Merge pull request #695 from Arihant-Bhandari/tomato-leaf

[Project Addition] Tomato-Leaf Classification using DL
abhisheks008 · Jun 2, 2024 · f9591db · f9591db
2 parents 9c92700 + 68822e4
commit f9591db
Show file tree

Hide file tree

Showing 21 changed files with 146 additions and 0 deletions.
diff --git a/Tomato-Leaf Classification using DL/Dataset/README.md b/Tomato-Leaf Classification using DL/Dataset/README.md
@@ -0,0 +1,3 @@
+The link for the dataset used in this project:  https://www.kaggle.com/datasets/kaustubhb999/tomatoleaf
+
+The dataset consists of two subdirectories: train and val. Both train and val contain 10 subdirectories, each representing a category of leaf images. The train subdirectory contains 1000 images per category, while the val subdirectory contains 100 images per category.
diff --git a/Tomato-Leaf Classification using DL/Images/CNN Accuracy.png b/Tomato-Leaf Classification using DL/Images/CNN Accuracy.png
diff --git a/Tomato-Leaf Classification using DL/Images/CNN Loss.png b/Tomato-Leaf Classification using DL/Images/CNN Loss.png
diff --git a/Tomato-Leaf Classification using DL/Images/DenseNet121 Accuracy.png b/Tomato-Leaf Classification using DL/Images/DenseNet121 Accuracy.png
diff --git a/Tomato-Leaf Classification using DL/Images/DenseNet121 Loss.png b/Tomato-Leaf Classification using DL/Images/DenseNet121 Loss.png
diff --git a/Tomato-Leaf Classification using DL/Images/EDA-1.png b/Tomato-Leaf Classification using DL/Images/EDA-1.png
diff --git a/Tomato-Leaf Classification using DL/Images/EfficientNet Accuracy.png b/Tomato-Leaf Classification using DL/Images/EfficientNet Accuracy.png
diff --git a/Tomato-Leaf Classification using DL/Images/EfficientNet Loss.png b/Tomato-Leaf Classification using DL/Images/EfficientNet Loss.png
diff --git a/Tomato-Leaf Classification using DL/Images/Inception Accuracy.png b/Tomato-Leaf Classification using DL/Images/Inception Accuracy.png
diff --git a/Tomato-Leaf Classification using DL/Images/Inception Loss.png b/Tomato-Leaf Classification using DL/Images/Inception Loss.png
diff --git a/Tomato-Leaf Classification using DL/Images/RESNET50 Accuracy.png b/Tomato-Leaf Classification using DL/Images/RESNET50 Accuracy.png
diff --git a/Tomato-Leaf Classification using DL/Images/RESNET50 Loss.png b/Tomato-Leaf Classification using DL/Images/RESNET50 Loss.png
diff --git a/Tomato-Leaf Classification using DL/Images/VGG16 Accuracy.png b/Tomato-Leaf Classification using DL/Images/VGG16 Accuracy.png
diff --git a/Tomato-Leaf Classification using DL/Images/VGG16 loss.png b/Tomato-Leaf Classification using DL/Images/VGG16 loss.png
diff --git a/Tomato-Leaf Classification using DL/Images/Xception Accuracy.png b/Tomato-Leaf Classification using DL/Images/Xception Accuracy.png
diff --git a/Tomato-Leaf Classification using DL/Images/Xception Loss.png b/Tomato-Leaf Classification using DL/Images/Xception Loss.png
diff --git a/Tomato-Leaf Classification using DL/Images/diseased leaf.png b/Tomato-Leaf Classification using DL/Images/diseased leaf.png
diff --git a/Tomato-Leaf Classification using DL/Images/eda.png b/Tomato-Leaf Classification using DL/Images/eda.png
diff --git a/Tomato-Leaf Classification using DL/Images/healthy leaf.png b/Tomato-Leaf Classification using DL/Images/healthy leaf.png
diff --git a/Tomato-Leaf Classification using DL/Model/tomato-leaf.ipynb b/Tomato-Leaf Classification using DL/Model/tomato-leaf.ipynb
diff --git a/Tomato-Leaf Classification using DL/README.md b/Tomato-Leaf Classification using DL/README.md
@@ -0,0 +1,142 @@
+## **Tomato-Leaf Classification using DL**
+
+### 🎯 **Goal**
+
+The objective of this project is to classify images of Tomato leaves into 10 distinct categories based on type and level of illness as well as healthy.
+
+### 🧵 **Dataset**
+
+The dataset consists of two subdirectories: train and val. Both train and val contain 10 subdirectories, each representing a category of leaf images. The train subdirectory contains 1000 images per category, while the val subdirectory contains 100 images per category.
+
+### 🧾 **Description**
+
+The project deals with multi-class classification, classifying images into 10 classes.
+
+### 🧮 **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
+- DenseNet-121
+- EfficientNetB7
+
+### 📚 **Libraries Needed**
+
+- Keras
+
+- Tensorflow
+
+- Numpy
+
+- Matplotlib
+
+### 📊 **Exploratory Data Analysis Results**
+
+
+- #### **Exploratory Data Analysis**
+
+<img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/EDA-1.png">
+<img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/eda.png">
+
+<br>
+
+<p align="center">
+  <figure>
+    <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/healthy%20leaf.png" height="400px" width="400px" alt="healthy tomato leaf" />
+    <figcaption>Healthy Tomato Leaf</figcaption>
+  </figure>
+  <br>
+  <figure>
+    <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/diseased%20leaf.png" height="400px" width="400px" alt="diseased tomato leaf" />
+    <figcaption>Diseased Tomato Leaf</figcaption>
+  </figure>
+</p>
+
+- #### **CNN**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/CNN%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%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/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/Inception%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/Inception%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **VGG16**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/VGG16%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%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/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/EfficientNet%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/EfficientNet%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **RESNET50**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/RESNET50%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/RESNET50%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **DenseNet-121**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/DenseNet121%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/DenseNet121%20Loss.png" height="400px" width="400px" />
+</p>
+
+- #### **Xception**
+
+<p align="center">
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/Xception%20Accuracy.png" height="400px" width="400px" />
+  <img src="https://github.com/Arihant-Bhandari/DL-Simplified/blob/tomato-leaf/Tomato-Leaf%20Classification%20using%20DL/Images/Xception%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 | 10.00% | 14.5063 |
+| InceptionV3 | 84.30%  | 0.5310 | 
+| CNN | 98.00% | 0.0657 |
+| VGG16 | 92.70% | 0.2489 |
+| EfficientNetB7 | 10.00% | 2.3026 |
+| DenseNet-121 | 93.60% | 0.1880 |
+| Xception | 88.90% | 0.3858 |
+
+### 📢 **Conclusion**
+
+We conclude the following:
+
+Pre-trained models like **DenseNet-121** and **VGG16** worked well. **CNN** was the clear winner owing to its significantly higher accuracy and minimal loss as well as its minimal architecture.
+
+### ✒️ **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/kaustubhb999/tomatoleaf

		The dataset consists of two subdirectories: train and val. Both train and val contain 10 subdirectories, each representing a category of leaf images. The train subdirectory contains 1000 images per category, while the val subdirectory contains 100 images per category.