Snake Breed Identification

Snake Breed Identification/README.md

@@ -0,0 +1,61 @@
+# <h1 align = "center"> Snake Breed Identification</h1>
+## Aim of the project: 
+### The project focuses on identification of different breeds of snakes using various Deep Learning Algorithms.
+
+###  Libraries and Frameworks used:
+1. Pandas
+2. Numpy 
+3. Matplotlib
+4. Seaborn
+5. Tensorflow
+6. Keras
+7. sklearn
+8. shutil
+9. pillow
+10. pickle
+
+
+## Deep Learning Algorithms used:
+1. Vgg16
+2. ResNet
+3. DenseNet
+
+## Accuracy and training time comparison of all the Deep Learning Algorithms
+|                |   Accuracy    |
+|----------------|---------------|
+|     Vgg16      |     22%       |
+|     ResNet     |     45%       |  
+|    DenseNet    |     50%       |     
+
+# Representation of breeds of snakes
+![EDA](https://github.com/the-silent-geek/DL-Simplified/blob/97358a7e149e84235180ddcc30f8a9d9f4462b77/Snake%20Breed%20Identification/images/snakes.png)
+
+# Counts of each species
+![values](https://github.com/the-silent-geek/DL-Simplified/blob/97358a7e149e84235180ddcc30f8a9d9f4462b77/Snake%20Breed%20Identification/images/value%20counts.png)
+
+# Random images from the dataset
+![ri](https://github.com/the-silent-geek/DL-Simplified/blob/28d3fb0417b830c98b821c12803e65e19a221f52/Snake%20Breed%20Identification/images/random%20images.png)
+
+# Random images belonging to a particular class from the csv file
+![ri2](https://github.com/the-silent-geek/DL-Simplified/blob/28d3fb0417b830c98b821c12803e65e19a221f52/Snake%20Breed%20Identification/images/random%20images%20from%20csv.png)
+
+# Orignal image vs grayscale image
+![ovsg](https://github.com/the-silent-geek/DL-Simplified/blob/28d3fb0417b830c98b821c12803e65e19a221f52/Snake%20Breed%20Identification/images/original%20vs%20grayscale.png)
+
+# Original vs Resized image(224*224 pixels)
+![ovri](https://github.com/the-silent-geek/DL-Simplified/blob/28d3fb0417b830c98b821c12803e65e19a221f52/Snake%20Breed%20Identification/images/original%20vs%20resized.png)
+
+
+# Accuracy plots of all models
+
+## Vgg16
+![vgg16](https://github.com/the-silent-geek/DL-Simplified/blob/97358a7e149e84235180ddcc30f8a9d9f4462b77/Snake%20Breed%20Identification/images/vgg16.png)
+
+## DenseNet
+![densenet](https://github.com/the-silent-geek/DL-Simplified/blob/97358a7e149e84235180ddcc30f8a9d9f4462b77/Snake%20Breed%20Identification/images/densenet.png)
+
+## ResNet
+![resnet](https://github.com/the-silent-geek/DL-Simplified/blob/97358a7e149e84235180ddcc30f8a9d9f4462b77/Snake%20Breed%20Identification/images/resnet.png)
+
+# Conclusion
+DenseNet201 model performs better comparative to other models used on the above dataset.

Snake Breed Identification/dataset/README.md

@@ -0,0 +1,12 @@
+# Dataset
+
+The dataset used in this project is take from the Kaggle website.
+<br>
+<b>Dataset Link:- https://www.kaggle.com/datasets/oossiiris/hackerearth-deep-learning-identify-the-snake-breed/data </b>
+<br>
+<br>The data folder consists of two folders and two .csv files. The details are as follows:
+<br>train: Contains 5508 images for 35 classes
+<br>test: Contains 2361 images
+<br>train.csv: 5508 x 2
+<br>test.csv: 2361 x 1
+<br>

Snake Breed Identification/requirements.txt

@@ -0,0 +1,10 @@
+Pandas
+Numpy 
+Matplotlib
+Seaborn
+Tensorflow
+Keras
+sklearn
+shutil
+pillow
+pickle