Upload 6 files

README.md

@@ -0,0 +1,45 @@
+# Waste Classification Model
+
+This is a deep learning model for classifying waste images into two categories: Dry Waste and Wet Waste. The model is built using PyTorch and can be used for automated waste sorting systems.
+
+## Model Details
+
+- **Model Type**: Convolutional Neural Network (CNN)
+- **Input**: RGB images
+- **Output**: Binary classification (Dry Waste / Wet Waste)
+- **Framework**: PyTorch
+
+## Usage
+
+```python
+import torch
+from model import WasteClassifier
+
+# Load the model
+model = WasteClassifier()
+model.load_state_dict(torch.load('waste_classifier.pth'))
+model.eval()
+
+# Make predictions
+def predict(image):
+    with torch.no_grad():
+        output = model(image)
+        prediction = torch.argmax(output, dim=1)
+        return "Dry Waste" if prediction.item() == 0 else "Wet Waste"
+```
+
+## Requirements
+
+The model requires the following dependencies:
+- PyTorch
+- torchvision
+- PIL
+- numpy
+
+## Training
+
+The model was trained on a custom dataset of waste images. The training notebook (`training.ipynb`) contains the complete training pipeline and data preprocessing steps.
+
+## License
+
+This model is released under the MIT License. 

app.py

@@ -0,0 +1,86 @@
+import os
+import json
+import base64
+from datetime import datetime
+from flask import Flask, render_template, request, jsonify
+from werkzeug.utils import secure_filename
+from predict import predict_waste
+
+app = Flask(__name__)
+app.config['UPLOAD_FOLDER'] = 'uploads'
+app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024  # 16MB max file size
+app.config['HISTORY_FILE'] = 'prediction_history.json'
+
+# Ensure upload directory exists
+os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
+
+ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}
+
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+def load_history():
+    if os.path.exists(app.config['HISTORY_FILE']):
+        try:
+            with open(app.config['HISTORY_FILE'], 'r') as f:
+                return json.load(f)
+        except json.JSONDecodeError:
+            return []
+    return []
+
+def save_history(history):
+    with open(app.config['HISTORY_FILE'], 'w') as f:
+        json.dump(history, f)
+
+@app.route('/')
+def home():
+    history = load_history()
+    return render_template('index.html', history=history)
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    if 'file' not in request.files:
+        return jsonify({'error': 'No file uploaded'}), 400
+    
+    file = request.files['file']
+    if file.filename == '':
+        return jsonify({'error': 'No file selected'}), 400
+    
+    if file and allowed_file(file.filename):
+        filename = secure_filename(file.filename)
+        filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+        file.save(filepath)
+        
+        try:
+            # Read the file for history before prediction
+            with open(filepath, 'rb') as img_file:
+                img_data = base64.b64encode(img_file.read()).decode('utf-8')
+            
+            prediction = predict_waste(filepath)
+            
+            # Save to history
+            history = load_history()
+            history.append({
+                'timestamp': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
+                'prediction': prediction,
+                'image': img_data
+            })
+            # Keep only last 10 predictions
+            history = history[-10:]
+            save_history(history)
+            
+            # Clean up the uploaded file
+            os.remove(filepath)
+            return jsonify({'prediction': prediction})
+        except Exception as e:
+            return jsonify({'error': str(e)}), 500
+    
+    return jsonify({'error': 'Invalid file type'}), 400
+
+@app.route('/clear-history', methods=['POST'])
+def clear_history():
+    save_history([])
+    return jsonify({'success': True})
+
+if __name__ == '__main__':
+    app.run(debug=True) 

model.py

@@ -0,0 +1,22 @@
+import torch.nn as nn
+
+class WasteCNN(nn.Module):
+    def __init__(self):
+        super(WasteCNN, self).__init__()
+        self.conv_layer = nn.Sequential(
+            nn.Conv2d(3, 32, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2),
+            nn.Conv2d(32, 64, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2),
+            nn.Conv2d(64, 128, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2),
+        )
+        self.fc_layer = nn.Sequential(
+            nn.Flatten(),
+            nn.Linear(128 * 16 * 16, 128),
+            nn.ReLU(),
+            nn.Dropout(0.5),
+            nn.Linear(128, 2)  # 2 classes: dry/wet
+        )
+
+    def forward(self, x):
+        x = self.conv_layer(x)
+        x = self.fc_layer(x)
+        return x 

predict.py

@@ -0,0 +1,32 @@
+import torch
+from torchvision import transforms
+from PIL import Image
+from model import WasteCNN  # Import the model architecture
+
+def predict_waste(image_path):
+    # Load the model
+    model = WasteCNN()
+    model.load_state_dict(torch.load('waste_classifier.pth', map_location=torch.device('cpu')))
+    model.eval()
+
+    # Prepare the image
+    transform = transforms.Compose([
+        transforms.Resize((128, 128)),
+        transforms.ToTensor(),
+    ])
+    
+    image = Image.open(image_path).convert('RGB')
+    image = transform(image).unsqueeze(0)  # Add batch dimension
+
+    # Make prediction
+    with torch.no_grad():
+        output = model(image)
+        _, predicted = torch.max(output, 1)
+        
+    return "Dry Waste" if predicted.item() == 0 else "Wet Waste"
+
+if __name__ == "__main__":
+    # Example usage
+    image_path = input("Enter the path to your waste image: ")
+    result = predict_waste(image_path)
+    print(f"Prediction: {result}") 

requirements.txt

@@ -0,0 +1,10 @@
+torch>=1.9.0
+torchvision>=0.10.0
+pandas>=1.3.0
+Pillow>=8.3.1
+scikit-learn>=0.24.2
+matplotlib>=3.4.2
+# notebook>=6.4.0
+# ipykernel>=6.0.0
+flask>=2.0.0
+werkzeug>=2.0.0 

waste_classifier.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c17fd64e9b2681b18bc091832d9feba72864af4875aff84205c10f11fa155b
+size 17156086