metrics=['accuracy', METRICS],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/100\n",
+      "28/28 [==============================] - 9s 32ms/step - loss: 1.6648 - accuracy: 0.4187 - precision: 0.6679 - recall: 0.2059 - auc: 0.7528 - prc: 0.4534\n",
+      "Epoch 2/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 1.0191 - accuracy: 0.6951 - precision: 0.8600 - recall: 0.4681 - auc: 0.9261 - prc: 0.7770\n",
+      "Epoch 3/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.8193 - accuracy: 0.7554 - precision: 0.8752 - recall: 0.6064 - auc: 0.9498 - prc: 0.8431\n",
+      "Epoch 4/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.7211 - accuracy: 0.7895 - precision: 0.8833 - recall: 0.6672 - auc: 0.9598 - prc: 0.8714\n",
+      "Epoch 5/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.6315 - accuracy: 0.8225 - precision: 0.8999 - recall: 0.7213 - auc: 0.9700 - prc: 0.9017\n",
+      "Epoch 6/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.5847 - accuracy: 0.8390 - precision: 0.9040 - recall: 0.7389 - auc: 0.9736 - prc: 0.9129\n",
+      "Epoch 7/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.5485 - accuracy: 0.8441 - precision: 0.9003 - recall: 0.7651 - auc: 0.9765 - prc: 0.9203\n",
+      "Epoch 8/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.5017 - accuracy: 0.8561 - precision: 0.9198 - recall: 0.7833 - auc: 0.9797 - prc: 0.9320\n",
+      "Epoch 9/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.4691 - accuracy: 0.8714 - precision: 0.9242 - recall: 0.8117 - auc: 0.9830 - prc: 0.9415\n",
+      "Epoch 10/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.4410 - accuracy: 0.8692 - precision: 0.9257 - recall: 0.8225 - auc: 0.9848 - prc: 0.9477\n",
+      "Epoch 11/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.4194 - accuracy: 0.8800 - precision: 0.9303 - recall: 0.8276 - auc: 0.9856 - prc: 0.9508\n",
+      "Epoch 12/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.3955 - accuracy: 0.8931 - precision: 0.9374 - recall: 0.8436 - auc: 0.9882 - prc: 0.9574\n",
+      "Epoch 13/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.3781 - accuracy: 0.8970 - precision: 0.9407 - recall: 0.8481 - auc: 0.9887 - prc: 0.9603\n",
+      "Epoch 14/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.3627 - accuracy: 0.9039 - precision: 0.9394 - recall: 0.8470 - auc: 0.9892 - prc: 0.9614\n",
+      "Epoch 15/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.3420 - accuracy: 0.9022 - precision: 0.9396 - recall: 0.8584 - auc: 0.9902 - prc: 0.9648\n",
+      "Epoch 16/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.3340 - accuracy: 0.9073 - precision: 0.9372 - recall: 0.8652 - auc: 0.9910 - prc: 0.9676\n",
+      "Epoch 17/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.3199 - accuracy: 0.9050 - precision: 0.9435 - recall: 0.8652 - auc: 0.9917 - prc: 0.9696\n",
+      "Epoch 18/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.3054 - accuracy: 0.9187 - precision: 0.9466 - recall: 0.8879 - auc: 0.9928 - prc: 0.9727\n",
+      "Epoch 19/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.2886 - accuracy: 0.9198 - precision: 0.9533 - recall: 0.8828 - auc: 0.9937 - prc: 0.9759\n",
+      "Epoch 20/100\n",
+      "28/28 [==============================] - 1s 27ms/step - loss: 0.2760 - accuracy: 0.9255 - precision: 0.9516 - recall: 0.8953 - auc: 0.9940 - prc: 0.9777\n",
+      "Epoch 21/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.2645 - accuracy: 0.9403 - precision: 0.9601 - recall: 0.9039 - auc: 0.9943 - prc: 0.9801\n",
+      "Epoch 22/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.2531 - accuracy: 0.9363 - precision: 0.9631 - recall: 0.9056 - auc: 0.9952 - prc: 0.9825\n",
+      "Epoch 23/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.2413 - accuracy: 0.9386 - precision: 0.9591 - recall: 0.9078 - auc: 0.9954 - prc: 0.9828\n",
+      "Epoch 24/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.2274 - accuracy: 0.9471 - precision: 0.9635 - recall: 0.9170 - auc: 0.9961 - prc: 0.9854\n",
+      "Epoch 25/100\n",
+      "28/28 [==============================] - 1s 27ms/step - loss: 0.2288 - accuracy: 0.9482 - precision: 0.9647 - recall: 0.9170 - auc: 0.9962 - prc: 0.9858\n",
+      "Epoch 26/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.2219 - accuracy: 0.9465 - precision: 0.9655 - recall: 0.9232 - auc: 0.9962 - prc: 0.9859\n",
+      "Epoch 27/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.2083 - accuracy: 0.9465 - precision: 0.9684 - recall: 0.9238 - auc: 0.9967 - prc: 0.9877\n",
+      "Epoch 28/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.1979 - accuracy: 0.9539 - precision: 0.9686 - recall: 0.9312 - auc: 0.9968 - prc: 0.9879\n",
+      "Epoch 29/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.1905 - accuracy: 0.9539 - precision: 0.9698 - recall: 0.9300 - auc: 0.9971 - prc: 0.9891\n",
+      "Epoch 30/100\n",
+      "28/28 [==============================] - 1s 27ms/step - loss: 0.1899 - accuracy: 0.9562 - precision: 0.9740 - recall: 0.9380 - auc: 0.9974 - prc: 0.9903\n",
+      "Epoch 31/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.1697 - accuracy: 0.9619 - precision: 0.9760 - recall: 0.9471 - auc: 0.9979 - prc: 0.9921\n",
+      "Epoch 32/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.1731 - accuracy: 0.9568 - precision: 0.9705 - recall: 0.9357 - auc: 0.9980 - prc: 0.9920\n",
+      "Epoch 33/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.1638 - accuracy: 0.9625 - precision: 0.9793 - recall: 0.9425 - auc: 0.9982 - prc: 0.9933\n",
+      "Epoch 34/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.1573 - accuracy: 0.9670 - precision: 0.9795 - recall: 0.9505 - auc: 0.9981 - prc: 0.9932\n",
+      "Epoch 35/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.1520 - accuracy: 0.9681 - precision: 0.9790 - recall: 0.9534 - auc: 0.9982 - prc: 0.9934\n",
+      "Epoch 36/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.1427 - accuracy: 0.9687 - precision: 0.9830 - recall: 0.9556 - auc: 0.9985 - prc: 0.9945\n",
+      "Epoch 37/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.1397 - accuracy: 0.9716 - precision: 0.9836 - recall: 0.9579 - auc: 0.9987 - prc: 0.9954\n",
+      "Epoch 38/100\n",
+      "28/28 [==============================] - 1s 29ms/step - loss: 0.1370 - accuracy: 0.9733 - precision: 0.9825 - recall: 0.9596 - auc: 0.9986 - prc: 0.9951\n",
+      "Epoch 39/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.1304 - accuracy: 0.9721 - precision: 0.9802 - recall: 0.9585 - auc: 0.9986 - prc: 0.9952\n",
+      "Epoch 40/100\n",
+      "28/28 [==============================] - 1s 27ms/step - loss: 0.1258 - accuracy: 0.9716 - precision: 0.9825 - recall: 0.9596 - auc: 0.9988 - prc: 0.9960\n",
+      "Epoch 41/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.1260 - accuracy: 0.9738 - precision: 0.9843 - recall: 0.9636 - auc: 0.9987 - prc: 0.9955\n",
+      "Epoch 42/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.1211 - accuracy: 0.9721 - precision: 0.9843 - recall: 0.9613 - auc: 0.9988 - prc: 0.9959\n",
+      "Epoch 43/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.1169 - accuracy: 0.9807 - precision: 0.9861 - recall: 0.9687 - auc: 0.9990 - prc: 0.9967\n",
+      "Epoch 44/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.1143 - accuracy: 0.9761 - precision: 0.9861 - recall: 0.9664 - auc: 0.9989 - prc: 0.9964\n",
+      "Epoch 45/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.1102 - accuracy: 0.9790 - precision: 0.9849 - recall: 0.9642 - auc: 0.9993 - prc: 0.9971\n",
+      "Epoch 46/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.1019 - accuracy: 0.9835 - precision: 0.9907 - recall: 0.9716 - auc: 0.9992 - prc: 0.9973\n",
+      "Epoch 47/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0995 - accuracy: 0.9807 - precision: 0.9862 - recall: 0.9721 - auc: 0.9994 - prc: 0.9974\n",
+      "Epoch 48/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0923 - accuracy: 0.9846 - precision: 0.9891 - recall: 0.9790 - auc: 0.9995 - prc: 0.9980\n",
+      "Epoch 49/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0936 - accuracy: 0.9846 - precision: 0.9902 - recall: 0.9812 - auc: 0.9992 - prc: 0.9974\n",
+      "Epoch 50/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0968 - accuracy: 0.9829 - precision: 0.9913 - recall: 0.9767 - auc: 0.9993 - prc: 0.9972\n",
+      "Epoch 51/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0855 - accuracy: 0.9869 - precision: 0.9919 - recall: 0.9801 - auc: 0.9997 - prc: 0.9987\n",
+      "Epoch 52/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0820 - accuracy: 0.9886 - precision: 0.9919 - recall: 0.9801 - auc: 0.9997 - prc: 0.9987\n",
+      "Epoch 53/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0853 - accuracy: 0.9852 - precision: 0.9902 - recall: 0.9807 - auc: 0.9996 - prc: 0.9982\n",
+      "Epoch 54/100\n",
+      "28/28 [==============================] - 1s 27ms/step - loss: 0.0767 - accuracy: 0.9881 - precision: 0.9925 - recall: 0.9846 - auc: 0.9994 - prc: 0.9983\n",
+      "Epoch 55/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0791 - accuracy: 0.9875 - precision: 0.9914 - recall: 0.9835 - auc: 0.9994 - prc: 0.9984\n",
+      "Epoch 56/100\n",
+      "28/28 [==============================] - 1s 30ms/step - loss: 0.0764 - accuracy: 0.9886 - precision: 0.9942 - recall: 0.9829 - auc: 0.9996 - prc: 0.9986\n",
+      "Epoch 57/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.0721 - accuracy: 0.9898 - precision: 0.9920 - recall: 0.9852 - auc: 0.9994 - prc: 0.9983\n",
+      "Epoch 58/100\n",
+      "28/28 [==============================] - 1s 29ms/step - loss: 0.0701 - accuracy: 0.9892 - precision: 0.9943 - recall: 0.9841 - auc: 0.9995 - prc: 0.9987\n",
+      "Epoch 59/100\n",
+      "28/28 [==============================] - 1s 30ms/step - loss: 0.0699 - accuracy: 0.9881 - precision: 0.9902 - recall: 0.9807 - auc: 0.9997 - prc: 0.9988\n",
+      "Epoch 60/100\n",
+      "28/28 [==============================] - 1s 27ms/step - loss: 0.0658 - accuracy: 0.9926 - precision: 0.9960 - recall: 0.9886 - auc: 0.9995 - prc: 0.9989\n",
+      "Epoch 61/100\n",
+      "28/28 [==============================] - 1s 29ms/step - loss: 0.0619 - accuracy: 0.9920 - precision: 0.9943 - recall: 0.9903 - auc: 0.9997 - prc: 0.9989\n",
+      "Epoch 62/100\n",
+      "28/28 [==============================] - 1s 29ms/step - loss: 0.0607 - accuracy: 0.9915 - precision: 0.9943 - recall: 0.9886 - auc: 0.9998 - prc: 0.9990\n",
+      "Epoch 63/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.0611 - accuracy: 0.9915 - precision: 0.9937 - recall: 0.9858 - auc: 0.9995 - prc: 0.9986\n",
+      "Epoch 64/100\n",
+      "28/28 [==============================] - 1s 27ms/step - loss: 0.0551 - accuracy: 0.9937 - precision: 0.9966 - recall: 0.9909 - auc: 0.9999 - prc: 0.9994\n",
+      "Epoch 65/100\n",
+      "28/28 [==============================] - 1s 28ms/step - loss: 0.0569 - accuracy: 0.9932 - precision: 0.9966 - recall: 0.9903 - auc: 0.9998 - prc: 0.9993\n",
+      "Epoch 66/100\n",
+      "28/28 [==============================] - 1s 27ms/step - loss: 0.0541 - accuracy: 0.9909 - precision: 0.9931 - recall: 0.9892 - auc: 0.9998 - prc: 0.9990\n",
+      "Epoch 67/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0521 - accuracy: 0.9920 - precision: 0.9931 - recall: 0.9892 - auc: 0.9998 - prc: 0.9991\n",
+      "Epoch 68/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0480 - accuracy: 0.9949 - precision: 0.9960 - recall: 0.9926 - auc: 0.9999 - prc: 0.9995\n",
+      "Epoch 69/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0492 - accuracy: 0.9960 - precision: 0.9966 - recall: 0.9926 - auc: 0.9999 - prc: 0.9995\n",
+      "Epoch 70/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0473 - accuracy: 0.9954 - precision: 0.9960 - recall: 0.9898 - auc: 0.9999 - prc: 0.9996\n",
+      "Epoch 71/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0480 - accuracy: 0.9937 - precision: 0.9954 - recall: 0.9920 - auc: 0.9999 - prc: 0.9996\n",
+      "Epoch 72/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0428 - accuracy: 0.9972 - precision: 0.9971 - recall: 0.9932 - auc: 0.9999 - prc: 0.9997\n",
+      "Epoch 73/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0447 - accuracy: 0.9960 - precision: 0.9971 - recall: 0.9920 - auc: 0.9999 - prc: 0.9997\n",
+      "Epoch 74/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0445 - accuracy: 0.9972 - precision: 0.9972 - recall: 0.9954 - auc: 0.9999 - prc: 0.9997\n",
+      "Epoch 75/100\n",
+      "28/28 [==============================] - 1s 28ms/step - loss: 0.0425 - accuracy: 0.9954 - precision: 0.9960 - recall: 0.9926 - auc: 1.0000 - prc: 0.9998\n",
+      "Epoch 76/100\n",
+      "28/28 [==============================] - 1s 27ms/step - loss: 0.0405 - accuracy: 0.9954 - precision: 0.9977 - recall: 0.9920 - auc: 0.9999 - prc: 0.9996\n",
+      "Epoch 77/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0387 - accuracy: 0.9966 - precision: 0.9971 - recall: 0.9932 - auc: 1.0000 - prc: 0.9998\n",
+      "Epoch 78/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0378 - accuracy: 0.9966 - precision: 0.9983 - recall: 0.9949 - auc: 0.9999 - prc: 0.9997\n",
+      "Epoch 79/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0375 - accuracy: 0.9960 - precision: 0.9972 - recall: 0.9960 - auc: 1.0000 - prc: 0.9998\n",
+      "Epoch 80/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0376 - accuracy: 0.9949 - precision: 0.9960 - recall: 0.9949 - auc: 1.0000 - prc: 0.9998\n",
+      "Epoch 81/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0350 - accuracy: 0.9949 - precision: 0.9971 - recall: 0.9937 - auc: 1.0000 - prc: 0.9999\n",
+      "Epoch 82/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0341 - accuracy: 0.9966 - precision: 0.9966 - recall: 0.9949 - auc: 1.0000 - prc: 0.9998\n",
+      "Epoch 83/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0325 - accuracy: 0.9966 - precision: 0.9966 - recall: 0.9960 - auc: 1.0000 - prc: 0.9999\n",
+      "Epoch 84/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0297 - accuracy: 0.9972 - precision: 0.9977 - recall: 0.9960 - auc: 1.0000 - prc: 1.0000\n",
+      "Epoch 85/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0318 - accuracy: 0.9977 - precision: 0.9983 - recall: 0.9960 - auc: 1.0000 - prc: 0.9999\n",
+      "Epoch 86/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0302 - accuracy: 0.9972 - precision: 0.9972 - recall: 0.9954 - auc: 1.0000 - prc: 0.9999\n",
+      "Epoch 87/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0302 - accuracy: 0.9972 - precision: 0.9972 - recall: 0.9954 - auc: 1.0000 - prc: 0.9999\n",
+      "Epoch 88/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0283 - accuracy: 0.9972 - precision: 0.9983 - recall: 0.9960 - auc: 1.0000 - prc: 0.9999\n",
+      "Epoch 89/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0266 - accuracy: 0.9966 - precision: 0.9972 - recall: 0.9960 - auc: 1.0000 - prc: 0.9999\n",
+      "Epoch 90/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0270 - accuracy: 0.9977 - precision: 0.9983 - recall: 0.9972 - auc: 1.0000 - prc: 1.0000\n",
+      "Epoch 91/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0261 - accuracy: 0.9977 - precision: 0.9983 - recall: 0.9966 - auc: 1.0000 - prc: 1.0000\n",
+      "Epoch 92/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0275 - accuracy: 0.9977 - precision: 0.9977 - recall: 0.9977 - auc: 1.0000 - prc: 1.0000\n",
+      "Epoch 93/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0258 - accuracy: 0.9977 - precision: 0.9989 - recall: 0.9966 - auc: 1.0000 - prc: 1.0000\n",
+      "Epoch 94/100\n",
+      "28/28 [==============================] - 1s 29ms/step - loss: 0.0264 - accuracy: 0.9977 - precision: 0.9983 - recall: 0.9972 - auc: 1.0000 - prc: 0.9999\n",
+      "Epoch 95/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0228 - accuracy: 0.9977 - precision: 0.9983 - recall: 0.9977 - auc: 1.0000 - prc: 1.0000\n",
+      "Epoch 96/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0259 - accuracy: 0.9966 - precision: 0.9977 - recall: 0.9943 - auc: 1.0000 - prc: 0.9999\n",
+      "Epoch 97/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0231 - accuracy: 0.9983 - precision: 0.9994 - recall: 0.9966 - auc: 1.0000 - prc: 1.0000\n",
+      "Epoch 98/100\n",
+      "28/28 [==============================] - 1s 25ms/step - loss: 0.0224 - accuracy: 0.9983 - precision: 0.9989 - recall: 0.9977 - auc: 1.0000 - prc: 1.0000\n",
+      "Epoch 99/100\n",
+      "28/28 [==============================] - 1s 26ms/step - loss: 0.0232 - accuracy: 0.9983 - precision: 0.9983 - recall: 0.9977 - auc: 1.0000 - prc: 1.0000\n",
+      "Epoch 100/100\n",
+      "28/28 [==============================] - 1s 28ms/step - loss: 0.0207 - accuracy: 0.9983 - precision: 0.9994 - recall: 0.9977 - auc: 1.0000 - prc: 1.0000\n"
+     ]
+    }
+   ],
+   "source": [
+    "InceptionV3_history=InceptionV3_learner.fit(train_generator,epochs=100,class_weight=class_weight_dict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.DataFrame(InceptionV3_history.history)\n",
+    "df.to_csv(\"InceptionV3_plot.csv\",index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1600x800 with 6 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot training history for multiple metrics\n",
+    "plt.figure(figsize=(16, 8))\n",
+    "\n",
+    "# Plot training & validation accuracy values\n",
+    "plt.subplot(2, 3, 1)\n",
+    "plt.plot(InceptionV3_history.history['accuracy'])\n",
+    "plt.title('Model Accuracy')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation loss values\n",
+    "plt.subplot(2, 3, 2)\n",
+    "plt.plot(InceptionV3_history.history['loss'])\n",
+    "plt.title('Model Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation precision values\n",
+    "plt.subplot(2, 3, 3)\n",
+    "plt.plot(InceptionV3_history.history['precision'])\n",
+    "plt.title('Model Precision')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Precision')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation recall values\n",
+    "plt.subplot(2, 3, 4)\n",
+    "plt.plot(InceptionV3_history.history['recall'])\n",
+    "plt.title('Model Recall')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Recall')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation AUC values\n",
+    "plt.subplot(2, 3, 5)\n",
+    "plt.plot(InceptionV3_history.history['auc'])\n",
+    "plt.title('Model AUC')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('AUC')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation PRC values\n",
+    "plt.subplot(2, 3, 6)\n",
+    "plt.plot(InceptionV3_history.history['prc'])\n",
+    "plt.title('Model PRC')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('PRC')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "tf",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.17"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/High Throughput Algae Cell Detection/Model/Xception.ipynb b/High Throughput Algae Cell Detection/Model/Xception.ipynb
new file mode 100644
index 000000000..52798ea4f
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/Xception.ipynb	
@@ -0,0 +1,687 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Xception Model Transfer Learning"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\"import splitfolders\n",
+    "splitfolders.ratio(r\"D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\non_yolo\", output=\"D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\non_yolo_splitted\",seed=1337, ratio=(.9,.1))\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import tensorflow as tf\n",
+    "from tensorflow import keras\n",
+    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+    "import matplotlib.pyplot as plt\n",
+    "from tensorflow.keras import layers, models\n",
+    "from tensorflow.keras.applications import Xception\n",
+    "from tensorflow.keras.optimizers import Adam\n",
+    "import seaborn as sns\n",
+    "import numpy as np\n",
+    "from sklearn.utils.class_weight import compute_class_weight\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found 1758 images belonging to 6 classes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "train_datagen = ImageDataGenerator(\n",
+    "        rescale=1./255)\n",
+    "train_generator = train_datagen.flow_from_directory(\n",
+    "    directory=r\"D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\non_yolo\",\n",
+    "    target_size=(71,71),\n",
+    "    color_mode=\"rgb\",\n",
+    "    batch_size=64,\n",
+    "    class_mode=\"categorical\",\n",
+    "    shuffle=True,\n",
+    "    seed=42\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Class Distribution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "class_indices = train_generator.class_indices\n",
+    "\n",
+    "class_names = {v: k for k, v in class_indices.items()}\n",
+    "\n",
+    "class_distribution = train_generator.classes\n",
+    "\n",
+    "class_names_list = [class_names[class_idx] for class_idx in class_distribution]\n",
+    "\n",
+    "# Plot the class distribution using Seaborn\n",
+    "plt.figure(figsize=(10, 5))\n",
+    "sns.countplot(x=class_names_list, palette='viridis')\n",
+    "plt.title('Class Distribution in the Training Dataset')\n",
+    "plt.xlabel('Class')\n",
+    "plt.ylabel('Number of Samples')\n",
+    "plt.xticks(rotation='vertical')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Class Weights: [1.5923913  0.40581717 1.25213675 1.2907489  1.07720588 2.46218487]\n"
+     ]
+    }
+   ],
+   "source": [
+    "class_labels = train_generator.classes\n",
+    "class_weights = compute_class_weight(class_weight='balanced', classes=np.unique(class_labels), y=class_labels)\n",
+    "\n",
+    "print(\"Class Weights:\", class_weights)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{0: 1.5923913043478262,\n",
+       " 1: 0.40581717451523547,\n",
+       " 2: 1.2521367521367521,\n",
+       " 3: 1.2907488986784141,\n",
+       " 4: 1.0772058823529411,\n",
+       " 5: 2.46218487394958}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "class_weight_dict = {i: class_weights[i] for i in range(len(class_weights))}\n",
+    "class_weight_dict"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "- ##### This inverse proportion from our original distribution indicates Class_weight multiple requires for all class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "class_weights = [1.5923913, 0.40581717, 1.25213675, 1.2907489, 1.07720588, 2.46218487]\n",
+    "class_names_list = ['Class 0', 'Class 1', 'Class 2', 'Class 3', 'Class 4', 'Class 5']\n",
+    "\n",
+    "# Create a DataFrame for Seaborn\n",
+    "data = {'Class': class_names_list, 'Weight': class_weights}\n",
+    "df = pd.DataFrame(data)\n",
+    "# Plot the class distribution using Seaborn\n",
+    "plt.figure(figsize=(10, 5))\n",
+    "sns.barplot(x='Class', y='Weight', data=df, palette='viridis')\n",
+    "plt.title('Class Weight Distribution')\n",
+    "plt.xlabel('Class')\n",
+    "plt.ylabel('Class Weight')\n",
+    "plt.xticks(rotation='vertical')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "- Ploting from majority classes which have relatively poor resolution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAacAAAGgCAYAAAAO6qggAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAAAoR0lEQVR4nO3df3Ac9X3/8dfeSTqbSDphY0tWkYySGGR+mB8yyMKkaUGNx2Uo1IISxpmYQMvgCgfb7YSoDTh0UuQm09ihg02h1CaTuG6ciR2cBlxHgJg0so0FDhhqYYInVmNLJm11J7vxSb79fP8wvnC2BNx9dr/6nPx8zOyMtXf70eezt3cv7fmz+/aMMUYAADgkMtYdAADgdIQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOaGF02OPPaYLLrhAEyZMUGNjo3bt2hXWrwIAjDNeGPfW+9d//Vd9/vOf1+OPP67GxkatXr1amzZtUk9Pj6ZOnfqB2/q+r0OHDqmsrEye5wXdNQBAyIwxGhwcVHV1tSKRPM+BTAiuueYa09ramvk5nU6b6upq097e/qHb9vb2GkksLCwsLAW+9Pb25p0jRQrY0NCQuru71dbWllkXiUTU3Nysrq6uM56fSqWUSqUyP5v3TuR27d6p0tLSwPrlRfz8N46eCKwfp0QidmeFYdxL/sSJ/PdRxAT/DXEkYnl4WrzkowphnJ5Fm74J/thM+6kPf9IHCOMbj+KSCXlv6/vBHwi+5RvQC+E/VFz6puno4FHNvmqOysrK8m4j8HD69a9/rXQ6rcrKyqz1lZWV2rdv3xnPb29v18MPP3zG+tLSUquBnc65cIpahlMIH7yE00dwVoRTsdX24YTTxLy3JZzGjk2fxny2XltbmxKJRGbp7e0d6y4BAMZY4GdO5513nqLRqPr7+7PW9/f3q6qq6oznx2IxxWKxoLsBAChggZ85lZSUqKGhQR0dHZl1vu+ro6NDTU1NQf86AMA4FPiZkyQtX75cixYt0uzZs3XNNddo9erVOnbsmL7whS+E8esAAONMKOF0++23691339VDDz2kvr4+XXHFFXruuefOmCQBAMBIQrkI10YymVQ8Hteb+95gtt4HYLbeR8Bsvbyk/eNW2zNb78ON99l6g4ODqp9xqRKJhMrLy/NqY8xn6wEAcDrCCQDgHMIJAOAcwgkA4BzCCQDgHMIJAOCcUK5zcpHNdFJP6QB7clJaltM+TfDTRm2uKghluq4/ZNlACNPbveDfMlGLbnoK/kqQvOvvvCeMKc3pdP7vQceulpEk+X4Ir5vNZ4pllYTTBbHPOXMCADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOMfZkhkRzyjiBXdb+bRFU2Hcct+z6ZAkzwuhHITyL3sRRlUC49vdxj/AwyfD13DgbXqK5r3tiRMh9CdiVyImGs1/PKNJp0/kvW006t7HnGdbMmcEViUzAu5PJIDzHs6cAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOyTmcXnrpJd10002qrq6W53nasmVL1uPGGD300EOaNm2aJk6cqObmZu3fvz+o/gIAzgJFuW5w7NgxXX755brrrru0YMGCMx7/+te/rkcffVRPP/206urq9OCDD2revHl68803NWHChEA6nQ/P+Hlva4wJsCcn+V7aanvPy/ml+1A24wxhF8k3dvsoomhAPXkfE/yXDcZ4eW+b9ocD7MlJUS///pyU/3ttNOl0/sdCJBL8a+Z5lm2GcRxF8n8T2r7iYcj5E27+/PmaP3/+iI8ZY7R69Wp95Stf0c033yxJ+va3v63Kykpt2bJFn/3sZ+16CwA4KwQa3wcOHFBfX5+am5sz6+LxuBobG9XV1TXiNqlUSslkMmsBAJzdAg2nvr4+SVJlZWXW+srKysxjp2tvb1c8Hs8sNTU1QXYJAFCAxny2XltbmxKJRGbp7e0d6y4BAMZYoOFUVVUlServ789a39/fn3nsdLFYTOXl5VkLAODsFmg41dXVqaqqSh0dHZl1yWRSO3fuVFNTU5C/CgAwjuU8W+/o0aN6++23Mz8fOHBAe/bs0aRJk1RbW6ulS5fqa1/7mmbMmJGZSl5dXa1bbrklyH4DAMaxnMNp9+7d+v3f//3Mz8uXL5ckLVq0SOvXr9eXvvQlHTt2TPfcc48GBgZ03XXX6bnnnhvTa5wAAIXFM2FcYWohmUwqHo9rX89elZWVBdaub3GxolHwFzqa8XYRrt1wRuT7dhdzFspFuNFo/v0cGj4eYE9OikbtLsksKgp+Hw0N539sFhfHAuzJSS5ehOvZXIRrfeF1tsHBQV104SVKJBJ5zyMY89l6AACcjnACADiHcAIAOIdwAgA4h3ACADiHcAIAOCf4+cgBSQ+fUHr4RGDt+cp/rrOx2HZUllPJFcIFAHZXFYRR58hukL4J7vg5xfOCn57uWdQbsp32PRLr8kde8AenVd2q4K8EkRcptmwh+PdLxGJ6eiQS7HGUDqCkF2dOAADnEE4AAOcQTgAA5xBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOc4WzLDGGNdMiG7wfxvCW9CKAFgrG8pH8A96QMVQg0PBxkTfPmUEyfy33fpdPD1IHzLlzL4Ih6SzfGVtn+zncH4dseBF8JOili8bpGA99GJAMrVcOYEAHAO4QQAcA7hBABwDuEEAHAO4QQAcA7hBABwDuEEAHAO4QQAcA7hBABwDuEEAHAO4QQAcA7hBABwDuEEAHAO4QQAcA7hBABwjrP1nDwvKs+LBtiiW/WGbGtVWZSn+oBGbf5WcWv/SlIkhDpcvh98bSCbek6+ZV2hEds8YVeLJ1oU/MdKJFKc97ZhVD7zLI9344VQY8riMyHo3vgBtMiZEwDAOYQTAMA5hBMAwDk5hVN7e7uuvvpqlZWVaerUqbrlllvU09OT9Zzjx4+rtbVVkydPVmlpqVpaWtTf3x9opwEA41tO4dTZ2anW1lbt2LFD27dv1/DwsD7zmc/o2LFjmecsW7ZMW7du1aZNm9TZ2alDhw5pwYIFgXccADB+ecZi2ti7776rqVOnqrOzU7/7u7+rRCKhKVOmaMOGDbr11lslSfv27dPMmTPV1dWlOXPmfGibyWRS8Xhcb+x9TWVlZfl27QzG5D8DKa3jgfXjFNtZVsYLYbqe1Ww99xTKbD2bmZuhzNazeK9ILs7WC74/nixnEkeCf69FLNoM+uNkcHBQV8y8UolEQuXl5Xm1YbWHEomEJGnSpEmSpO7ubg0PD6u5uTnznPr6etXW1qqrq2vENlKplJLJZNYCADi75R1Ovu9r6dKlmjt3ri699FJJUl9fn0pKSlRRUZH13MrKSvX19Y3YTnt7u+LxeGapqanJt0sAgHEi73BqbW3V3r17tXHjRqsOtLW1KZFIZJbe3l6r9gAAhS+vL2Pvu+8+/ehHP9JLL72k888/P7O+qqpKQ0NDGhgYyDp76u/vV1VV1YhtxWIxxWKxfLoBABincjpzMsbovvvu0+bNm/X888+rrq4u6/GGhgYVFxero6Mjs66np0cHDx5UU1NTMD0GAIx7OZ05tba2asOGDfrhD3+osrKyzP8jxeNxTZw4UfF4XHfffbeWL1+uSZMmqby8XEuWLFFTU9NHmqkHAICUYzitXbtWkvR7v/d7WevXrVunO++8U5K0atUqRSIRtbS0KJVKad68eVqzZk0gnQUAnB2srnMKA9c5fTRc5/ThuM4pzza5zulDcZ3TBxvz65wAAAgD4QQAcA7hBABwDuEEAHAO4QQAcA7hBABwTvBzLAPieZ68AOc3+sq/LeMHP207bTmD3wQ/g1iel/806TCuSLCdth0tkD+9bPadCeOKAtnt9xOym4o+kmKvJO9tjR/8sWn70eSF8H6xaTPome1BXMZRIG9fAMDZhHACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADjH2ZIZaf/kEhTf5N+Yp2hwHXmPbTmHE5blJEZiU4UjWhT8oRS1LN3ghVFXJATRSP71F4aHUwH25CTbUjVFxcUB9eR9LA6F4uLg378Ry1olAVSUOLNNWTQa8OdJJID2OHMCADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4x9l6TsYYGRNc0RNjkcNeJPjaSb6x+7vAWNbcGbnR/Pe3H0J9KWNZjykaRtEcm5o5o7VocSzY1l4aUTT4+ke2bMonhXJspk9YbR8J4TjyvPxfNy/g94rt/pE4cwIAOIhwAgA4h3ACADgnp3Bau3atZs2apfLycpWXl6upqUnPPvts5vHjx4+rtbVVkydPVmlpqVpaWtTf3x94pwEA41tO4XT++edr5cqV6u7u1u7du3X99dfr5ptv1htvvCFJWrZsmbZu3apNmzaps7NThw4d0oIFC0LpOABg/PKM5ZS4SZMm6Rvf+IZuvfVWTZkyRRs2bNCtt94qSdq3b59mzpyprq4uzZkz5yO1l0wmFY/H9dprr6msrMyma1l85T/zy4vYzzw53QljN4MofSKMWWP5t+lFwujP2TFbLxLJ/9v1dHo4wJ6cZKJ2Y4yGMNvPmOK8t40o+P54abv373ifrTc4eFSXXTZHiURC5eXlebWR97sinU5r48aNOnbsmJqamtTd3a3h4WE1NzdnnlNfX6/a2lp1dXWN2k4qlVIymcxaAABnt5zD6fXXX1dpaalisZjuvfdebd68WRdffLH6+vpUUlKiioqKrOdXVlaqr69v1Pba29sVj8czS01NTc6DAACMLzmH00UXXaQ9e/Zo586dWrx4sRYtWqQ333wz7w60tbUpkUhklt7e3rzbAgCMDznfIaKkpESf/OQnJUkNDQ16+eWX9a1vfUu33367hoaGNDAwkHX21N/fr6qqqlHbi8ViisViufccADBuWV/n5Pu+UqmUGhoaVFxcrI6OjsxjPT09OnjwoJqammx/DQDgLJLTmVNbW5vmz5+v2tpaDQ4OasOGDXrxxRe1bds2xeNx3X333Vq+fLkmTZqk8vJyLVmyRE1NTR95ph4AAFKO4XTkyBF9/vOf1+HDhxWPxzVr1ixt27ZNf/AHfyBJWrVqlSKRiFpaWpRKpTRv3jytWbMmlI4DAMYv6+ucgsZ1Th8N1zl9OK5zyg/XOX04rnP6YGN6nRMAAGFxt56TZ1fD5cwGA2wrALZ1eMIo4+Nb7CQTwg72Lc8uw/hSIBINfsfbjDNSHHx/PMvX0rEvY0Kp51RkeTLmKYTXzaLJoOuCeQG8TzhzAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADjH2ZIZvu8HfKv7/G/jb1NKYjSulRWwFcZ4bNu0LbkxEs+xP+e8EDpkWz4hnbYrEjmSqMUwTQj1ZYzlseWHUPImYtGnoN8p6QDee4691QAAIJwAAA4inAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4pGusOjM5/bwmGMen8N04H149TjGe3ve+bYDryfsamzeD7Y9InrLaPWO7jEds0Ifw95+V/fEVCOAzsjgPJWG4fNM8L/kBIW77/PAXfJ2PxHgz648R2/0icOQEAHEQ4AQCcQzgBAJxjFU4rV66U53launRpZt3x48fV2tqqyZMnq7S0VC0tLerv77ftJwDgLJJ3OL388sv6x3/8R82aNStr/bJly7R161Zt2rRJnZ2dOnTokBYsWGDdUQDA2SOvcDp69KgWLlyoJ598Uueee25mfSKR0FNPPaVvfvObuv7669XQ0KB169bpZz/7mXbs2BFYpwEA41te4dTa2qobb7xRzc3NWeu7u7s1PDyctb6+vl61tbXq6uqy6ykA4KyR83VOGzdu1CuvvKKXX375jMf6+vpUUlKiioqKrPWVlZXq6+sbsb1UKqVUKpX5OZlM5tolAMA4k9OZU29vr+6//35997vf1YQJEwLpQHt7u+LxeGapqakJpF0AQOHKKZy6u7t15MgRXXXVVSoqKlJRUZE6Ozv16KOPqqioSJWVlRoaGtLAwEDWdv39/aqqqhqxzba2NiUSiczS29ub92AAAONDTl/r3XDDDXr99dez1n3hC19QfX29HnjgAdXU1Ki4uFgdHR1qaWmRJPX09OjgwYNqamoasc1YLKZYLJZn9wEA41FO4VRWVqZLL700a93HPvYxTZ48ObP+7rvv1vLlyzVp0iSVl5dryZIlampq0pw5c4LrNQBgXAv8xq+rVq1SJBJRS0uLUqmU5s2bpzVr1gT9awAA45hnHLuFcDKZVDwe16s/f0VlZWWBtWt1V3LPYttR+JY3JU6fCOEu4BaHglHw+yidTn34kz5ANIS7khcVuXVX8lD6Y3mH+WE/+Lv4F0XPyX9jEw2uI+/xfbs75odxp3SbIyHoV+zo4FFdddm1SiQSKi8vz6sN7q0HAHCOs/WcIpGIIpHgstO3+WsujL9ybM7kJKW9UAr5WGwa/F/L9oLvkx/COG3qToVS18viTE6SoiH8zetZjNMPodaY7WeTa2dOQfMC+Ox2aTwAAEginAAADiKcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAznG3ZIZnFAmwLISxuG2+CaH0gq2ogr/lvm9VbDD4fWTzmkmSF8brFkaJCou/EdN+8EUebasdBFEu4XQ2JW9MCGVOPM/yozOEQpg2pX2C7o5nW01VnDkBABxEOAEAnEM4AQCcQzgBAJxDOAEAnEM4AQCcQzgBAJxDOAEAnEM4AQCcQzgBAJxDOAEAnEM4AQCcQzgBAJxDOAEAnEM4AQCc42w9Jz99cgmsPYsyPBZljj6gTbsaM8aEURAmfyaA+i2BiwTfJ2NRVygMfjqM+lJ2+60oGvzfvOm0TT2nADvyHi8Sxn63Y9Uji1pQYeHMCQDgHMIJAOAcwgkA4BzCCQDgHMIJAOAcwgkA4BzCCQDgHMIJAOCcnMLpq1/9qjzPy1rq6+szjx8/flytra2aPHmySktL1dLSov7+/sA7DQAY33I+c7rkkkt0+PDhzPLTn/4089iyZcu0detWbdq0SZ2dnTp06JAWLFgQaIcBAONfzrcvKioqUlVV1RnrE4mEnnrqKW3YsEHXX3+9JGndunWaOXOmduzYoTlz5tj3FgBwVsj5zGn//v2qrq7Wxz/+cS1cuFAHDx6UJHV3d2t4eFjNzc2Z59bX16u2tlZdXV3B9RgAMO7ldObU2Nio9evX66KLLtLhw4f18MMP61Of+pT27t2rvr4+lZSUqKKiImubyspK9fX1jdpmKpVSKpXK/JxMJnMbAQBg3MkpnObPn5/596xZs9TY2Kjp06fre9/7niZOnJhXB9rb2/Xwww/ntS0AYHyymkpeUVGhCy+8UG+//baqqqo0NDSkgYGBrOf09/eP+H9Up7S1tSmRSGSW3t5emy4BAMYBq3A6evSofvGLX2jatGlqaGhQcXGxOjo6Mo/39PTo4MGDampqGrWNWCym8vLyrAUAcHbL6Wu9v/zLv9RNN92k6dOn69ChQ1qxYoWi0ajuuOMOxeNx3X333Vq+fLkmTZqk8vJyLVmyRE1NTczUAwDkJKdw+q//+i/dcccd+u///m9NmTJF1113nXbs2KEpU6ZIklatWqVIJKKWlhalUinNmzdPa9asCaXjAIDxyzMmjCLG+Usmk4rH4/r5z19VWVlZYO2mzYm8tzXKf9tR2zR2NejDKNNucyj4fvD7yDfDVttHoiGUVPftXreRRKPRvLdNp4PvTyRqWaa9uCSgnvxW+kT++yiMT7hopNhqey+EsugRmzYD7s/g4FFdcVmjEolE3v9Vw731AADOyfkOEf+/GC8i4wWYnSb/tsI4Sznhu/h3gcU4o8EfSp7lfj/hDwXUk98qtjyrGFEk/2PBM/mfUYwmYnlWoEjwx4Jv8e3FiXQIZ/WWf9dHQthHxRafl0F/x+DbfJa8x8VPSADAWY5wAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADiHcAIAOIdwAgA4h3ACADjH2XpO0WjUqkLo6TzPpsprCNVGrVtwqxJuGP2xbTLI4+cUP/DKN3b1wkwIFVVlWTnWouj06G1aHJthHAcRixpcUjiVcNM2L1zA1YKDKLDOmRMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOc6WzFD0vSUgxuKe8J5FSYPRRGzHFkKfbGpUBHGL/DPatL6Pf/CHt2+CL59iJ/j9bsv3wygrkv84i4uLA+zJSZ5n9wa2KZNytuDMCQDgHMIJAOAcwgkA4BzCCQDgHMIJAOAcwgkA4BzCCQDgHMIJAOCcnMPpV7/6lT73uc9p8uTJmjhxoi677DLt3r0787gxRg899JCmTZumiRMnqrm5Wfv37w+00wCA8S2ncPrf//1fzZ07V8XFxXr22Wf15ptv6u///u917rnnZp7z9a9/XY8++qgef/xx7dy5Ux/72Mc0b948HT9+PPDOAwDGp5zu7/J3f/d3qqmp0bp16zLr6urqMv82xmj16tX6yle+optvvlmS9O1vf1uVlZXasmWLPvvZzwbUbQDAeJbTmdMzzzyj2bNn67bbbtPUqVN15ZVX6sknn8w8fuDAAfX19am5uTmzLh6Pq7GxUV1dXcH1GgAwruUUTu+8847Wrl2rGTNmaNu2bVq8eLG++MUv6umnn5Yk9fX1SZIqKyuztqusrMw8drpUKqVkMpm1AADObjl9ref7vmbPnq1HHnlEknTllVdq7969evzxx7Vo0aK8OtDe3q6HH344r20BAONTTmdO06ZN08UXX5y1bubMmTp48KAkqaqqSpLU39+f9Zz+/v7MY6dra2tTIpHILL29vbl0CQAwDuV05jR37lz19PRkrXvrrbc0ffp0SScnR1RVVamjo0NXXHGFJCmZTGrnzp1avHjxiG3GYjHFYrERHvHfW4LhWZRP8SIh1MyxrOcSQvkkK57NDh61TbvL8EKpmRPGoWB1mIcwRsv9HsaxEInm36bNtqOyPraC71MYNdXGUk7htGzZMl177bV65JFH9Cd/8ifatWuXnnjiCT3xxBOSTh6US5cu1de+9jXNmDFDdXV1evDBB1VdXa1bbrkljP4DAMahnMLp6quv1ubNm9XW1qa/+Zu/UV1dnVavXq2FCxdmnvOlL31Jx44d0z333KOBgQFdd911eu655zRhwoTAOw8AGJ8849i5YDKZVDwe1+v7XlNZWVlg7fp+/uW10/5wYP04xXa3G/8sKPPs2X2ta0zwr1vaPxF4m3Zf6wUvErErbx/G13pG+e/3MMq0y7hXpt2lj/Kjg0fVMKtRiURC5eXlebXBvfUAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAziGcAADOIZwAAM4hnAAAzrEreRki309bVa8NkucFX2HSWJY/DaXmpcn/bxXPC/7vHE921UZ9L4TjJ4Rx2hRFDaP6aSRiV6U1ErV73UbiW7xf/BDeLZ71fg+hTw4Vxw7iM5MzJwCAcwgnAIBzCCcAgHMIJwCAcwgnAIBzCCcAgHMIJwCAcwgnAIBzCCcAgHMIJwCAcwgnAIBzCCcAgHMIJwCAcwgnAIBznC2ZETgv/1vue3LoXvTvCaNUgvEt9lEIu8i2dIMJ5XULoTSIRXmBMI4Dz7MreRENoWSGLMrnhLKPZFfyxnYfj9ymO59TXsT+fcKZEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5hBMAwDmEEwDAOYQTAMA5OYXTBRdcIM/zzlhaW1slScePH1dra6smT56s0tJStbS0qL+/P5SOAwDGr5zC6eWXX9bhw4czy/bt2yVJt912myRp2bJl2rp1qzZt2qTOzk4dOnRICxYsCL7XAIBxLafbF02ZMiXr55UrV+oTn/iEPv3pTyuRSOipp57Shg0bdP3110uS1q1bp5kzZ2rHjh2aM2dOcL0GAIxref+f09DQkL7zne/orrvukud56u7u1vDwsJqbmzPPqa+vV21trbq6ugLpLADg7JD3jV+3bNmigYEB3XnnnZKkvr4+lZSUqKKiIut5lZWV6uvrG7WdVCqlVCqV+TmZTObbJQDAOJH3mdNTTz2l+fPnq7q62qoD7e3tisfjmaWmpsaqPQBA4cvrzOmXv/ylfvKTn+gHP/hBZl1VVZWGhoY0MDCQdfbU39+vqqqqUdtqa2vT8uXLMz8nEgnV1tbq6NGj+XRtdFZlCfK/Xf9o/LRdm+l0GCUz8r/lvucFf1WCbcmMtE4E1JPfCuNYsCnp4Bu70g0jKS4attq+qDj4chC+P5T3tmGUzIgYy+N9nJfMOPX5bbXvTR5WrFhhqqqqzPDwcGbdwMCAKS4uNt///vcz6/bt22ckma6uro/cdm9vr5HEwsLCwlLgS29vbz4RY4wxxjMmt2jzfV91dXW64447tHLlyqzHFi9erB//+Mdav369ysvLtWTJEknSz372s5zaP3TokMrKyjQ4OKiamhr19vaqvLw8l246KZlMMh6HMR63MR63vX88pz6/q6urFcmz8GDOX+v95Cc/0cGDB3XXXXed8diqVasUiUTU0tKiVCqlefPmac2aNTm1H4lEdP7550v67WlqeXn5uHjxTmE8bmM8bmM8bjs1nng8btVOzuH0mc98ZtTvESdMmKDHHntMjz32mFWnAABnN+6tBwBwjtPhFIvFtGLFCsVisbHuSiAYj9sYj9sYj9uCHk/OEyIAAAib02dOAICzE+EEAHAO4QQAcA7hBABwjrPh9Nhjj+mCCy7QhAkT1NjYqF27do11lz6yl156STfddJOqq6vleZ62bNmS9bgxRg899JCmTZumiRMnqrm5Wfv37x+bzn6I9vZ2XX311SorK9PUqVN1yy23qKenJ+s5hVQBee3atZo1a1bmQsGmpiY9++yzmccLaSwjWblypTzP09KlSzPrCm1MX/3qV8+otl1fX595vNDG86tf/Uqf+9znNHnyZE2cOFGXXXaZdu/enXm8kD4PpP+PFdHzvvFRiDZu3GhKSkrMP//zP5s33njD/Nmf/ZmpqKgw/f39Y921j+THP/6x+eu//mvzgx/8wEgymzdvznp85cqVJh6Pmy1btpif//zn5o/+6I9MXV2d+c1vfjM2Hf4A8+bNM+vWrTN79+41e/bsMX/4h39oamtrzdGjRzPPuffee01NTY3p6Ogwu3fvNnPmzDHXXnvtGPZ6dM8884z5t3/7N/PWW2+Znp4e81d/9VemuLjY7N271xhTWGM53a5du8wFF1xgZs2aZe6///7M+kIb04oVK8wll1xiDh8+nFnefffdzOOFNJ7/+Z//MdOnTzd33nmn2blzp3nnnXfMtm3bzNtvv515TiF9HhhjzJEjR7Jem+3btxtJ5oUXXjDGBPf6OBlO11xzjWltbc38nE6nTXV1tWlvbx/DXuXn9HDyfd9UVVWZb3zjG5l1AwMDJhaLmX/5l38Zgx7m5siRI0aS6ezsNMb89oa/mzZtyjznP//zP42U2w1/x9K5555r/umf/qmgxzI4OGhmzJhhtm/fbj796U9nwqkQx7RixQpz+eWXj/hYoY3ngQceMNddd92ojxf654Exxtx///3mE5/4hPF9P9DXx7mv9YaGhtTd3Z1VUTcSiai5uXlcVNQ9cOCA+vr6ssYXj8fV2NhYEONLJBKSpEmTJklSQVdATqfT2rhxo44dO6ampqaCHktra6tuvPHGrL5Lhfv67N+/X9XV1fr4xz+uhQsX6uDBg5IKbzzPPPOMZs+erdtuu01Tp07VlVdeqSeffDLzeKF/HoRZEd25cPr1r3+tdDqtysrKrPUfVlG3UJwaQyGOz/d9LV26VHPnztWll14qKf8KyGPp9ddfV2lpqWKxmO69915t3rxZF198cUGORZI2btyoV155Re3t7Wc8Vohjamxs1Pr16/Xcc89p7dq1OnDggD71qU9pcHCw4MbzzjvvaO3atZoxY4a2bdumxYsX64tf/KKefvppSYX9eSAFVxF9JHmXacfZp7W1VXv37tVPf/rTse6KlYsuukh79uxRIpHQ97//fS1atEidnZ1j3a289Pb26v7779f27ds1YcKEse5OIObPn5/596xZs9TY2Kjp06fre9/7niZOnDiGPcud7/uaPXu2HnnkEUnSlVdeqb179+rxxx/XokWLxrh39oKqiD4S586czjvvPEWj0TNmd3xYRd1CcWoMhTa+++67Tz/60Y/0wgsvZEqaSNkVkN/P5fGUlJTok5/8pBoaGtTe3q7LL79c3/rWtwpyLN3d3Tpy5IiuuuoqFRUVqaioSJ2dnXr00UdVVFSkysrKghvT6SoqKnThhRfq7bffLrjXaNq0abr44ouz1s2cOTPzNWWhfh5Iv62I/qd/+qeZdUG+Ps6FU0lJiRoaGtTR0ZFZ5/u+Ojo61NTUNIY9C0ZdXZ2qqqqyxpdMJrVz504nx2eM0X333afNmzfr+eefV11dXdbjDQ0NKi4uzhpPT0+PDh486OR4RuL7vlKpVEGO5YYbbtDrr7+uPXv2ZJbZs2dr4cKFmX8X2phOd/ToUf3iF7/QtGnTCu41mjt37hmXXrz11luaPn26pML7PHi/devWaerUqbrxxhsz6wJ9fQKeuBGIjRs3mlgsZtavX2/efPNNc88995iKigrT19c31l37SAYHB82rr75qXn31VSPJfPOb3zSvvvqq+eUvf2mMOTl1tKKiwvzwhz80r732mrn55pudnTq6ePFiE4/HzYsvvpg1ffT//u//Ms+59957TW1trXn++efN7t27TVNTk2lqahrDXo/uy1/+suns7DQHDhwwr732mvnyl79sPM8z//7v/26MKayxjOb9s/WMKbwx/cVf/IV58cUXzYEDB8x//Md/mObmZnPeeeeZI0eOGGMKazy7du0yRUVF5m//9m/N/v37zXe/+11zzjnnmO985zuZ5xTS58Ep6XTa1NbWmgceeOCMx4J6fZwMJ2OM+Yd/+AdTW1trSkpKzDXXXGN27Ngx1l36yF544QUj6Yxl0aJFxpiT00cffPBBU1lZaWKxmLnhhhtMT0/P2HZ6FCONQ5JZt25d5jm/+c1vzJ//+Z+bc88915xzzjnmj//4j83hw4fHrtMf4K677jLTp083JSUlZsqUKeaGG27IBJMxhTWW0ZweToU2pttvv91MmzbNlJSUmN/5nd8xt99+e9Z1QYU2nq1bt5pLL73UxGIxU19fb5544omsxwvp8+CUbdu2GUkj9jOo14eSGQAA5zj3f04AABBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOcQTgAA5xBOAADnEE4AAOf8P/uOP6ie8bJ2AAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "for _ in range(10):\n",
+    "    img, label = train_generator.next()\n",
+    "    if (label[0][1]==1):\n",
+    "        plt.imshow(img[0])\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_model=tf.keras.applications.Xception(\n",
+    "    include_top=False,\n",
+    "    weights=\"imagenet\",\n",
+    "    input_tensor=None,\n",
+    "    input_shape=(71, 71, 3),\n",
+    "    pooling=None,\n",
+    "    classes=6,\n",
+    "    classifier_activation=\"softmax\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for layer in base_model.layers:\n",
+    "    layer.trainable = False"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Xception_learn=models.Sequential([\n",
+    "    base_model,\n",
+    "    layers.GlobalAveragePooling2D(),\n",
+    "    layers.Dense(256, activation='relu'),\n",
+    "    layers.Dropout(0.2),\n",
+    "    layers.Dense(6, activation='softmax')\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " xception (Functional)       (None, 3, 3, 2048)        20861480  \n",
+      "                                                                 \n",
+      " global_average_pooling2d (G  (None, 2048)             0         \n",
+      " lobalAveragePooling2D)                                          \n",
+      "                                                                 \n",
+      " dense (Dense)               (None, 256)               524544    \n",
+      "                                                                 \n",
+      " dropout (Dropout)           (None, 256)               0         \n",
+      "                                                                 \n",
+      " dense_1 (Dense)             (None, 6)                 1542      \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 21,387,566\n",
+      "Trainable params: 526,086\n",
+      "Non-trainable params: 20,861,480\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "Xception_learn.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "METRICS = [\n",
+    "      keras.metrics.Precision(name='precision'),\n",
+    "      keras.metrics.Recall(name='recall'),\n",
+    "      keras.metrics.AUC(name='auc'),\n",
+    "      keras.metrics.AUC(name='prc', curve='PR'), # precision-recall curve\n",
+    "]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\arpit\\anaconda3\\envs\\tf\\lib\\site-packages\\keras\\optimizers\\optimizer_v2\\adam.py:114: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.\n",
+      "  super().__init__(name, **kwargs)\n"
+     ]
+    }
+   ],
+   "source": [
+    "Xception_learn.compile(\n",
+    "    optimizer=Adam(lr=0.0001),\n",
+    "    loss='categorical_crossentropy',\n",
+    "    metrics=['accuracy', METRICS],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/100\n",
+      "28/28 [==============================] - 5s 32ms/step - loss: 1.3770 - accuracy: 0.4807 - precision: 0.7460 - recall: 0.1052 - auc: 0.7966 - prc: 0.4687\n",
+      "Epoch 2/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.8986 - accuracy: 0.7719 - precision: 0.8542 - recall: 0.3965 - auc: 0.9215 - prc: 0.7451\n",
+      "Epoch 3/100\n",
+      "28/28 [==============================] - 1s 30ms/step - loss: 0.7409 - accuracy: 0.8174 - precision: 0.8755 - recall: 0.5040 - auc: 0.9430 - prc: 0.8105\n",
+      "Epoch 4/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.6662 - accuracy: 0.8311 - precision: 0.8888 - recall: 0.5592 - auc: 0.9529 - prc: 0.8433\n",
+      "Epoch 5/100\n",
+      "28/28 [==============================] - 1s 30ms/step - loss: 0.5953 - accuracy: 0.8555 - precision: 0.8976 - recall: 0.6035 - auc: 0.9624 - prc: 0.8700\n",
+      "Epoch 6/100\n",
+      "28/28 [==============================] - 1s 30ms/step - loss: 0.5561 - accuracy: 0.8686 - precision: 0.9002 - recall: 0.6257 - auc: 0.9669 - prc: 0.8857\n",
+      "Epoch 7/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.5271 - accuracy: 0.8686 - precision: 0.9006 - recall: 0.6439 - auc: 0.9698 - prc: 0.8939\n",
+      "Epoch 8/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.4980 - accuracy: 0.8760 - precision: 0.9141 - recall: 0.6718 - auc: 0.9718 - prc: 0.9019\n",
+      "Epoch 9/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.4701 - accuracy: 0.8771 - precision: 0.9135 - recall: 0.6786 - auc: 0.9750 - prc: 0.9115\n",
+      "Epoch 10/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.4507 - accuracy: 0.8845 - precision: 0.9196 - recall: 0.7025 - auc: 0.9777 - prc: 0.9185\n",
+      "Epoch 11/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.4202 - accuracy: 0.8976 - precision: 0.9227 - recall: 0.7201 - auc: 0.9809 - prc: 0.9288\n",
+      "Epoch 12/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.4082 - accuracy: 0.8948 - precision: 0.9260 - recall: 0.7332 - auc: 0.9815 - prc: 0.9333\n",
+      "Epoch 13/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.4012 - accuracy: 0.8993 - precision: 0.9223 - recall: 0.7361 - auc: 0.9816 - prc: 0.9328\n",
+      "Epoch 14/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.3824 - accuracy: 0.9078 - precision: 0.9328 - recall: 0.7503 - auc: 0.9836 - prc: 0.9396\n",
+      "Epoch 15/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.3751 - accuracy: 0.9061 - precision: 0.9312 - recall: 0.7628 - auc: 0.9842 - prc: 0.9419\n",
+      "Epoch 16/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.3595 - accuracy: 0.9061 - precision: 0.9304 - recall: 0.7605 - auc: 0.9856 - prc: 0.9450\n",
+      "Epoch 17/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.3295 - accuracy: 0.9187 - precision: 0.9444 - recall: 0.7821 - auc: 0.9881 - prc: 0.9551\n",
+      "Epoch 18/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.3307 - accuracy: 0.9158 - precision: 0.9413 - recall: 0.7935 - auc: 0.9881 - prc: 0.9549\n",
+      "Epoch 19/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.3116 - accuracy: 0.9238 - precision: 0.9490 - recall: 0.8049 - auc: 0.9895 - prc: 0.9597\n",
+      "Epoch 20/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.3108 - accuracy: 0.9209 - precision: 0.9410 - recall: 0.8072 - auc: 0.9895 - prc: 0.9601\n",
+      "Epoch 21/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.2895 - accuracy: 0.9323 - precision: 0.9528 - recall: 0.8265 - auc: 0.9907 - prc: 0.9648\n",
+      "Epoch 22/100\n",
+      "28/28 [==============================] - 1s 30ms/step - loss: 0.2849 - accuracy: 0.9323 - precision: 0.9513 - recall: 0.8231 - auc: 0.9910 - prc: 0.9661\n",
+      "Epoch 23/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.2740 - accuracy: 0.9334 - precision: 0.9569 - recall: 0.8453 - auc: 0.9916 - prc: 0.9683\n",
+      "Epoch 24/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.2671 - accuracy: 0.9300 - precision: 0.9493 - recall: 0.8419 - auc: 0.9924 - prc: 0.9707\n",
+      "Epoch 25/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.2585 - accuracy: 0.9352 - precision: 0.9541 - recall: 0.8515 - auc: 0.9924 - prc: 0.9710\n",
+      "Epoch 26/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.2568 - accuracy: 0.9397 - precision: 0.9568 - recall: 0.8561 - auc: 0.9927 - prc: 0.9718\n",
+      "Epoch 27/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.2492 - accuracy: 0.9363 - precision: 0.9537 - recall: 0.8561 - auc: 0.9928 - prc: 0.9723\n",
+      "Epoch 28/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.2450 - accuracy: 0.9363 - precision: 0.9509 - recall: 0.8589 - auc: 0.9931 - prc: 0.9726\n",
+      "Epoch 29/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.2375 - accuracy: 0.9460 - precision: 0.9621 - recall: 0.8805 - auc: 0.9938 - prc: 0.9765\n",
+      "Epoch 30/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.2267 - accuracy: 0.9437 - precision: 0.9613 - recall: 0.8760 - auc: 0.9948 - prc: 0.9791\n",
+      "Epoch 31/100\n",
+      "28/28 [==============================] - 1s 35ms/step - loss: 0.2257 - accuracy: 0.9448 - precision: 0.9604 - recall: 0.8834 - auc: 0.9943 - prc: 0.9780\n",
+      "Epoch 32/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.2149 - accuracy: 0.9482 - precision: 0.9641 - recall: 0.8862 - auc: 0.9949 - prc: 0.9810\n",
+      "Epoch 33/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.2098 - accuracy: 0.9471 - precision: 0.9631 - recall: 0.8896 - auc: 0.9956 - prc: 0.9828\n",
+      "Epoch 34/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.2149 - accuracy: 0.9408 - precision: 0.9577 - recall: 0.8885 - auc: 0.9949 - prc: 0.9801\n",
+      "Epoch 35/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.2047 - accuracy: 0.9528 - precision: 0.9629 - recall: 0.9005 - auc: 0.9950 - prc: 0.9813\n",
+      "Epoch 36/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.2031 - accuracy: 0.9488 - precision: 0.9604 - recall: 0.8970 - auc: 0.9950 - prc: 0.9813\n",
+      "Epoch 37/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.1946 - accuracy: 0.9511 - precision: 0.9678 - recall: 0.9061 - auc: 0.9957 - prc: 0.9834\n",
+      "Epoch 38/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1885 - accuracy: 0.9585 - precision: 0.9710 - recall: 0.9130 - auc: 0.9961 - prc: 0.9855\n",
+      "Epoch 39/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1825 - accuracy: 0.9551 - precision: 0.9691 - recall: 0.9090 - auc: 0.9959 - prc: 0.9852\n",
+      "Epoch 40/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1781 - accuracy: 0.9613 - precision: 0.9705 - recall: 0.9158 - auc: 0.9963 - prc: 0.9863\n",
+      "Epoch 41/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.1755 - accuracy: 0.9625 - precision: 0.9712 - recall: 0.9198 - auc: 0.9963 - prc: 0.9863\n",
+      "Epoch 42/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1710 - accuracy: 0.9602 - precision: 0.9689 - recall: 0.9209 - auc: 0.9966 - prc: 0.9868\n",
+      "Epoch 43/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1658 - accuracy: 0.9630 - precision: 0.9721 - recall: 0.9323 - auc: 0.9969 - prc: 0.9884\n",
+      "Epoch 44/100\n",
+      "28/28 [==============================] - 1s 34ms/step - loss: 0.1634 - accuracy: 0.9653 - precision: 0.9738 - recall: 0.9289 - auc: 0.9968 - prc: 0.9880\n",
+      "Epoch 45/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1634 - accuracy: 0.9653 - precision: 0.9727 - recall: 0.9323 - auc: 0.9967 - prc: 0.9881\n",
+      "Epoch 46/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.1557 - accuracy: 0.9681 - precision: 0.9763 - recall: 0.9369 - auc: 0.9967 - prc: 0.9881\n",
+      "Epoch 47/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1617 - accuracy: 0.9625 - precision: 0.9710 - recall: 0.9323 - auc: 0.9970 - prc: 0.9886\n",
+      "Epoch 48/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1521 - accuracy: 0.9693 - precision: 0.9747 - recall: 0.9414 - auc: 0.9972 - prc: 0.9896\n",
+      "Epoch 49/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.1421 - accuracy: 0.9721 - precision: 0.9781 - recall: 0.9414 - auc: 0.9973 - prc: 0.9904\n",
+      "Epoch 50/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.1420 - accuracy: 0.9687 - precision: 0.9747 - recall: 0.9437 - auc: 0.9977 - prc: 0.9908\n",
+      "Epoch 51/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1424 - accuracy: 0.9699 - precision: 0.9781 - recall: 0.9420 - auc: 0.9974 - prc: 0.9905\n",
+      "Epoch 52/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1430 - accuracy: 0.9693 - precision: 0.9771 - recall: 0.9448 - auc: 0.9973 - prc: 0.9901\n",
+      "Epoch 53/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1360 - accuracy: 0.9693 - precision: 0.9805 - recall: 0.9443 - auc: 0.9976 - prc: 0.9914\n",
+      "Epoch 54/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1335 - accuracy: 0.9716 - precision: 0.9806 - recall: 0.9499 - auc: 0.9976 - prc: 0.9914\n",
+      "Epoch 55/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1349 - accuracy: 0.9687 - precision: 0.9754 - recall: 0.9477 - auc: 0.9976 - prc: 0.9911\n",
+      "Epoch 56/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1284 - accuracy: 0.9738 - precision: 0.9818 - recall: 0.9499 - auc: 0.9977 - prc: 0.9918\n",
+      "Epoch 57/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1248 - accuracy: 0.9733 - precision: 0.9818 - recall: 0.9534 - auc: 0.9980 - prc: 0.9927\n",
+      "Epoch 58/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1202 - accuracy: 0.9772 - precision: 0.9860 - recall: 0.9613 - auc: 0.9980 - prc: 0.9932\n",
+      "Epoch 59/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1196 - accuracy: 0.9761 - precision: 0.9825 - recall: 0.9568 - auc: 0.9983 - prc: 0.9938\n",
+      "Epoch 60/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1168 - accuracy: 0.9750 - precision: 0.9825 - recall: 0.9579 - auc: 0.9979 - prc: 0.9926\n",
+      "Epoch 61/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1205 - accuracy: 0.9761 - precision: 0.9831 - recall: 0.9608 - auc: 0.9982 - prc: 0.9927\n",
+      "Epoch 62/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1131 - accuracy: 0.9790 - precision: 0.9878 - recall: 0.9659 - auc: 0.9981 - prc: 0.9937\n",
+      "Epoch 63/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1133 - accuracy: 0.9744 - precision: 0.9802 - recall: 0.9596 - auc: 0.9984 - prc: 0.9943\n",
+      "Epoch 64/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1140 - accuracy: 0.9761 - precision: 0.9826 - recall: 0.9613 - auc: 0.9981 - prc: 0.9931\n",
+      "Epoch 65/100\n",
+      "28/28 [==============================] - 1s 34ms/step - loss: 0.1144 - accuracy: 0.9733 - precision: 0.9808 - recall: 0.9568 - auc: 0.9979 - prc: 0.9926\n",
+      "Epoch 66/100\n",
+      "28/28 [==============================] - 1s 35ms/step - loss: 0.1048 - accuracy: 0.9818 - precision: 0.9855 - recall: 0.9681 - auc: 0.9982 - prc: 0.9940\n",
+      "Epoch 67/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.1090 - accuracy: 0.9790 - precision: 0.9832 - recall: 0.9653 - auc: 0.9983 - prc: 0.9933\n",
+      "Epoch 68/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.1003 - accuracy: 0.9812 - precision: 0.9844 - recall: 0.9664 - auc: 0.9983 - prc: 0.9942\n",
+      "Epoch 69/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.1016 - accuracy: 0.9812 - precision: 0.9855 - recall: 0.9687 - auc: 0.9982 - prc: 0.9939\n",
+      "Epoch 70/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.1008 - accuracy: 0.9824 - precision: 0.9856 - recall: 0.9727 - auc: 0.9987 - prc: 0.9951\n",
+      "Epoch 71/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.0995 - accuracy: 0.9824 - precision: 0.9850 - recall: 0.9704 - auc: 0.9986 - prc: 0.9951\n",
+      "Epoch 72/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.0971 - accuracy: 0.9829 - precision: 0.9873 - recall: 0.9693 - auc: 0.9986 - prc: 0.9954\n",
+      "Epoch 73/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.0935 - accuracy: 0.9818 - precision: 0.9867 - recall: 0.9721 - auc: 0.9987 - prc: 0.9957\n",
+      "Epoch 74/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.0969 - accuracy: 0.9807 - precision: 0.9867 - recall: 0.9693 - auc: 0.9989 - prc: 0.9957\n",
+      "Epoch 75/100\n",
+      "28/28 [==============================] - 1s 31ms/step - loss: 0.0955 - accuracy: 0.9812 - precision: 0.9850 - recall: 0.9704 - auc: 0.9986 - prc: 0.9952\n",
+      "Epoch 76/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.0917 - accuracy: 0.9829 - precision: 0.9868 - recall: 0.9750 - auc: 0.9986 - prc: 0.9954\n",
+      "Epoch 77/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0906 - accuracy: 0.9829 - precision: 0.9862 - recall: 0.9721 - auc: 0.9987 - prc: 0.9957\n",
+      "Epoch 78/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0872 - accuracy: 0.9846 - precision: 0.9885 - recall: 0.9772 - auc: 0.9989 - prc: 0.9965\n",
+      "Epoch 79/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0886 - accuracy: 0.9863 - precision: 0.9902 - recall: 0.9790 - auc: 0.9987 - prc: 0.9955\n",
+      "Epoch 80/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0855 - accuracy: 0.9829 - precision: 0.9873 - recall: 0.9744 - auc: 0.9989 - prc: 0.9965\n",
+      "Epoch 81/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0844 - accuracy: 0.9863 - precision: 0.9908 - recall: 0.9801 - auc: 0.9989 - prc: 0.9968\n",
+      "Epoch 82/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0871 - accuracy: 0.9835 - precision: 0.9879 - recall: 0.9784 - auc: 0.9988 - prc: 0.9958\n",
+      "Epoch 83/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0827 - accuracy: 0.9858 - precision: 0.9885 - recall: 0.9790 - auc: 0.9989 - prc: 0.9963\n",
+      "Epoch 84/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0784 - accuracy: 0.9881 - precision: 0.9919 - recall: 0.9807 - auc: 0.9989 - prc: 0.9965\n",
+      "Epoch 85/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0780 - accuracy: 0.9869 - precision: 0.9897 - recall: 0.9801 - auc: 0.9990 - prc: 0.9971\n",
+      "Epoch 86/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0773 - accuracy: 0.9875 - precision: 0.9897 - recall: 0.9818 - auc: 0.9990 - prc: 0.9967\n",
+      "Epoch 87/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0782 - accuracy: 0.9852 - precision: 0.9880 - recall: 0.9807 - auc: 0.9990 - prc: 0.9968\n",
+      "Epoch 88/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0761 - accuracy: 0.9881 - precision: 0.9903 - recall: 0.9841 - auc: 0.9990 - prc: 0.9969\n",
+      "Epoch 89/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0771 - accuracy: 0.9869 - precision: 0.9902 - recall: 0.9807 - auc: 0.9990 - prc: 0.9969\n",
+      "Epoch 90/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0744 - accuracy: 0.9869 - precision: 0.9903 - recall: 0.9829 - auc: 0.9989 - prc: 0.9961\n",
+      "Epoch 91/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0712 - accuracy: 0.9869 - precision: 0.9891 - recall: 0.9841 - auc: 0.9994 - prc: 0.9975\n",
+      "Epoch 92/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0754 - accuracy: 0.9886 - precision: 0.9908 - recall: 0.9841 - auc: 0.9990 - prc: 0.9966\n",
+      "Epoch 93/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0700 - accuracy: 0.9881 - precision: 0.9908 - recall: 0.9852 - auc: 0.9991 - prc: 0.9972\n",
+      "Epoch 94/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0685 - accuracy: 0.9881 - precision: 0.9909 - recall: 0.9858 - auc: 0.9991 - prc: 0.9971\n",
+      "Epoch 95/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0679 - accuracy: 0.9875 - precision: 0.9897 - recall: 0.9852 - auc: 0.9992 - prc: 0.9976\n",
+      "Epoch 96/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0679 - accuracy: 0.9881 - precision: 0.9908 - recall: 0.9852 - auc: 0.9992 - prc: 0.9977\n",
+      "Epoch 97/100\n",
+      "28/28 [==============================] - 1s 32ms/step - loss: 0.0670 - accuracy: 0.9886 - precision: 0.9914 - recall: 0.9852 - auc: 0.9992 - prc: 0.9978\n",
+      "Epoch 98/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0674 - accuracy: 0.9858 - precision: 0.9886 - recall: 0.9841 - auc: 0.9992 - prc: 0.9976\n",
+      "Epoch 99/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0658 - accuracy: 0.9881 - precision: 0.9908 - recall: 0.9841 - auc: 0.9992 - prc: 0.9976\n",
+      "Epoch 100/100\n",
+      "28/28 [==============================] - 1s 33ms/step - loss: 0.0673 - accuracy: 0.9869 - precision: 0.9891 - recall: 0.9841 - auc: 0.9994 - prc: 0.9976\n"
+     ]
+    }
+   ],
+   "source": [
+    "Xception_history=Xception_learn.fit(train_generator,epochs=100,class_weight=class_weight_dict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\"df=pd.DataFrame(Xception_history.history)\n",
+    "df.to_csv(\"Xception_plots.csv\",index=False)\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1600x800 with 6 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot training history for multiple metrics\n",
+    "plt.figure(figsize=(16, 8))\n",
+    "\n",
+    "# Plot training & validation accuracy values\n",
+    "plt.subplot(2, 3, 1)\n",
+    "plt.plot(Xception_history.history['accuracy'])\n",
+    "plt.title('Model Accuracy')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation loss values\n",
+    "plt.subplot(2, 3, 2)\n",
+    "plt.plot(Xception_history.history['loss'])\n",
+    "plt.title('Model Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation precision values\n",
+    "plt.subplot(2, 3, 3)\n",
+    "plt.plot(Xception_history.history['precision'])\n",
+    "plt.title('Model Precision')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Precision')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation recall values\n",
+    "plt.subplot(2, 3, 4)\n",
+    "plt.plot(Xception_history.history['recall'])\n",
+    "plt.title('Model Recall')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Recall')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation AUC values\n",
+    "plt.subplot(2, 3, 5)\n",
+    "plt.plot(Xception_history.history['auc'])\n",
+    "plt.title('Model AUC')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('AUC')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "# Plot training & validation PRC values\n",
+    "plt.subplot(2, 3, 6)\n",
+    "plt.plot(Xception_history.history['prc'])\n",
+    "plt.title('Model PRC')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('PRC')\n",
+    "plt.legend(['Train'], loc='upper left')\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "tf",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.17"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/High Throughput Algae Cell Detection/Model/YOLOv8n.ipynb b/High Throughput Algae Cell Detection/Model/YOLOv8n.ipynb
new file mode 100644
index 000000000..c65778846
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/YOLOv8n.ipynb	
@@ -0,0 +1,911 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')\n",
+    "import glob\n",
+    "import random\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "\n",
+    "sns.set_theme(style=\"darkgrid\", rc={\"axes.unicode_minus\":False})\n",
+    "\n",
+    "import torch\n",
+    "\n",
+    "from ultralytics import YOLO\n",
+    "\n",
+    "from PIL import Image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "seed = 1\n",
+    "random.seed(seed)\n",
+    "np.random.seed(seed)\n",
+    "torch.manual_seed(seed)\n",
+    "torch.cuda.manual_seed(seed)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## YOLOV8m is comparatively more complex and takes more time to run on CPU. Here I'm performing YOLOn model for demonstration purposes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ultralytics YOLOv8.1.2 🚀 Python-3.11.0 torch-2.1.0+cu121 CUDA:0 (NVIDIA GeForce RTX 3050 Ti Laptop GPU, 4096MiB)\n",
+      "\u001b[34m\u001b[1mengine\\trainer: \u001b[0mtask=detect, mode=train, model=D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Model\\yolov8n.pt, data=D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\data.yaml, epochs=25, time=None, patience=50, batch=4, imgsz=640, save=True, save_period=-1, cache=False, device=0, workers=8, project=None, name=train2, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=runs\\detect\\train2\n",
+      "WARNING:tensorflow:From c:\\Pytorchenv\\Torchenv\\Lib\\site-packages\\keras\\src\\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.\n",
+      "\n",
+      "Overriding model.yaml nc=80 with nc=6\n",
+      "\n",
+      "                   from  n    params  module                                       arguments                     \n",
+      "  0                  -1  1       464  ultralytics.nn.modules.conv.Conv             [3, 16, 3, 2]                 \n",
+      "  1                  -1  1      4672  ultralytics.nn.modules.conv.Conv             [16, 32, 3, 2]                \n",
+      "  2                  -1  1      7360  ultralytics.nn.modules.block.C2f             [32, 32, 1, True]             \n",
+      "  3                  -1  1     18560  ultralytics.nn.modules.conv.Conv             [32, 64, 3, 2]                \n",
+      "  4                  -1  2     49664  ultralytics.nn.modules.block.C2f             [64, 64, 2, True]             \n",
+      "  5                  -1  1     73984  ultralytics.nn.modules.conv.Conv             [64, 128, 3, 2]               \n",
+      "  6                  -1  2    197632  ultralytics.nn.modules.block.C2f             [128, 128, 2, True]           \n",
+      "  7                  -1  1    295424  ultralytics.nn.modules.conv.Conv             [128, 256, 3, 2]              \n",
+      "  8                  -1  1    460288  ultralytics.nn.modules.block.C2f             [256, 256, 1, True]           \n",
+      "  9                  -1  1    164608  ultralytics.nn.modules.block.SPPF            [256, 256, 5]                 \n",
+      " 10                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 11             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 12                  -1  1    148224  ultralytics.nn.modules.block.C2f             [384, 128, 1]                 \n",
+      " 13                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+      " 14             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 15                  -1  1     37248  ultralytics.nn.modules.block.C2f             [192, 64, 1]                  \n",
+      " 16                  -1  1     36992  ultralytics.nn.modules.conv.Conv             [64, 64, 3, 2]                \n",
+      " 17            [-1, 12]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 18                  -1  1    123648  ultralytics.nn.modules.block.C2f             [192, 128, 1]                 \n",
+      " 19                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]              \n",
+      " 20             [-1, 9]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+      " 21                  -1  1    493056  ultralytics.nn.modules.block.C2f             [384, 256, 1]                 \n",
+      " 22        [15, 18, 21]  1    752482  ultralytics.nn.modules.head.Detect           [6, [64, 128, 256]]           \n",
+      "Model summary: 225 layers, 3012018 parameters, 3012002 gradients, 8.2 GFLOPs\n",
+      "\n",
+      "Transferred 319/355 items from pretrained weights\n",
+      "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs\\detect\\train2', view at http://localhost:6006/\n",
+      "Freezing layer 'model.22.dfl.conv.weight'\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks with YOLOv8n...\n",
+      "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[34m\u001b[1mtrain: \u001b[0mScanning D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\train\\labels.cache... 700 images, 0 backgrounds, 0 corrupt: 100%|██████████| 700/700 [00:00<?, ?it/s]\n",
+      "\u001b[34m\u001b[1mval: \u001b[0mScanning D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\train\\labels.cache... 700 images, 0 backgrounds, 0 corrupt: 100%|██████████| 700/700 [00:00<?, ?it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Plotting labels to runs\\detect\\train2\\labels.jpg... \n",
+      "\u001b[34m\u001b[1moptimizer:\u001b[0m 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... \n",
+      "\u001b[34m\u001b[1moptimizer:\u001b[0m AdamW(lr=0.001, momentum=0.9) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias(decay=0.0)\n",
+      "25 epochs...\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "       1/25     0.856G      1.454      3.512     0.9272         14        640: 100%|██████████| 175/175 [00:12<00:00, 13.55it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:05<00:00, 17.41it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.435       0.63      0.557      0.376\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "       2/25     0.864G      1.297      2.128     0.9153         20        640: 100%|██████████| 175/175 [00:11<00:00, 15.67it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 19.77it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.658      0.737      0.729      0.488\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "       3/25     0.864G      1.274      1.835     0.9163         26        640: 100%|██████████| 175/175 [00:11<00:00, 15.80it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 19.85it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.777      0.779       0.84      0.567\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "       4/25     0.864G      1.219      1.576     0.9106         24        640: 100%|██████████| 175/175 [00:11<00:00, 15.55it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 19.87it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.806      0.796      0.861      0.585\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "       5/25     0.864G      1.195      1.411     0.9026         17        640: 100%|██████████| 175/175 [00:11<00:00, 15.63it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.38it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758       0.82      0.803      0.885      0.599\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "       6/25      0.86G      1.198      1.312     0.9015         17        640: 100%|██████████| 175/175 [00:11<00:00, 15.82it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.42it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758       0.87      0.855      0.917      0.638\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "       7/25      0.86G      1.166      1.197     0.8954         16        640: 100%|██████████| 175/175 [00:11<00:00, 15.58it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.51it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.814      0.844       0.91       0.64\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "       8/25     0.858G      1.151      1.117     0.8907         22        640: 100%|██████████| 175/175 [00:11<00:00, 15.62it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.17it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.822      0.871      0.911      0.648\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "       9/25     0.858G      1.163      1.058     0.8865         23        640: 100%|██████████| 175/175 [00:10<00:00, 15.95it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.67it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.883      0.872      0.928      0.657\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      10/25     0.858G      1.125      1.016     0.8883         17        640: 100%|██████████| 175/175 [00:11<00:00, 15.78it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 19.93it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.875      0.846       0.93      0.656\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      11/25     0.858G      1.149     0.9903     0.8971          8        640: 100%|██████████| 175/175 [00:11<00:00, 15.47it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 19.46it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.856      0.866      0.923      0.659\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      12/25     0.858G      1.117          1      0.882         14        640: 100%|██████████| 175/175 [00:11<00:00, 15.40it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.57it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.883      0.866      0.931      0.678\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      13/25     0.858G      1.091     0.9111     0.8778         22        640: 100%|██████████| 175/175 [00:11<00:00, 15.51it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.46it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.901       0.86      0.939      0.688\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      14/25     0.858G      1.109     0.9134     0.8771         21        640: 100%|██████████| 175/175 [00:11<00:00, 15.68it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.23it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.884       0.85      0.929      0.644\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      15/25     0.858G      1.098     0.8812     0.8834          8        640: 100%|██████████| 175/175 [00:11<00:00, 15.65it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.894      0.883      0.942      0.664\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Closing dataloader mosaic\n",
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      16/25     0.858G      1.107      0.976     0.8891         10        640: 100%|██████████| 175/175 [00:11<00:00, 15.37it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.26it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.923      0.884      0.947       0.68\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      17/25     0.858G      1.092     0.9368     0.8863         15        640: 100%|██████████| 175/175 [00:11<00:00, 15.76it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.50it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.864      0.874      0.933       0.65\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      18/25     0.858G      1.083     0.8857     0.8935         10        640: 100%|██████████| 175/175 [00:11<00:00, 15.73it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.18it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.891      0.893      0.947      0.686\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      19/25     0.858G      1.069     0.8262     0.8833         10        640: 100%|██████████| 175/175 [00:11<00:00, 15.65it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.49it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758       0.91        0.9       0.95      0.693\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      20/25     0.858G      1.079     0.8028     0.8829         16        640: 100%|██████████| 175/175 [00:11<00:00, 15.71it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.32it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.899      0.882      0.947      0.684\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      21/25     0.858G      1.066     0.8125     0.8872          8        640: 100%|██████████| 175/175 [00:11<00:00, 15.72it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.31it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.904      0.906      0.942      0.676\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      22/25     0.858G      1.056     0.7916     0.8819          6        640: 100%|██████████| 175/175 [00:10<00:00, 15.94it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.52it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.933      0.891      0.948      0.703\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      23/25     0.858G      1.046     0.7818     0.8748         13        640: 100%|██████████| 175/175 [00:11<00:00, 15.75it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.39it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.896      0.913      0.954      0.706\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      24/25     0.858G       1.02     0.7486     0.8699          6        640: 100%|██████████| 175/175 [00:11<00:00, 15.75it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.38it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758       0.93      0.908      0.954       0.71\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "      25/25     0.858G      1.038     0.7502     0.8708         11        640: 100%|██████████| 175/175 [00:11<00:00, 15.61it/s]\n",
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:04<00:00, 20.12it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758      0.935      0.906      0.956      0.711\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "25 epochs completed in 0.114 hours.\n",
+      "Optimizer stripped from runs\\detect\\train2\\weights\\last.pt, 6.2MB\n",
+      "Optimizer stripped from runs\\detect\\train2\\weights\\best.pt, 6.2MB\n",
+      "\n",
+      "Validating runs\\detect\\train2\\weights\\best.pt...\n",
+      "Ultralytics YOLOv8.1.2 🚀 Python-3.11.0 torch-2.1.0+cu121 CUDA:0 (NVIDIA GeForce RTX 3050 Ti Laptop GPU, 4096MiB)\n",
+      "Model summary (fused): 168 layers, 3006818 parameters, 0 gradients, 8.1 GFLOPs\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 88/88 [00:03<00:00, 23.12it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                   all        700       1758       0.93      0.907      0.956      0.711\n",
+      "            Platymonas        700        184      0.945      0.913      0.961      0.743\n",
+      "             Chlorella        700        722      0.872      0.716      0.854       0.44\n",
+      "     Dunaliella salina        700        234      0.903      0.918      0.963      0.692\n",
+      "             Effrenium        700        227      0.921      0.956      0.976      0.781\n",
+      "          Porphyridium        700        272      0.989      0.967      0.991      0.757\n",
+      "         Haematococcus        700        119      0.949      0.975      0.989       0.85\n",
+      "Speed: 0.1ms preprocess, 1.8ms inference, 0.0ms loss, 0.9ms postprocess per image\n",
+      "Results saved to \u001b[1mruns\\detect\\train2\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "model = YOLO(r\"D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Model\\yolov8n.pt\")\n",
+    "\n",
+    "data = r\"D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\data.yaml\"\n",
+    "results = model.train(\n",
+    "    data=data,\n",
+    "    epochs=25,\n",
+    "    device='0',\n",
+    "    batch=4,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "tf",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/High Throughput Algae Cell Detection/Model/results/ConvNeXtTiny_plot.csv b/High Throughput Algae Cell Detection/Model/results/ConvNeXtTiny_plot.csv
new file mode 100644
index 000000000..1949157c3
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/results/ConvNeXtTiny_plot.csv	
@@ -0,0 +1,101 @@
+loss,accuracy,precision,recall,auc,prc
+1.3942583799362183,0.4937428832054138,0.6587395668029785,0.3151308298110962,0.7885667085647583,0.5201273560523987
+0.6697201728820801,0.8179749846458435,0.8833445906639099,0.7451649308204651,0.9627014994621277,0.8799673318862915
+0.49029842019081116,0.8680318593978882,0.9030644297599792,0.8213879466056824,0.9752253293991089,0.9187780618667603
+0.42553871870040894,0.8879408240318298,0.9120678901672363,0.8555176258087158,0.9789171814918518,0.9293205738067627
+0.39471766352653503,0.8981797695159912,0.9138240814208984,0.8686006665229797,0.981457531452179,0.9381368160247803
+0.353733628988266,0.905005693435669,0.9184397459030151,0.8839590549468994,0.9837429523468018,0.9433581829071045
+0.3331870436668396,0.9163822531700134,0.9303985834121704,0.8896473050117493,0.9855303168296814,0.9481487274169922
+0.3098905682563782,0.916951060295105,0.9284037351608276,0.8998862504959106,0.9862349629402161,0.9507415294647217
+0.2808905839920044,0.9249146580696106,0.9347442388534546,0.9044368863105774,0.9891401529312134,0.9616978168487549
+0.28155556321144104,0.9186575412750244,0.9330199956893921,0.9032992124557495,0.9886100888252258,0.959484338760376
+0.2497548758983612,0.9317406415939331,0.9362319111824036,0.9186575412750244,0.990950882434845,0.9664196968078613
+0.2506907880306244,0.9271900057792664,0.938300371170044,0.916951060295105,0.9916189908981323,0.9678337574005127
+0.22989006340503693,0.9402730464935303,0.948225736618042,0.9271900057792664,0.992643415927887,0.9723751544952393
+0.22618818283081055,0.9328782558441162,0.9446709156036377,0.9226393699645996,0.9927043318748474,0.9719914197921753
+0.21800151467323303,0.939704179763794,0.9482558369636536,0.9277588129043579,0.9923192858695984,0.9706952571868896
+0.20747815072536469,0.9408418536186218,0.9463358521461487,0.9328782558441162,0.9935113191604614,0.9751814007759094
+0.20734333992004395,0.937428891658783,0.9439630508422852,0.9294652938842773,0.9937881231307983,0.9763277769088745
+0.20748981833457947,0.9402730464935303,0.9463667869567871,0.9334471225738525,0.9932700395584106,0.9736002683639526
+0.19143548607826233,0.9442548155784607,0.9519397616386414,0.935153603553772,0.9945933222770691,0.9788082242012024
+0.1769961565732956,0.9499431252479553,0.9571263194084167,0.939704179763794,0.9950023293495178,0.9804129004478455
+0.17897528409957886,0.9465301632881165,0.9506031274795532,0.9414107203483582,0.9940164685249329,0.9790631532669067
+0.16756419837474823,0.9505119323730469,0.9583333134651184,0.9419795274734497,0.9955140948295593,0.9833331108093262
+0.16364434361457825,0.9476677775382996,0.9587209224700928,0.9379976987838745,0.9957172274589539,0.9838131666183472
+0.16882658004760742,0.9465301632881165,0.9532332420349121,0.9391353726387024,0.9955578446388245,0.9824628829956055
+0.15178214013576508,0.9493743181228638,0.9550432562828064,0.9425483345985413,0.995286762714386,0.9829226136207581
+0.15579083561897278,0.9499431252479553,0.955594003200531,0.9425483345985413,0.9954832792282104,0.9832720756530762
+0.15311351418495178,0.9533560872077942,0.9579250812530518,0.9453924894332886,0.9957537055015564,0.9848613739013672
+0.13896550238132477,0.9556313753128052,0.9596773982048035,0.9476677775382996,0.995899498462677,0.9856350421905518
+0.1423618495464325,0.9544937610626221,0.9608069062232971,0.9482366442680359,0.9965716004371643,0.9853231310844421
+0.14877241849899292,0.9607508778572083,0.9644699096679688,0.9573378562927246,0.9960246086120605,0.9855639934539795
+0.14109361171722412,0.9584755301475525,0.9635627269744873,0.9476677775382996,0.9962719678878784,0.9864133596420288
+0.13371670246124268,0.9562002420425415,0.9620471596717834,0.9516496062278748,0.9957359433174133,0.9850848913192749
+0.1337222158908844,0.9596132040023804,0.9642857313156128,0.9522184133529663,0.996552586555481,0.9881551861763
+0.12541764974594116,0.9647326469421387,0.9671847820281982,0.9556313753128052,0.9964953660964966,0.9869700074195862
+0.1240358054637909,0.9630261659622192,0.9651029706001282,0.9596132040023804,0.99617999792099,0.98758864402771
+0.12621502578258514,0.9613196849822998,0.9677233695983887,0.9550625681877136,0.9972124695777893,0.9892480373382568
+0.11849718540906906,0.9653014540672302,0.9690189361572266,0.9607508778572083,0.9974278807640076,0.9901639223098755
+0.12281851470470428,0.9590443968772888,0.9615163803100586,0.9522184133529663,0.9968498349189758,0.988113522529602
+0.12264405190944672,0.9630261659622192,0.967797577381134,0.9573378562927246,0.9970694184303284,0.9887561202049255
+0.11180049926042557,0.9664391279220581,0.9701834917068481,0.9624573588371277,0.9975731372833252,0.990838885307312
+0.10078640282154083,0.9749715328216553,0.978210985660553,0.9704209566116333,0.9981859922409058,0.9923694133758545
+0.11049111187458038,0.9653014540672302,0.970588207244873,0.9573378562927246,0.9972842335700989,0.9897324442863464
+0.10339044779539108,0.9704209566116333,0.9730504751205444,0.9653014540672302,0.9977856278419495,0.9915480613708496
+0.1089555025100708,0.967576801776886,0.9697315692901611,0.9658703207969666,0.9971859455108643,0.9893217086791992
+0.10336574167013168,0.9715585708618164,0.9736389517784119,0.9664391279220581,0.9980313777923584,0.9917585849761963
+0.09870748966932297,0.9681456089019775,0.9735935926437378,0.9647326469421387,0.9977318644523621,0.9921488165855408
+0.09823784232139587,0.9692832827568054,0.972429633140564,0.9630261659622192,0.9971795678138733,0.990694522857666
+0.09548819810152054,0.9721274375915527,0.9753298759460449,0.9670079350471497,0.9979173541069031,0.9922537803649902
+0.0949258878827095,0.9715585708618164,0.9770641922950745,0.9692832827568054,0.9977142214775085,0.992358922958374
+0.09482529014348984,0.9726962447166443,0.9764232039451599,0.9658703207969666,0.998042106628418,0.9921389818191528
+0.09152963012456894,0.9766780138015747,0.9776760339736938,0.9715585708618164,0.9986726641654968,0.9943348169326782
+0.09344302862882614,0.9749715328216553,0.975428581237793,0.9709897637367249,0.9981762170791626,0.9933494329452515
+0.08973385393619537,0.969852089881897,0.9748139381408691,0.9687144756317139,0.9980113506317139,0.9926403760910034
+0.0874982699751854,0.9778156876564026,0.9799426794052124,0.9726962447166443,0.9984930753707886,0.9943183660507202
+0.08393929898738861,0.9761092066764832,0.9810453653335571,0.9715585708618164,0.9982644319534302,0.9942236542701721
+0.08262048661708832,0.977246880531311,0.978881299495697,0.9755403995513916,0.9983848929405212,0.994336724281311
+0.08208095282316208,0.9755403995513916,0.9793932437896729,0.9732650518417358,0.9980804324150085,0.9932053089141846
+0.07648372650146484,0.9755403995513916,0.9783228635787964,0.9755403995513916,0.9984478950500488,0.9950834512710571
+0.07722129672765732,0.979522168636322,0.9822756052017212,0.977246880531311,0.9983680248260498,0.9947298765182495
+0.08125697821378708,0.9755403995513916,0.9776887893676758,0.9721274375915527,0.9982940554618835,0.9946743249893188
+0.07599399983882904,0.9817975163459778,0.9839357137680054,0.9755403995513916,0.9983168840408325,0.9941132068634033
+0.07131173461675644,0.979522168636322,0.9816513657569885,0.9738339185714722,0.9991269707679749,0.9962496161460876
+0.07278816401958466,0.9783845543861389,0.9805380702018738,0.9744027256965637,0.9987047910690308,0.9953234791755676
+0.06941016018390656,0.9806598424911499,0.9817559719085693,0.979522168636322,0.9987846612930298,0.9957167506217957
+0.06376221030950546,0.9835039973258972,0.9851258397102356,0.979522168636322,0.9984447956085205,0.9958920478820801
+0.07381600141525269,0.977246880531311,0.9821736812591553,0.9715585708618164,0.9984621405601501,0.9951611757278442
+0.06688714772462845,0.9800910353660583,0.9822247624397278,0.9744027256965637,0.9989004731178284,0.9960941076278687
+0.06448492407798767,0.979522168636322,0.9828571677207947,0.9783845543861389,0.9991653561592102,0.9963357448577881
+0.06505831331014633,0.9817975163459778,0.9828864932060242,0.9800910353660583,0.9986417293548584,0.9958041310310364
+0.06624960154294968,0.9817975163459778,0.9834191203117371,0.9783845543861389,0.9989438056945801,0.9963352680206299
+0.06315187364816666,0.9800910353660583,0.9828473329544067,0.9778156876564026,0.999371349811554,0.9970996379852295
+0.06636320799589157,0.9812286496162415,0.9845449328422546,0.9783845543861389,0.9992210268974304,0.9965946674346924
+0.0665307492017746,0.9823663234710693,0.9845449328422546,0.9783845543861389,0.9989587068557739,0.9964061379432678
+0.06153884530067444,0.979522168636322,0.9806267619132996,0.9789533615112305,0.9991110563278198,0.9970529079437256
+0.06372620910406113,0.9812286496162415,0.9839816689491272,0.9783845543861389,0.999197781085968,0.996554970741272
+0.05985747277736664,0.979522168636322,0.9828669428825378,0.9789533615112305,0.9992223381996155,0.9966117143630981
+0.05903417617082596,0.9835039973258972,0.9846153855323792,0.9829351305961609,0.999108612537384,0.9970117211341858
+0.05808115005493164,0.9829351305961609,0.982876718044281,0.979522168636322,0.9990972876548767,0.9969843029975891
+0.05677972733974457,0.9852104783058167,0.9868496060371399,0.9817975163459778,0.9994135499000549,0.9974126815795898
+0.05644851550459862,0.9840728044509888,0.9868646264076233,0.9829351305961609,0.9993917346000671,0.9974344372749329
+0.059466660022735596,0.9835039973258972,0.985706090927124,0.9806598424911499,0.9987488389015198,0.9959186315536499
+0.05746515095233917,0.9852104783058167,0.9862935543060303,0.9823663234710693,0.9993742108345032,0.997226357460022
+0.052917249500751495,0.9869169592857361,0.9880205392837524,0.9852104783058167,0.9994082450866699,0.9973530173301697
+0.05229931324720383,0.9852104783058167,0.9891366362571716,0.9840728044509888,0.9995571970939636,0.9979367256164551
+0.052168309688568115,0.9857792854309082,0.9885779619216919,0.9846416115760803,0.999593198299408,0.9982014894485474
+0.05218290165066719,0.9823663234710693,0.982876718044281,0.979522168636322,0.9994428753852844,0.99753338098526
+0.05557442083954811,0.9817975163459778,0.982326090335846,0.9800910353660583,0.9995075464248657,0.9977473020553589
+0.051532045006752014,0.9835039973258972,0.9845802187919617,0.9806598424911499,0.9996336698532104,0.9982422590255737
+0.04963291063904762,0.9852104783058167,0.9857549667358398,0.9840728044509888,0.9996355772018433,0.9982765913009644
+0.04915642365813255,0.9874857664108276,0.9891552329063416,0.9857792854309082,0.999623715877533,0.9982589483261108
+0.04782269522547722,0.9863481521606445,0.9879931211471558,0.9829351305961609,0.9996870756149292,0.998512864112854
+0.04832166060805321,0.9857792854309082,0.9874429106712341,0.9840728044509888,0.9995641112327576,0.9980909824371338
+0.04604528099298477,0.9857792854309082,0.986340343952179,0.9857792854309082,0.9996117353439331,0.9981839656829834
+0.04651648923754692,0.9846416115760803,0.9885649085044861,0.9835039973258972,0.9995681047439575,0.9980481863021851
+0.04359951615333557,0.988054633140564,0.9897260069847107,0.9863481521606445,0.9997365474700928,0.9987494349479675
+0.045045409351587296,0.9852104783058167,0.9874213933944702,0.9823663234710693,0.9996474385261536,0.9983422756195068
+0.047463104128837585,0.9846416115760803,0.9868870973587036,0.9846416115760803,0.9995218515396118,0.9977399110794067
+0.047390248626470566,0.9869169592857361,0.9885910153388977,0.9857792854309082,0.9997038245201111,0.9985732436180115
+0.04124865308403969,0.9891922473907471,0.9908779859542847,0.9886234402656555,0.9997351765632629,0.9987437129020691
+0.044788263738155365,0.9874857664108276,0.9891552329063416,0.9857792854309082,0.9996287226676941,0.9982591271400452
diff --git a/High Throughput Algae Cell Detection/Model/results/InceptionV3_plot.csv b/High Throughput Algae Cell Detection/Model/results/InceptionV3_plot.csv
new file mode 100644
index 000000000..01afead5f
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/results/InceptionV3_plot.csv	
@@ -0,0 +1,101 @@
+loss,accuracy,precision,recall,auc,prc
+1.664758563041687,0.4186575710773468,0.6678966879844666,0.20591580867767334,0.7528169751167297,0.4533534348011017
+1.0190612077713013,0.6951080560684204,0.8599790930747986,0.46814560890197754,0.9260979890823364,0.7769625782966614
+0.8193126320838928,0.7554038763046265,0.8752052783966064,0.6063708662986755,0.9497746825218201,0.8430585265159607
+0.7210893630981445,0.7895335555076599,0.8832831382751465,0.6672354936599731,0.9597742557525635,0.8713758587837219
+0.6315101385116577,0.8225256204605103,0.8999290466308594,0.721274197101593,0.9700339436531067,0.901669442653656
+0.5847276449203491,0.839021623134613,0.9039666056632996,0.7389078736305237,0.97360759973526,0.9128838181495667
+0.5484592318534851,0.8441410660743713,0.9002677202224731,0.7650739550590515,0.9765422344207764,0.9202828407287598
+0.5016637444496155,0.8560864329338074,0.9198396801948547,0.7832764387130737,0.979736864566803,0.9320226907730103
+0.4691239297389984,0.871444821357727,0.9242228269577026,0.8117178678512573,0.9830114245414734,0.9415128231048584
+0.4409714937210083,0.8691695332527161,0.9257362484931946,0.8225256204605103,0.9847623705863953,0.947664201259613
+0.41937023401260376,0.8799772262573242,0.9303069114685059,0.8276450634002686,0.9856159090995789,0.9507944583892822
+0.39548107981681824,0.8930602669715881,0.9374209642410278,0.8435722589492798,0.9881764054298401,0.957429826259613
+0.3780876696109772,0.8970420956611633,0.9406940340995789,0.8481228947639465,0.9886634945869446,0.9603395462036133
+0.3627292811870575,0.9038680195808411,0.9394322037696838,0.8469852209091187,0.9891924262046814,0.9614449143409729
+0.34200209379196167,0.9021615386009216,0.939601480960846,0.8583617806434631,0.9902109503746033,0.9647938013076782
+0.334041029214859,0.9072809815406799,0.9371533989906311,0.8651877045631409,0.990960955619812,0.967582106590271
+0.3198903799057007,0.905005693435669,0.9435483813285828,0.8651877045631409,0.9917459487915039,0.9696226119995117
+0.3053702712059021,0.9186575412750244,0.9466343522071838,0.8879408240318298,0.9928143620491028,0.9726831316947937
+0.28857776522636414,0.9197952151298523,0.9533169269561768,0.8828213810920715,0.9937466382980347,0.9759120941162109
+0.2760087251663208,0.9254835247993469,0.9516323804855347,0.8953356146812439,0.9939822554588318,0.9776926636695862
+0.264492928981781,0.9402730464935303,0.9601208567619324,0.9038680195808411,0.9943122267723083,0.9800554513931274
+0.25308170914649963,0.9362912178039551,0.9630973935127258,0.9055745005607605,0.9952266812324524,0.9825465679168701
+0.2412933111190796,0.9385665655136108,0.9591346383094788,0.9078498482704163,0.995365560054779,0.98276686668396
+0.2274499386548996,0.947098970413208,0.9635385274887085,0.916951060295105,0.9961479902267456,0.9854483008384705
+0.22880755364894867,0.9482366442680359,0.9646918177604675,0.916951060295105,0.9962066411972046,0.985849142074585
+0.22187364101409912,0.9465301632881165,0.9654967188835144,0.9232081770896912,0.9962157011032104,0.985856294631958
+0.20829614996910095,0.9465301632881165,0.9683959484100342,0.9237770438194275,0.9966818690299988,0.9877234697341919
+0.19785714149475098,0.9539248943328857,0.968639075756073,0.9311717748641968,0.9967736601829529,0.9879173636436462
+0.1905350685119629,0.9539248943328857,0.9697508811950684,0.9300341010093689,0.997134804725647,0.9890785813331604
+0.1898670196533203,0.9562002420425415,0.9740106463432312,0.9379976987838745,0.9974026679992676,0.9902877807617188
+0.16971267759799957,0.9618884921073914,0.9759671688079834,0.947098970413208,0.9978582262992859,0.9921320676803589
+0.1731279045343399,0.9567690491676331,0.9705014824867249,0.9357224106788635,0.9980117678642273,0.992042064666748
+0.16379214823246002,0.9624573588371277,0.9793144464492798,0.9425483345985413,0.9981778264045715,0.993337869644165
+0.15729886293411255,0.9670079350471497,0.9794842004776001,0.9505119323730469,0.9981173276901245,0.9932225942611694
+0.1519521027803421,0.9681456089019775,0.9789719581604004,0.9533560872077942,0.9982203841209412,0.9933836460113525
+0.1426904946565628,0.9687144756317139,0.9830310344696045,0.9556313753128052,0.9984652996063232,0.9944801330566406
+0.1396665722131729,0.9715585708618164,0.9836448431015015,0.9579067230224609,0.9987286329269409,0.99540114402771
+0.13700713217258453,0.9732650518417358,0.9825276732444763,0.9596132040023804,0.9985508918762207,0.9950873255729675
+0.1304110884666443,0.9721274375915527,0.9802210330963135,0.9584755301475525,0.9986488819122314,0.995171308517456
+0.12580250203609467,0.9715585708618164,0.9825276732444763,0.9596132040023804,0.9988203644752502,0.9959862232208252
+0.1259748488664627,0.9738339185714722,0.9843114614486694,0.9635949730873108,0.9987438321113586,0.9954633712768555
+0.12113135308027267,0.9721274375915527,0.9842749238014221,0.9613196849822998,0.9988210797309875,0.9958704710006714
+0.11687353253364563,0.9806598424911499,0.9861030578613281,0.9687144756317139,0.9990288615226746,0.9966581463813782
+0.11428899317979813,0.9761092066764832,0.9860708117485046,0.9664391279220581,0.9989103674888611,0.9963631629943848
+0.11015055328607559,0.9789533615112305,0.9848924875259399,0.9641638398170471,0.9993072152137756,0.9970510005950928
+0.1018630787730217,0.9835039973258972,0.9907192587852478,0.9715585708618164,0.9991720914840698,0.9973061084747314
+0.09948068857192993,0.9806598424911499,0.9861511588096619,0.9721274375915527,0.9993759393692017,0.9973627328872681
+0.09226065129041672,0.9846416115760803,0.9890804886817932,0.9789533615112305,0.999488115310669,0.9979531168937683
+0.09357326477766037,0.9846416115760803,0.9902411103248596,0.9812286496162415,0.999201238155365,0.9974350929260254
+0.09682224690914154,0.9829351305961609,0.9913395047187805,0.9766780138015747,0.9992966055870056,0.9971510767936707
+0.08545508980751038,0.9869169592857361,0.9919401407241821,0.9800910353660583,0.99965900182724,0.9986804723739624
+0.08204644918441772,0.9886234402656555,0.9919401407241821,0.9800910353660583,0.9997038841247559,0.9986907243728638
+0.08530836552381516,0.9852104783058167,0.9902355074882507,0.9806598424911499,0.9995555281639099,0.9981527328491211
+0.07668951153755188,0.988054633140564,0.9925458431243896,0.9846416115760803,0.999380350112915,0.9982993602752686
+0.07907727360725403,0.9874857664108276,0.9913991093635559,0.9835039973258972,0.999413013458252,0.9984429478645325
+0.07635454833507538,0.9886234402656555,0.994246244430542,0.9829351305961609,0.9996430277824402,0.9985947608947754
+0.0720764771103859,0.9897611141204834,0.9919816851615906,0.9852104783058167,0.9993979930877686,0.9983196258544922
+0.07009478658437729,0.9891922473907471,0.9942528605461121,0.9840728044509888,0.9994844794273376,0.9987422227859497
+0.06989792734384537,0.988054633140564,0.9902355074882507,0.9806598424911499,0.9997352957725525,0.9988374710083008
+0.06578279286623001,0.9926052093505859,0.9959885478019714,0.9886234402656555,0.9995163679122925,0.998877763748169
+0.06186188757419586,0.9920364022254944,0.994288980960846,0.990329921245575,0.9997380971908569,0.998934268951416
+0.06074108928442001,0.9914675951004028,0.9942792057991028,0.9886234402656555,0.9997789263725281,0.9990378618240356
+0.06113959476351738,0.9914675951004028,0.9936926364898682,0.9857792854309082,0.9994560480117798,0.9985777139663696
+0.055103547871112823,0.9937428832054138,0.9965674877166748,0.9908987283706665,0.9998592138290405,0.9993912577629089
+0.05687163770198822,0.9931740760803223,0.9965655207633972,0.990329921245575,0.9998411536216736,0.999319314956665
+0.054107341915369034,0.9908987283706665,0.9931467771530151,0.9891922473907471,0.9997796416282654,0.9990480542182922
+0.05211716517806053,0.9920364022254944,0.9931467771530151,0.9891922473907471,0.9998010396957397,0.9991270303726196
+0.048029713332653046,0.9948805570602417,0.996004581451416,0.9926052093505859,0.9998986721038818,0.999527096748352
+0.0492374487221241,0.9960182309150696,0.9965733885765076,0.9926052093505859,0.9998887181282043,0.999537467956543
+0.047328729182481766,0.9954493641853333,0.9959931373596191,0.9897611141204834,0.9999162554740906,0.9995969533920288
+0.048006121069192886,0.9937428832054138,0.9954338073730469,0.9920364022254944,0.9999111890792847,0.999610424041748
+0.04283490031957626,0.9971558451652527,0.9971444606781006,0.9931740760803223,0.9999421238899231,0.999731183052063
+0.044679854065179825,0.9960182309150696,0.9971412420272827,0.9920364022254944,0.9999396800994873,0.9997044801712036
+0.044514305889606476,0.9971558451652527,0.9971510171890259,0.9954493641853333,0.9999289512634277,0.9996696710586548
+0.042500089854002,0.9954493641853333,0.996004581451416,0.9926052093505859,0.9999589920043945,0.9997988939285278
+0.040481049567461014,0.9954493641853333,0.9977116584777832,0.9920364022254944,0.9999074935913086,0.9995880126953125
+0.038696154952049255,0.9965870380401611,0.9971444606781006,0.9931740760803223,0.9999667406082153,0.9998382329940796
+0.03781864047050476,0.9965870380401611,0.9982876777648926,0.9948805570602417,0.9999375939369202,0.9997057914733887
+0.03749913349747658,0.9960182309150696,0.9971526265144348,0.9960182309150696,0.9999620318412781,0.9998192191123962
+0.037564508616924286,0.9948805570602417,0.9960136413574219,0.9948805570602417,0.9999606609344482,0.9998129606246948
+0.034960221499204636,0.9948805570602417,0.9971461296081543,0.9937428832054138,0.9999890923500061,0.9999460577964783
+0.03410770371556282,0.9965870380401611,0.9965811967849731,0.9948805570602417,0.9999533295631409,0.9997756481170654
+0.03249245136976242,0.9965870380401611,0.9965850710868835,0.9960182309150696,0.9999715685844421,0.9998619556427002
+0.02971029467880726,0.9971558451652527,0.9977207779884338,0.9960182309150696,0.9999905228614807,0.9999533891677856
+0.03182255104184151,0.997724711894989,0.9982896447181702,0.9960182309150696,0.9999852180480957,0.9999271631240845
+0.030200952664017677,0.9971558451652527,0.9971510171890259,0.9954493641853333,0.999987006187439,0.9999362230300903
+0.03015146404504776,0.9971558451652527,0.9971510171890259,0.9954493641853333,0.9999826550483704,0.9999139904975891
+0.02828197367489338,0.9971558451652527,0.9982896447181702,0.9960182309150696,0.999983012676239,0.9999187588691711
+0.02655121311545372,0.9965870380401611,0.9971526265144348,0.9960182309150696,0.9999889731407166,0.9999455213546753
+0.027044467628002167,0.997724711894989,0.998291552066803,0.9971558451652527,0.999995768070221,0.9999790191650391
+0.02613493800163269,0.997724711894989,0.9982905983924866,0.9965870380401611,0.9999914765357971,0.9999574422836304
+0.027532944455742836,0.997724711894989,0.997724711894989,0.997724711894989,0.999990701675415,0.9999537467956543
+0.025817418470978737,0.997724711894989,0.9988597631454468,0.9965870380401611,0.9999938011169434,0.999969482421875
+0.02641206420958042,0.997724711894989,0.998291552066803,0.9971558451652527,0.9999896883964539,0.9999490976333618
+0.022835543379187584,0.997724711894989,0.9982925653457642,0.997724711894989,0.9999910593032837,0.9999561309814453
+0.025914177298545837,0.9965870380401611,0.9977169036865234,0.9943116903305054,0.9999747276306152,0.9998764991760254
+0.02310544066131115,0.9982935190200806,0.9994295239448547,0.9965870380401611,0.9999976754188538,0.9999882578849792
+0.02241845428943634,0.9982935190200806,0.9988610744476318,0.997724711894989,0.9999951124191284,0.9999752640724182
+0.023210283368825912,0.9982935190200806,0.9982925653457642,0.997724711894989,0.9999966621398926,0.999983549118042
+0.020729660987854004,0.9982935190200806,0.9994301795959473,0.997724711894989,0.9999986886978149,0.9999935030937195
diff --git a/High Throughput Algae Cell Detection/Model/results/Xception_plots.csv b/High Throughput Algae Cell Detection/Model/results/Xception_plots.csv
new file mode 100644
index 000000000..d13575fec
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/results/Xception_plots.csv	
@@ -0,0 +1,101 @@
+loss,accuracy,precision,recall,auc,prc
+1.3769829273223877,0.4806598424911499,0.7459677457809448,0.10523322224617004,0.7965501546859741,0.46872520446777344
+0.8985863924026489,0.7718998789787292,0.8541666865348816,0.3964732587337494,0.9214739799499512,0.7450732588768005
+0.7409140467643738,0.8174061179161072,0.8754940629005432,0.5039817690849304,0.9430081844329834,0.8104636669158936
+0.6661986708641052,0.8310580253601074,0.8887884020805359,0.5591581463813782,0.9528785347938538,0.8433266878128052
+0.5953144431114197,0.8555176258087158,0.8976311087608337,0.6035267114639282,0.9624031782150269,0.8700284957885742
+0.5561298131942749,0.8686006665229797,0.9001636505126953,0.6257110238075256,0.9668911695480347,0.885712742805481
+0.527125358581543,0.8686006665229797,0.9005568623542786,0.6439135670661926,0.9698118567466736,0.8938959240913391
+0.49795064330101013,0.8759954571723938,0.9140866994857788,0.6717861294746399,0.9718418121337891,0.9018910527229309
+0.4700825810432434,0.8771331310272217,0.913476288318634,0.6786120533943176,0.9750156402587891,0.9115422964096069
+0.4506581127643585,0.884527862071991,0.9195830225944519,0.7025028467178345,0.9776692390441895,0.9185434579849243
+0.4202112555503845,0.8976109027862549,0.9227405190467834,0.7201365232467651,0.9809104204177856,0.9288268685340881
+0.4082212746143341,0.8947668075561523,0.9260057210922241,0.733219563961029,0.9815074801445007,0.9333463907241821
+0.4012455344200134,0.8993173837661743,0.9223093390464783,0.7360637187957764,0.9815773963928223,0.9328016042709351
+0.38240769505500793,0.9078498482704163,0.9328147172927856,0.7502844333648682,0.9836495518684387,0.9396300315856934
+0.37507084012031555,0.9061433672904968,0.9312499761581421,0.7627986073493958,0.9841921329498291,0.9418942928314209
+0.3594977855682373,0.9061433672904968,0.9304105639457703,0.7605233192443848,0.9856107234954834,0.9450128078460693
+0.32945749163627625,0.9186575412750244,0.9443681240081787,0.7821387648582458,0.9880568385124207,0.9550848007202148
+0.33071017265319824,0.9158134460449219,0.9412955641746521,0.7935153841972351,0.9881169199943542,0.9549114108085632
+0.31159326434135437,0.9237770438194275,0.9490274786949158,0.8048919439315796,0.9894621968269348,0.9597463607788086
+0.310829758644104,0.9209328889846802,0.9409814476966858,0.8071672320365906,0.989523708820343,0.9601486921310425
+0.28947412967681885,0.9323094487190247,0.9527868628501892,0.8265073895454407,0.9907016754150391,0.9648427367210388
+0.2848530113697052,0.9323094487190247,0.9513477683067322,0.8230944275856018,0.9909653663635254,0.9660617113113403
+0.27400678396224976,0.9334471225738525,0.9568576812744141,0.8452787399291992,0.9916463494300842,0.9683443307876587
+0.26711997389793396,0.9300341010093689,0.9493265151977539,0.8418657779693604,0.99242103099823,0.9706801176071167
+0.25851622223854065,0.935153603553772,0.9541109204292297,0.8515358567237854,0.9923595786094666,0.9710221886634827
+0.25681886076927185,0.939704179763794,0.9567704796791077,0.8560864329338074,0.9926534295082092,0.9718136787414551
+0.24920867383480072,0.9362912178039551,0.9537389278411865,0.8560864329338074,0.9928205013275146,0.9723143577575684
+0.24495500326156616,0.9362912178039551,0.9508816003799438,0.8589305877685547,0.9931420087814331,0.9726341962814331
+0.23752428591251373,0.9459612965583801,0.9620882272720337,0.8805460929870605,0.9937940835952759,0.9765164852142334
+0.22674541175365448,0.9436860084533691,0.961298406124115,0.8759954571723938,0.9947915077209473,0.9790838956832886
+0.22568662464618683,0.944823682308197,0.960420548915863,0.8833901882171631,0.9942945837974548,0.9780174493789673
+0.2149425595998764,0.9482366442680359,0.9641088843345642,0.8862343430519104,0.9948568940162659,0.9809944033622742
+0.20977936685085297,0.947098970413208,0.9630541801452637,0.8896473050117493,0.9955761432647705,0.9827520847320557
+0.214882031083107,0.9408418536186218,0.9576946496963501,0.8885096907615662,0.99488765001297,0.9800847768783569
+0.20469139516353607,0.9527872800827026,0.962895393371582,0.9004550576210022,0.9949600100517273,0.9812939167022705
+0.20309972763061523,0.9488054513931274,0.9604141116142273,0.8970420956611633,0.994994580745697,0.9812809228897095
+0.1945742815732956,0.9510807991027832,0.9678007364273071,0.9061433672904968,0.995715856552124,0.9834401607513428
+0.18846602737903595,0.9584755301475525,0.97096186876297,0.9129692912101746,0.9960967302322388,0.9854697585105896
+0.1824798732995987,0.9550625681877136,0.969072163105011,0.9089874625205994,0.9959458708763123,0.9851770997047424
+0.17809882760047913,0.9613196849822998,0.9704641103744507,0.9158134460449219,0.9963282942771912,0.9862570762634277
+0.17552271485328674,0.9624573588371277,0.9711712002754211,0.9197952151298523,0.9963115453720093,0.9862874746322632
+0.1710059940814972,0.9601820111274719,0.9688808917999268,0.9209328889846802,0.9965870380401611,0.986777126789093
+0.16578419506549835,0.9630261659622192,0.972123384475708,0.9323094487190247,0.9968913197517395,0.9883508086204529
+0.16341160237789154,0.9653014540672302,0.9737626910209656,0.9288964867591858,0.9968337416648865,0.9879857897758484
+0.163384810090065,0.9653014540672302,0.972700297832489,0.9323094487190247,0.9967413544654846,0.9880588054656982
+0.15566910803318024,0.9681456089019775,0.9762892723083496,0.9368600845336914,0.9966914057731628,0.988093912601471
+0.16170263290405273,0.9624573588371277,0.9709715843200684,0.9323094487190247,0.9969808459281921,0.9886012077331543
+0.1520625799894333,0.9692832827568054,0.9746760725975037,0.9414107203483582,0.9972171187400818,0.9896076321601868
+0.1421247124671936,0.9721274375915527,0.9781323671340942,0.9414107203483582,0.9973379969596863,0.9903505444526672
+0.142020583152771,0.9687144756317139,0.9747356176376343,0.9436860084533691,0.9976617097854614,0.9907681345939636
+0.14237947762012482,0.969852089881897,0.9781453013420105,0.9419795274734497,0.99739670753479,0.9904931783676147
+0.14297471940517426,0.9692832827568054,0.9770588278770447,0.944823682308197,0.9972649812698364,0.9901269674301147
+0.13595132529735565,0.9692832827568054,0.9805079698562622,0.9442548155784607,0.9976242780685425,0.9913553595542908
+0.13349805772304535,0.9715585708618164,0.980622410774231,0.9499431252479553,0.9976051449775696,0.9913954734802246
+0.13485120236873627,0.9687144756317139,0.9754098653793335,0.9476677775382996,0.9975928068161011,0.9911050796508789
+0.12840114533901215,0.9738339185714722,0.9817754030227661,0.9499431252479553,0.997737467288971,0.991814374923706
+0.12476295232772827,0.9732650518417358,0.9818394780158997,0.9533560872077942,0.9979749321937561,0.9927277565002441
+0.12020270526409149,0.977246880531311,0.9859976768493652,0.9613196849822998,0.9980480670928955,0.9932315349578857
+0.11961393058300018,0.9761092066764832,0.9824766516685486,0.9567690491676331,0.9982509613037109,0.9937843084335327
+0.1168150082230568,0.9749715328216553,0.9824970960617065,0.9579067230224609,0.9979377388954163,0.9925529360771179
+0.12053978443145752,0.9761092066764832,0.9831199049949646,0.9607508778572083,0.998152494430542,0.9926928281784058
+0.11308369040489197,0.9789533615112305,0.9877836108207703,0.9658703207969666,0.9981464743614197,0.9936792850494385
+0.11326047778129578,0.9744027256965637,0.9802440404891968,0.9596132040023804,0.9983853101730347,0.9943222999572754
+0.1139998808503151,0.9761092066764832,0.9825581312179565,0.9613196849822998,0.9980518817901611,0.9931145906448364
+0.11444590240716934,0.9732650518417358,0.980758011341095,0.9567690491676331,0.9979317784309387,0.992638349533081
+0.1048067957162857,0.9817975163459778,0.98552405834198,0.9681456089019775,0.9982160925865173,0.9940332770347595
+0.10898139327764511,0.9789533615112305,0.9831981658935547,0.9653014540672302,0.9982714653015137,0.9933271408081055
+0.10033179819583893,0.9812286496162415,0.9843568801879883,0.9664391279220581,0.9982701539993286,0.9941838979721069
+0.10158497095108032,0.9812286496162415,0.9855324029922485,0.9687144756317139,0.9982030987739563,0.9938737154006958
+0.10083014518022537,0.9823663234710693,0.9855907559394836,0.9726962447166443,0.9987203478813171,0.9950913190841675
+0.09948203712701797,0.9823663234710693,0.9849884510040283,0.9704209566116333,0.9985734820365906,0.9950747489929199
+0.09707845002412796,0.9829351305961609,0.9872537851333618,0.9692832827568054,0.9986366033554077,0.9954487085342407
+0.0934772789478302,0.9817975163459778,0.9867205619812012,0.9721274375915527,0.998687744140625,0.9956583976745605
+0.09688351303339005,0.9806598424911499,0.986682116985321,0.9692832827568054,0.9989092350006104,0.9957476258277893
+0.09551651030778885,0.9812286496162415,0.9849884510040283,0.9704209566116333,0.998552680015564,0.9951937794685364
+0.09167633205652237,0.9829351305961609,0.9867587685585022,0.9749715328216553,0.9986187219619751,0.9954332709312439
+0.09055093675851822,0.9829351305961609,0.9861511588096619,0.9721274375915527,0.9987378120422363,0.9957334995269775
+0.08719505369663239,0.9846416115760803,0.9884925484657288,0.977246880531311,0.9988967776298523,0.9965276718139648
+0.08861978352069855,0.9863481521606445,0.9902186393737793,0.9789533615112305,0.9986681342124939,0.995522141456604
+0.08548131585121155,0.9829351305961609,0.9873198866844177,0.9744027256965637,0.9989365339279175,0.9965312480926514
+0.08440718799829483,0.9863481521606445,0.9907993078231812,0.9800910353660583,0.9989369511604309,0.9968434572219849
+0.08714567124843597,0.9835039973258972,0.9879379868507385,0.9783845543861389,0.9987747669219971,0.9957923293113708
+0.0826885923743248,0.9857792854309082,0.9885123372077942,0.9789533615112305,0.9988892078399658,0.9963358640670776
+0.07844257354736328,0.988054633140564,0.9919447898864746,0.9806598424911499,0.9989372491836548,0.9964680075645447
+0.07798032462596893,0.9869169592857361,0.9896610975265503,0.9800910353660583,0.9990319609642029,0.9971157312393188
+0.07725126296281815,0.9874857664108276,0.9896789193153381,0.9817975163459778,0.9989948868751526,0.9967000484466553
+0.0782194659113884,0.9852104783058167,0.9879656434059143,0.9806598424911499,0.9989845156669617,0.9968193769454956
+0.07611382007598877,0.988054633140564,0.9902690052986145,0.9840728044509888,0.999032199382782,0.9969335794448853
+0.07709528505802155,0.9869169592857361,0.9902355074882507,0.9806598424911499,0.9989998936653137,0.9969272613525391
+0.07436680048704147,0.9869169592857361,0.9902578592300415,0.9829351305961609,0.99894118309021,0.9960660338401794
+0.07116539776325226,0.9869169592857361,0.9891366362571716,0.9840728044509888,0.9993827939033508,0.9975321292877197
+0.07543966174125671,0.9886234402656555,0.9908362030982971,0.9840728044509888,0.9989564418792725,0.9965940713882446
+0.06997927278280258,0.988054633140564,0.9908466935157776,0.9852104783058167,0.9990852475166321,0.9972314834594727
+0.06847427785396576,0.988054633140564,0.9908519387245178,0.9857792854309082,0.9991112351417542,0.9971040487289429
+0.06790818274021149,0.9874857664108276,0.9897142648696899,0.9852104783058167,0.999176025390625,0.9975606799125671
+0.06788841634988785,0.988054633140564,0.9908466935157776,0.9852104783058167,0.9991897940635681,0.9976742267608643
+0.06699346750974655,0.9886234402656555,0.9914138317108154,0.9852104783058167,0.9992354512214661,0.9977502822875977
+0.06736716628074646,0.9857792854309082,0.9885714054107666,0.9840728044509888,0.9991961121559143,0.9975553750991821
+0.06579464673995972,0.988054633140564,0.9908362030982971,0.9840728044509888,0.9992026686668396,0.9976078271865845
+0.06730754673480988,0.9869169592857361,0.9891366362571716,0.9840728044509888,0.999390721321106,0.9976036548614502
diff --git a/High Throughput Algae Cell Detection/Model/results/preprocess.ipynb b/High Throughput Algae Cell Detection/Model/results/preprocess.ipynb
new file mode 100644
index 000000000..c22f68903
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/results/preprocess.ipynb	
@@ -0,0 +1,299 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import pandas as pd\n",
+    "import cv2\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lab_dir=r\"D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\train\\labels\\\\\"\n",
+    "labels=os.listdir(lab_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "img_dir=r\"D:\\SWOC-2024\\DL-Simplified\\High Throughput Algae Cell Detection\\Dataset\\alge_dataset\\train\\images\\\\\"\n",
+    "images=os.listdir(img_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "          image  Class  x_center  y_center         w         h\n",
+      "0     00001.txt      4  0.251050  0.346217  0.022059  0.060855\n",
+      "1     00001.txt      4  0.335872  0.855263  0.019433  0.065789\n",
+      "2     00001.txt      3  0.266019  0.877467  0.026786  0.064145\n",
+      "3     00002.txt      2  0.572742  0.848684  0.025735  0.069079\n",
+      "4     00002.txt      1  0.662553  0.131579  0.008929  0.026316\n",
+      "...         ...    ...       ...       ...       ...       ...\n",
+      "1753  00699.txt      3  0.462500  0.906667  0.054167  0.103333\n",
+      "1754  00699.txt      4  0.305208  0.770833  0.035417  0.055000\n",
+      "1755  00700.txt      0  0.038542  0.620833  0.070833  0.075000\n",
+      "1756  00700.txt      0  0.035937  0.182500  0.063542  0.105000\n",
+      "1757  00700.txt      4  0.532813  0.182500  0.044792  0.065000\n",
+      "\n",
+      "[1701 rows x 6 columns]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Load the CSV file\n",
+    "csv_file = r'Dataset/alge_dataset/labels.csv'\n",
+    "df = pd.read_csv(csv_file,index_col=0)\n",
+    "grouped_df=df.groupby('image')\n",
+    "print(grouped_df.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "image       00001.txt\n",
+      "Class               4\n",
+      "x_center      0.25105\n",
+      "y_center     0.346217\n",
+      "w            0.022059\n",
+      "h            0.060855\n",
+      "Name: 0, dtype: object\n",
+      "image       00001.txt\n",
+      "Class               4\n",
+      "x_center     0.335872\n",
+      "y_center     0.855263\n",
+      "w            0.019433\n",
+      "h            0.065789\n",
+      "Name: 1, dtype: object\n",
+      "image       00001.txt\n",
+      "Class               3\n",
+      "x_center     0.266019\n",
+      "y_center     0.877467\n",
+      "w            0.026786\n",
+      "h            0.064145\n",
+      "Name: 2, dtype: object\n"
+     ]
+    }
+   ],
+   "source": [
+    "for image_filename,group in grouped_df:\n",
+    "    for ind,row in group.iterrows():\n",
+    "        print(row)\n",
+    "    break"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##### CODE TO CREATE DATASET FOR NON_YOLO MODELS TRAINING"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "- CREATE SUB FOLDER {0 TO 5} in non_yolo folder before running the code below"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\"import cv2\n",
+    "import os\n",
+    "import pandas as pd\n",
+    "\n",
+    "# Load the CSV file\n",
+    "csv_file = 'labels.csv'\n",
+    "df = pd.read_csv(csv_file, index_col=0)\n",
+    "\n",
+    "# Directory to save the cropped images\n",
+    "output_base_dir = r'path_to_non_yolo_folder'\n",
+    "\n",
+    "# Group the DataFrame by image filename\n",
+    "grouped_df = df.groupby('image')\n",
+    "\n",
+    "# Iterate over each image group\n",
+    "for image_filename, group in grouped_df:\n",
+    "    # Load the image\n",
+    "    image_path = image_filename.replace('.txt', '.jpg')\n",
+    "    image = cv2.imread(img_dir + image_path)\n",
+    "\n",
+    "    # Iterate over each row in the group\n",
+    "    for index, row in group.iterrows():\n",
+    "        # Extract information from the CSV row\n",
+    "        class_label = row['Class']\n",
+    "        x_center, y_center, width, height = row['x_center'], row['y_center'], row['w'], row['h']\n",
+    "\n",
+    "        # Convert normalized coordinates to pixel coordinates\n",
+    "        h, w, _ = image.shape\n",
+    "        x_center_pixel = int(x_center * w)\n",
+    "        y_center_pixel = int(y_center * h)\n",
+    "        width_pixel = int(width * w)\n",
+    "        height_pixel = int(height * h)\n",
+    "\n",
+    "        # Calculate bounding box coordinates\n",
+    "        x_min = max(0, x_center_pixel - width_pixel // 2)\n",
+    "        y_min = max(0, y_center_pixel - height_pixel // 2)\n",
+    "        x_max = min(w, x_center_pixel + width_pixel // 2)\n",
+    "        y_max = min(h, y_center_pixel + height_pixel // 2)\n",
+    "\n",
+    "        # Crop the image based on the bounding box coordinates\n",
+    "        cropped_image = image[y_min:y_max, x_min:x_max]\n",
+    "\n",
+    "        # Save the cropped image to its respective class folder\n",
+    "        output_dir = os.path.join(output_base_dir, str(class_label))\n",
+    "        os.makedirs(output_dir, exist_ok=True)\n",
+    "\n",
+    "        output_filename = f\"{class_label}_{index}.jpg\"\n",
+    "        output_path = os.path.join(output_dir, output_filename)\n",
+    "        cv2.imwrite(output_path, cropped_image)\"\"\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Plot Analysis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Conv=pd.read_csv('ConvNeXtTiny_plot.csv')\n",
+    "Incv3=pd.read_csv('InceptionV3_plot.csv')\n",
+    "Xcept=pd.read_csv('Xception_plots.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1600x800 with 6 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot training history for multiple metrics\n",
+    "plt.figure(figsize=(16, 8))\n",
+    "\n",
+    "# Plot training & validation accuracy values\n",
+    "plt.subplot(2, 3, 1)\n",
+    "plt.plot(Xcept['accuracy'],label='Xception')\n",
+    "plt.plot(Incv3['accuracy'],label='InceptionV3')\n",
+    "plt.plot(Conv['accuracy'],label='ConvNextTiny')\n",
+    "plt.title('Models Accuracy')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.legend()\n",
+    "# Plot training & validation loss values\n",
+    "plt.subplot(2, 3, 2)\n",
+    "plt.plot(Xcept['loss'],label='Xception')\n",
+    "plt.plot(Incv3['loss'],label='InceptionV3')\n",
+    "plt.plot(Conv['loss'],label='ConvNextTiny')\n",
+    "plt.title('Models Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.legend()\n",
+    "# Plot training & validation precision values\n",
+    "plt.subplot(2, 3, 3)\n",
+    "plt.plot(Xcept['precision'],label='Xception')\n",
+    "plt.plot(Incv3['precision'],label='InceptionV3')\n",
+    "plt.plot(Conv['precision'],label='ConvNextTiny')\n",
+    "plt.title('Models Precision')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Precision')\n",
+    "plt.legend()\n",
+    "# Plot training & validation recall values\n",
+    "plt.subplot(2, 3, 4)\n",
+    "plt.plot(Xcept['recall'],label='Xception')\n",
+    "plt.plot(Incv3['recall'],label='InceptionV3')\n",
+    "plt.plot(Conv['recall'],label='ConvNextTiny')\n",
+    "plt.title('Models Recall')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Recall')\n",
+    "plt.legend()\n",
+    "# Plot training & validation AUC values\n",
+    "plt.subplot(2, 3, 5)\n",
+    "plt.plot(Xcept['auc'],label='Xception')\n",
+    "plt.plot(Incv3['auc'],label='InceptionV3')\n",
+    "plt.plot(Conv['auc'],label='ConvNextTiny')\n",
+    "plt.title('Models AUC')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('AUC')\n",
+    "plt.legend()\n",
+    "# Plot training & validation PRC values\n",
+    "plt.subplot(2, 3, 6)\n",
+    "plt.plot(Xcept['prc'],label='Xception')\n",
+    "plt.plot(Incv3['prc'],label='InceptionV3')\n",
+    "plt.plot(Conv['prc'],label='ConvNextTiny')\n",
+    "plt.title('Models PRC')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('PRC')\n",
+    "plt.legend()\n",
+    "plt.tight_layout()\n",
+    "plt.savefig('NON_YOLO_RESULTS',dpi=300)\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "tf",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.17"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train/args.yaml b/High Throughput Algae Cell Detection/Model/runs/detect/train/args.yaml
new file mode 100644
index 000000000..38470e2bf
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/runs/detect/train/args.yaml	
@@ -0,0 +1,105 @@
+task: detect
+mode: train
+model: D:\SWOC-2024\DL-Simplified\High Throughput Algae Cell Detection\Model\yolov8n.pt
+data: D:\SWOC-2024\DL-Simplified\High Throughput Algae Cell Detection\Dataset\alge_dataset\data.yaml
+epochs: 25
+time: null
+patience: 50
+batch: 8
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: null
+name: train
+exist_ok: false
+pretrained: true
+optimizer: auto
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+save_hybrid: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: false
+opset: null
+workspace: 4
+nms: false
+lr0: 0.01
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+label_smoothing: 0.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+mosaic: 1.0
+mixup: 0.0
+copy_paste: 0.0
+auto_augment: randaugment
+erasing: 0.4
+crop_fraction: 1.0
+cfg: null
+tracker: botsort.yaml
+save_dir: runs\detect\train
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train/events.out.tfevents.1705441747.DESKTOP-9T80HOG.18292.0 b/High Throughput Algae Cell Detection/Model/runs/detect/train/events.out.tfevents.1705441747.DESKTOP-9T80HOG.18292.0
new file mode 100644
index 000000000..746d4e977
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train/events.out.tfevents.1705441747.DESKTOP-9T80HOG.18292.0 differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train/labels.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train/labels.jpg
new file mode 100644
index 000000000..6df865fb2
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train/labels.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train/labels_correlogram.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train/labels_correlogram.jpg
new file mode 100644
index 000000000..689678db8
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train/labels_correlogram.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/F1_curve.png b/High Throughput Algae Cell Detection/Model/runs/detect/train2/F1_curve.png
new file mode 100644
index 000000000..5c7f99861
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/F1_curve.png differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/PR_curve.png b/High Throughput Algae Cell Detection/Model/runs/detect/train2/PR_curve.png
new file mode 100644
index 000000000..6563254fb
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/PR_curve.png differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/P_curve.png b/High Throughput Algae Cell Detection/Model/runs/detect/train2/P_curve.png
new file mode 100644
index 000000000..474fb2837
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/P_curve.png differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/R_curve.png b/High Throughput Algae Cell Detection/Model/runs/detect/train2/R_curve.png
new file mode 100644
index 000000000..c706fea09
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/R_curve.png differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/args.yaml b/High Throughput Algae Cell Detection/Model/runs/detect/train2/args.yaml
new file mode 100644
index 000000000..057a8b609
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/runs/detect/train2/args.yaml	
@@ -0,0 +1,105 @@
+task: detect
+mode: train
+model: D:\SWOC-2024\DL-Simplified\High Throughput Algae Cell Detection\Model\yolov8n.pt
+data: D:\SWOC-2024\DL-Simplified\High Throughput Algae Cell Detection\Dataset\alge_dataset\data.yaml
+epochs: 25
+time: null
+patience: 50
+batch: 4
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: null
+name: train2
+exist_ok: false
+pretrained: true
+optimizer: auto
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 10
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+freeze: null
+multi_scale: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+save_hybrid: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+vid_stride: 1
+stream_buffer: false
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+embed: null
+show: false
+save_frames: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+show_boxes: true
+line_width: null
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: false
+opset: null
+workspace: 4
+nms: false
+lr0: 0.01
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+label_smoothing: 0.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+mosaic: 1.0
+mixup: 0.0
+copy_paste: 0.0
+auto_augment: randaugment
+erasing: 0.4
+crop_fraction: 1.0
+cfg: null
+tracker: botsort.yaml
+save_dir: runs\detect\train2
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/confusion_matrix.png b/High Throughput Algae Cell Detection/Model/runs/detect/train2/confusion_matrix.png
new file mode 100644
index 000000000..d66d8f540
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/confusion_matrix.png differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/confusion_matrix_normalized.png b/High Throughput Algae Cell Detection/Model/runs/detect/train2/confusion_matrix_normalized.png
new file mode 100644
index 000000000..b7f6aca06
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/confusion_matrix_normalized.png differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/events.out.tfevents.1705442000.DESKTOP-9T80HOG.7772.0 b/High Throughput Algae Cell Detection/Model/runs/detect/train2/events.out.tfevents.1705442000.DESKTOP-9T80HOG.7772.0
new file mode 100644
index 000000000..e2b83f530
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/events.out.tfevents.1705442000.DESKTOP-9T80HOG.7772.0 differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/labels.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/labels.jpg
new file mode 100644
index 000000000..6df865fb2
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/labels.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/labels_correlogram.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/labels_correlogram.jpg
new file mode 100644
index 000000000..689678db8
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/labels_correlogram.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/results.csv b/High Throughput Algae Cell Detection/Model/runs/detect/train2/results.csv
new file mode 100644
index 000000000..ccdd7768e
--- /dev/null
+++ b/High Throughput Algae Cell Detection/Model/runs/detect/train2/results.csv	
@@ -0,0 +1,26 @@
+                  epoch,         train/box_loss,         train/cls_loss,         train/dfl_loss,   metrics/precision(B),      metrics/recall(B),       metrics/mAP50(B),    metrics/mAP50-95(B),           val/box_loss,           val/cls_loss,           val/dfl_loss,                 lr/pg0,                 lr/pg1,                 lr/pg2
+                      1,                 1.4542,                 3.5124,                0.92716,                0.43475,                0.62993,                0.55686,                0.37573,                 1.2069,                 2.1035,                0.89563,             0.00033143,             0.00033143,             0.00033143
+                      2,                 1.2973,                 2.1275,                0.91527,                 0.6578,                0.73677,                0.72877,                0.48829,                  1.179,                 1.4469,                0.90394,             0.00063844,             0.00063844,             0.00063844
+                      3,                 1.2737,                 1.8346,                0.91629,                0.77707,                0.77948,                0.84026,                0.56736,                 1.1698,                 1.1521,                0.89373,             0.00091905,             0.00091905,             0.00091905
+                      4,                 1.2194,                 1.5755,                0.91063,                0.80622,                0.79577,                0.86104,                 0.5853,                 1.1225,                  1.019,                0.88573,              0.0008812,              0.0008812,              0.0008812
+                      5,                 1.1945,                 1.4113,                0.90257,                0.82012,                 0.8032,                0.88505,                0.59896,                 1.1803,                 1.0474,                0.89067,              0.0008812,              0.0008812,              0.0008812
+                      6,                 1.1976,                 1.3123,                0.90148,                0.86962,                0.85492,                0.91704,                0.63813,                 1.0971,                0.87568,                0.88011,              0.0008416,              0.0008416,              0.0008416
+                      7,                 1.1657,                 1.1966,                0.89544,                0.81404,                0.84378,                0.90964,                0.64016,                 1.1003,                0.84396,                0.87606,               0.000802,               0.000802,               0.000802
+                      8,                 1.1511,                 1.1171,                0.89073,                0.82192,                0.87102,                0.91116,                0.64808,                 1.0497,                0.80123,                 0.8709,              0.0007624,              0.0007624,              0.0007624
+                      9,                 1.1628,                 1.0576,                0.88653,                0.88331,                0.87193,                 0.9279,                0.65691,                 1.0818,                0.70762,                 0.8722,              0.0007228,              0.0007228,              0.0007228
+                     10,                 1.1255,                 1.0163,                0.88832,                0.87531,                0.84604,                0.93001,                0.65633,                 1.0662,                0.75338,                  0.865,              0.0006832,              0.0006832,              0.0006832
+                     11,                 1.1488,                 0.9903,                0.89707,                0.85559,                0.86556,                0.92321,                0.65875,                 1.0429,                0.73584,                0.86237,              0.0006436,              0.0006436,              0.0006436
+                     12,                  1.117,                0.99998,                0.88203,                0.88278,                0.86552,                0.93089,                0.67765,                 1.0093,                0.70316,                0.86073,               0.000604,               0.000604,               0.000604
+                     13,                 1.0913,                 0.9111,                0.87776,                0.90145,                0.85992,                0.93915,                0.68843,                 1.0035,                0.69295,                0.85844,              0.0005644,              0.0005644,              0.0005644
+                     14,                 1.1088,                0.91337,                0.87712,                0.88405,                0.84996,                0.92921,                0.64356,                 1.1204,                 0.7067,                0.87179,              0.0005248,              0.0005248,              0.0005248
+                     15,                  1.098,                0.88122,                0.88339,                0.89396,                0.88343,                0.94206,                0.66419,                  1.068,                0.68041,                0.86743,              0.0004852,              0.0004852,              0.0004852
+                     16,                 1.1066,                0.97598,                0.88913,                0.92263,                0.88369,                0.94741,                0.68031,                  1.047,                0.66042,                0.86395,              0.0004456,              0.0004456,              0.0004456
+                     17,                 1.0919,                0.93676,                0.88627,                0.86356,                0.87378,                0.93255,                0.65043,                 1.0862,                0.70603,                0.86642,               0.000406,               0.000406,               0.000406
+                     18,                 1.0833,                 0.8857,                0.89352,                0.89147,                0.89341,                0.94675,                0.68626,                 1.0148,                0.64304,                0.86124,              0.0003664,              0.0003664,              0.0003664
+                     19,                 1.0695,                0.82623,                0.88326,                0.91039,                0.89989,                0.94958,                0.69251,                 1.0094,                0.61632,                  0.855,              0.0003268,              0.0003268,              0.0003268
+                     20,                 1.0792,                 0.8028,                0.88291,                0.89874,                0.88189,                0.94705,                0.68422,                 1.0236,                0.62903,                0.85771,              0.0002872,              0.0002872,              0.0002872
+                     21,                 1.0661,                0.81249,                0.88724,                0.90427,                0.90566,                0.94217,                0.67582,                 1.0269,                0.62994,                0.86074,              0.0002476,              0.0002476,              0.0002476
+                     22,                 1.0557,                0.79156,                0.88187,                0.93308,                0.89075,                0.94824,                0.70325,                 0.9819,                0.58869,                0.85342,               0.000208,               0.000208,               0.000208
+                     23,                 1.0463,                0.78181,                0.87475,                0.89572,                0.91285,                  0.954,                0.70583,                0.96128,                0.57926,                0.84795,              0.0001684,              0.0001684,              0.0001684
+                     24,                 1.0201,                0.74865,                0.86989,                 0.9296,                0.90792,                0.95408,                0.70976,                0.95891,                0.57017,                0.84675,              0.0001288,              0.0001288,              0.0001288
+                     25,                 1.0385,                0.75024,                0.87078,                0.93498,                0.90584,                0.95607,                0.71083,                0.96263,                0.55896,                0.84809,               8.92e-05,               8.92e-05,               8.92e-05
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/results.png b/High Throughput Algae Cell Detection/Model/runs/detect/train2/results.png
new file mode 100644
index 000000000..b17f7629e
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/results.png differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch0.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch0.jpg
new file mode 100644
index 000000000..6bdb87cca
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch0.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch1.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch1.jpg
new file mode 100644
index 000000000..f2f4a151f
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch1.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2.jpg
new file mode 100644
index 000000000..5be021738
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2625.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2625.jpg
new file mode 100644
index 000000000..4101647d1
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2625.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2626.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2626.jpg
new file mode 100644
index 000000000..9d680fe67
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2626.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2627.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2627.jpg
new file mode 100644
index 000000000..a092bc334
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/train_batch2627.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch0_labels.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch0_labels.jpg
new file mode 100644
index 000000000..47a39184b
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch0_labels.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch0_pred.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch0_pred.jpg
new file mode 100644
index 000000000..ea2542bea
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch0_pred.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch1_labels.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch1_labels.jpg
new file mode 100644
index 000000000..1b26ab319
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch1_labels.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch1_pred.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch1_pred.jpg
new file mode 100644
index 000000000..c321cdc11
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch1_pred.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch2_labels.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch2_labels.jpg
new file mode 100644
index 000000000..1e70f4ca2
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch2_labels.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch2_pred.jpg b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch2_pred.jpg
new file mode 100644
index 000000000..1701d8416
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/val_batch2_pred.jpg differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/weights/best.pt b/High Throughput Algae Cell Detection/Model/runs/detect/train2/weights/best.pt
new file mode 100644
index 000000000..b3d5179fd
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/weights/best.pt differ
diff --git a/High Throughput Algae Cell Detection/Model/runs/detect/train2/weights/last.pt b/High Throughput Algae Cell Detection/Model/runs/detect/train2/weights/last.pt
new file mode 100644
index 000000000..16727bc97
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/runs/detect/train2/weights/last.pt differ
diff --git a/High Throughput Algae Cell Detection/Model/yolov8n.pt b/High Throughput Algae Cell Detection/Model/yolov8n.pt
new file mode 100644
index 000000000..d61ef50d3
Binary files /dev/null and b/High Throughput Algae Cell Detection/Model/yolov8n.pt differ
diff --git a/High Throughput Algae Cell Detection/README.md b/High Throughput Algae Cell Detection/README.md
new file mode 100644
index 000000000..951be1ac2
--- /dev/null
+++ b/High Throughput Algae Cell Detection/README.md	
@@ -0,0 +1,152 @@
+# 🌿 High Throughput Algae Cell Detection 🔍
+
+## 🚀 Project Overview
+
+**📌 Project Title**: High Throughput Algae Cell Detection
+
+**🎯 Aim**: The aim of this project is to detect high throughput algae cells using Deep Learning and OpenCV methods.
+
+**📊 Dataset**: [High Throughput Algae Cell Detection Dataset](https://www.kaggle.com/datasets/marquis03/high-throughput-algae-cell-detection)
+
+## 🛠 Approach
+
+I'm planning to explore the following models for the project:
+
+1. [Xception](https://keras.io/api/applications/xception) 🧠
+2. [ConvNeXtTiny](https://keras.io/api/applications/convnext/#convnexttiny-function) 🕹️
+3. [InceptionV3](https://keras.io/api/applications/inceptionv3) 🌀
+4. [YOLOv8n](https://github.com/ultralytics/ultralytics) 🚀
+
+**Reason for Choosing These Models:**
+All mentioned models have approximately close parameters, making them suitable for a comprehensive comparison. I have previous experience working with both pre-trained CNN architectures and YOLOv8 base architectures (tiny and base) for projects like [face-mask-detection](https://github.com/ARPIT2128/SAP-internal-face-mask-detection) and more.
+
+## 📚 Dataset and Models Used
+
+[Dataset](https://github.com/ARPIT2128/DL-Simplified/blob/main/High%20Throughput%20Algae%20Cell%20Detection/Dataset/DATASET.md) description is provided in the project. One of the approaches I recently went through was using [YOLOV5](https://www.kaggle.com/code/marquis03/yolov5-high-throughput-algae-cell-detection) for this dataset (YOLOV5 links to the notebook mentioning the approach).
+
+## 🚀 Getting Started
+
+To get started with the project, follow these steps:
+
+1. Clone the repository:
+   ```bash
+   git clone https://github.com/abhisheks008/DL-Simplified.git
+   cd High Throughput Algae Cell Detection
+
+2. Install dependencies:
+    ```bash
+    pip install -r requirements.txt
+
+3. Download the dataset from Kaggle and place it in the Dataset/ directory (create if not exist).
+
+4. Run the notebooks for each model to train and evaluate the performance.
+
+## 📂 Directory Structure
+```plain
+- Dataset/
+  - DATASET.md
+  - labels.csv
+  
+- Images/
+  - NON_YOLO_RESULTS.png
+  - confusion_matrix.png
+  - labels.png
+  - P_curve.png
+  - PR_curve.png
+  - R_curve.png
+  - results.png
+  - val_batch2_pred.jpg
+
+- Models/
+  - results/..
+  - runs/detect/
+    - train
+    - train2
+  - Xception.ipynb
+  - ConvNeXtTiny.ipynb
+  - InceptionV3.ipynb
+  - YOLOv8n.ipynb
+  - yolo8n.pt
+
+- README.md
+- requirements.txt
+```
+
+## 📊 Visualization
+
+### Non YOLO Results
+![Non-YOLO Results](Images/NON_YOLO_RESULTS.png)
+
+### YOLOn Results
+![Results](Images/results.png)
+![Labels](Images/labels.jpg)
+![Precision Curve](Images/P_curve.png)
+![PR Curve](Images/PR_curve.png)
+![Recall Curve](Images/R_curve.png)
+![Confusion Matrix](Images/confusion_matrix.png)
+
+### Sample Images
+![Validation Batch 2 Predictions](Images/val_batch2_pred.jpg)
+
+## 📈 Accuracies
+**Xception Model:**
+  - Accuracy: 98.86%
+
+**Conv Model:**
+  - Accuracy: 98.92%
+
+**InceptionV3 Model:**
+  - Accuracy: 99.83%
+
+
+## 🚀 What I Had Done
+
+### Step-by-Step Procedure:
+
+1. **Data Preprocessing:**
+   - Loaded the dataset and performed necessary data cleaning steps.
+
+2. **Model Training:**
+   - Implemented and trained the selected models (Xception, ConvNeXtTiny, InceptionV3, YOLOv8n) on the preprocessed dataset.
+   - Tuned hyperparameters for optimal performance.
+
+3. **Evaluation:**
+   - Evaluated the models using appropriate metrics.
+   - Generated accuracy scores and confusion matrices.
+
+4. **Visualization:**
+   - Created visualizations of the non-YOLO results and other relevant insights.
+
+## 📚 Libraries Needed
+  - tensorflow
+  - matplotlib.pyplot
+  - numpy
+  - pandas
+  - pytorch
+  - sebornsplit-folders
+  - scikit-learn
+  - ultralytics
+  - Pillow
+  - opencv-python-headless
+
+## 📝 Conclusion
+
+The project utilized a diverse set of deep learning models to detect high throughput algae cells, each with impressive accuracy:
+
+- **Xception Model:** 98.86%
+- **Conv Model:** 98.92%
+- **InceptionV3 Model:** 99.83%
+
+In addition to the mentioned models, YOLOv8n was also explored, adding to the comprehensive comparison of methodologies.
+
+The chosen models were justified by their close parameters, making them suitable for a thorough evaluation. Previous experience with pre-trained CNN architectures and YOLOv8 base architectures influenced the selection process.
+
+The project's approach, encompassing Xception, ConvNeXtTiny, InceptionV3, and YOLOv8n, provides a robust foundation for algae cell detection using deep learning techniques.
+
+The remarkable accuracies achieved by the models indicate the success of the project in meeting its objectives. The exploration of various models allows for flexibility in choosing the most suitable approach based on specific project requirements and constraints.
+
+## 🧑‍💻 Your Name
+
+- Name: Arpit Sharma
+- GitHub: [ARPIT2128](https://github.com/ARPIT2128)  
+- LinkedIn: [Arpit Sharma](https://www.linkedin.com/in/arpit-sharma-b3a565222/)
\ No newline at end of file
diff --git a/High Throughput Algae Cell Detection/requirements.txt b/High Throughput Algae Cell Detection/requirements.txt
new file mode 100644
index 000000000..d0b3e97dd
--- /dev/null
+++ b/High Throughput Algae Cell Detection/requirements.txt	
@@ -0,0 +1,10 @@
+tensorflow
+matplotlib.pyplot
+numpy
+pandas
+pytorch
+sebornsplit-folders
+scikit-learn
+ultralytics
+Pillow
+opencv-python-headless
\ No newline at end of file