Merge pull request #688 from Arihant-Bhandari/snake_classify

[Project Addition] Indian Venomous Snakes Classification using DL
abhisheks008 · Jun 2, 2024 · e7f9486 · e7f9486
2 parents 981f344 + e7522d8
commit e7f9486
Show file tree

Hide file tree

Showing 17 changed files with 123 additions and 0 deletions.
diff --git a/Indian Venomous Snakes Classification using DL/Dataset/README.md b/Indian Venomous Snakes Classification using DL/Dataset/README.md
@@ -0,0 +1,3 @@
+The link for the dataset used in this project:  https://www.kaggle.com/datasets/adityasharma01/snake-dataset-india
+
+The dataset consists of 2 subdirectories train and test. train again has 2 subdirectories named Venomous and Non Venomous with 1060 and 715 images respectively.
diff --git a/Indian Venomous Snakes Classification using DL/Images/CNN Accuracy.png b/Indian Venomous Snakes Classification using DL/Images/CNN Accuracy.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/CNN Loss.png b/Indian Venomous Snakes Classification using DL/Images/CNN Loss.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/EfficientNetB7 Accuracy.png b/Indian Venomous Snakes Classification using DL/Images/EfficientNetB7 Accuracy.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/EfficientNetB7 Loss.png b/Indian Venomous Snakes Classification using DL/Images/EfficientNetB7 Loss.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/InceptionV3 Accuracy.png b/Indian Venomous Snakes Classification using DL/Images/InceptionV3 Accuracy.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/InceptionV3 Loss.png b/Indian Venomous Snakes Classification using DL/Images/InceptionV3 Loss.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/NV1.png b/Indian Venomous Snakes Classification using DL/Images/NV1.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/NV2.png b/Indian Venomous Snakes Classification using DL/Images/NV2.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/RESNET50 Accuracy.png b/Indian Venomous Snakes Classification using DL/Images/RESNET50 Accuracy.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/RESNET50 Loss.png b/Indian Venomous Snakes Classification using DL/Images/RESNET50 Loss.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/VGG16 Accuracy.png b/Indian Venomous Snakes Classification using DL/Images/VGG16 Accuracy.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/VGG16 Loss.png b/Indian Venomous Snakes Classification using DL/Images/VGG16 Loss.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/ven1.png b/Indian Venomous Snakes Classification using DL/Images/ven1.png
diff --git a/Indian Venomous Snakes Classification using DL/Images/ven2.png b/Indian Venomous Snakes Classification using DL/Images/ven2.png
diff --git a/Indian Venomous Snakes Classification using DL/Model/snake-classification.ipynb b/Indian Venomous Snakes Classification using DL/Model/snake-classification.ipynb
diff --git a/Indian Venomous Snakes Classification using DL/README.md b/Indian Venomous Snakes Classification using DL/README.md
@@ -0,0 +1,119 @@
+## **Indian Venomous Snakes Classification using DL**
+
+### 🎯 **Goal**
+
+The objective of this project is to classify images of snakes as either venomous or non-venomous to identify dangerous snakes in Indian wildlife.
+
+### 🧵 **Dataset**
+
+The dataset consists of two subdirectories: train and test. Furthermore, the train directory has two subdirectories named Venomous and Non-Venomous with 1060 and 715 images, respectively.
+
+### 🧾 **Description**
+
+The project deals with binary classification, classifying images into the two classes: Venomous or Non-Venomous
+
+### 🧮 **What I had done!**
+
+To achieve our goals, the following steps were implemented:
+
+- Images were loaded using keras.utils and normalized to the range 0 to 1.
+
+- Images were resized to a fixed size of 224x224 pixels.
+
+- Custom and pre-trained models were used for this task.
+
+### 🚀 **Models Implemented**
+
+models used:
+
+- ResNet-50
+- Xception
+- VGG16
+- CNN-Keras
+- InceptionV3
+
+### 📚 **Libraries Needed**
+
+- Keras
+
+- Tensorflow
+
+- Numpy
+
+- Matplotlib
+
+### 📊 **Exploratory Data Analysis Results**
+
+
+- #### **Venomous**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/ven1.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/ven2.png" height="400px" width="400px" />
+</p>
+
+- #### **Non Venomous**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/NV1.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/NV2.png" height="400px" width="400px" />
+</p>
+
+- #### **CNN**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/CNN%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/CNN%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **InceptionV3**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/InceptionV3%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/InceptionV3%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **VGG16**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/VGG16%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/VGG16%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **EfficientNetB7**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/EfficientNetB7%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/EfficientNetB7%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **RESNET50**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/RESNET50%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/snake_classify/Indian%20Venomous%20Snakes%20Classification%20using%20DL/Images/RESNET50%20Loss.png" height="400px" width="400px" />
+</p>
+
+### 📈 **Performance of the Models based on the Accuracy Scores**
+
+#### Metrics: 
+
+We used Validation and Testing **Loss** and **Accuracy** as metrics.
+
+| Models | Accuracy | Loss |
+|--------|---------------------|--------------------------|
+| ResNet-50 | 65.17% | 0.6405 |
+| InceptionV3 | 86.89%  | 0.3523 | 
+| CNN | 74.44% | 0.5768 |
+| VGG16 | 75.28% | 0.5027 |
+| EfficientNetB7 | 60.67% | 0.6833 |
+
+### 📢 **Conclusion**
+
+We conclude the following:
+
+InceptionV3 and VGG16 work well on the dataset, while the custom CNN, being much lighter, falls just a bit short.
+
+### ✒️ **Your Signature**
+
+Original Contributor: Arihant Bhandari [https://github.com/Arihant-Bhandari]
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		The link for the dataset used in this project: https://www.kaggle.com/datasets/adityasharma01/snake-dataset-india

		The dataset consists of 2 subdirectories train and test. train again has 2 subdirectories named Venomous and Non Venomous with 1060 and 715 images respectively.