Cricket Shots Detection

Cricket Shots Detection/README.md

@@ -0,0 +1,57 @@
+# <h1 align = "center"> Cricket Shots Detection</h1>
+## Aim of the project: 
+### The project focuses on classification of different cricket shots using various Deep Learning Algorithms.
+
+###  Libraries and Frameworks used:
+1. Pandas
+2. Numpy 
+3. Matplotlib
+4. Seaborn
+5. Tensorflow
+6. Keras
+7. sklearn
+8. glob
+9. OpenCV
+
+
+## Deep Learning Algorithms used:
+1. ResNet
+2. DenseNet
+3. InceptionNet
+4. EfficientNet
+
+## Accuracy and training time comparison of all the Deep Learning Algorithms
+|                    |   Accuracy    |
+|--------------------|---------------|
+|      ResNet        |     86%       |  
+|     DenseNet       |     92%       |
+|    InceptionNet    |     96%       |
+|    EfficientNet    |     95%       |     
+
+# Representation of different cricket shots
+![EDA](https://github.com/the-silent-geek/DL-Simplified/blob/2e8e0b207bd08e758fca8e93d5433c73f277ef1e/Cricket%20Shots%20Detection/images/eda_cric.png)
+
+# Bar plot of counts of each shot in the dataset 
+![values](https://github.com/the-silent-geek/DL-Simplified/blob/2e8e0b207bd08e758fca8e93d5433c73f277ef1e/Cricket%20Shots%20Detection/images/bar.png)
+
+# Pie chart for the distribution of shots in the dataset
+![ri](https://github.com/the-silent-geek/DL-Simplified/blob/2e8e0b207bd08e758fca8e93d5433c73f277ef1e/Cricket%20Shots%20Detection/images/pie%20chart.png)
+
+
+# Accuracy and plots of all models
+
+## InceptionNetV2
+![inv2](https://github.com/the-silent-geek/DL-Simplified/blob/2e8e0b207bd08e758fca8e93d5433c73f277ef1e/Cricket%20Shots%20Detection/images/inception.png)
+
+## DenseNet
+![densenet](https://github.com/the-silent-geek/DL-Simplified/blob/2e8e0b207bd08e758fca8e93d5433c73f277ef1e/Cricket%20Shots%20Detection/images/dense.png)
+
+## ResNet50
+![resnet](https://github.com/the-silent-geek/DL-Simplified/blob/2e8e0b207bd08e758fca8e93d5433c73f277ef1e/Cricket%20Shots%20Detection/images/resnet.png)
+
+## EfficientNet
+![effnet](https://github.com/the-silent-geek/DL-Simplified/blob/2e8e0b207bd08e758fca8e93d5433c73f277ef1e/Cricket%20Shots%20Detection/images/efficient.png)
+
+
+# Conclusion
+InceptionNet model performs better comparative to other models used on the above dataset.

Cricket Shots Detection/dataset/README.md

@@ -0,0 +1,19 @@
+# Dataset
+
+The dataset used in this project is take from the Kaggle website.
+<br>
+<b>Dataset Link:- https://www.kaggle.com/datasets/aneesh10/cricket-shot-dataset</b>
+<br>
+
+<br>
+1. The directory drives consists of the cover drive, straight drive and off drive.
+<br>
+2. The directory legglance-flick contains the images for the leg glance and flick shot.
+<br>
+3. The directory pullshot has the images for pull shot.
+<br>
+4. The directory sweep has the image for sweep shot.
+<br>
+
+
+

Cricket Shots Detection/requirements.txt

@@ -0,0 +1,9 @@
+pandas
+numpy
+matplotlib
+glob
+tensorflow
+opencv
+scikit-learn
+seaborn
+glob