README.md

metadata

title: CDIApp
emoji: 🏆
colorFrom: red
colorTo: blue
sdk: gradio
sdk_version: 5.4.0
app_file: app.py
pinned: false
license: apache-2.0

Plant Disease Classification and Remedy System

This is a deep learning project for classifying plant diseases from images. It uses a convolutional neural network trained on a dataset of plant disease images.

A deep learning-based system that identifies plant diseases from images and provides remedies using AI.

Features

• 🌿 Identifies 38 different plant diseases across various crops
• 🔍 Uses advanced deep learning models for accurate disease detection
• 🤖 Integrates with Gemini AI for providing detailed remedies
• 🎯 Includes Out-of-Distribution detection for reliable predictions
• 🖥️ User-friendly Gradio web interface

System Requirements

• Python 3.8+
• CUDA-compatible GPU (optional, for faster inference)
• 4GB+ RAM

Installation

1. Clone the repository:

2. Install dependencies:

pip install -r requirements.txt

3. Set up environment variables: Create a .env file in the root directory and add:

GEMINI_API_KEY=your_gemini_api_key_here

Project Structure

├── acfg/               # Application configuration
├── ml/                 # Machine learning modules
│   ├── app/           # Core ML application code
│   └── input/         # Dataset directory
├── service/           # Backend service
└── static/           # Model checkpoints and static files

Usage

Running the Web Interface

python app.py

Access the interface at http://localhost:7860

Training Models

1. Train the classification model:

python train_classifier.py

2. Train the OOD detection model:

python train_ood.py

Model Architecture

• Classification: MobileNetV3 Small with custom MLP head
• OOD Detection: Custom Autoencoder architecture
• LLM Integration: Gemini 1.5 Flash for remedy generation

Dataset

The system is trained on a comprehensive dataset of plant disease images, covering:

• Multiple crop types (Apple, Corn, Tomato, etc.)
• Various disease conditions
• Healthy plant samples

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request