Shahan-Uz-Zaman/MediPlantClassify

# Medicinal Plant Detection Web App – Setup Guide This is a Flask-based web application that detects **20 species of medicinal plants** using a deep learning model trained with PyTorch. Users can upload a plant leaf image, and the app will identify the plant species and display detailed information in **English** or **Assamese**. --- ## 🌿 Project Features - Detects 20 medicinal plant species from leaf images - Displays plant information in English or Assamese - Supports image upload via web interface - Redirects to a fallback page for uncertain predictions --- ## 📁 Folder Structure ``` project_root/ ├── app.py # Main Flask application ├── model.pt # Trained PyTorch model ├── ass_plant_details/ # Assamese HTML info pages (0.html - 19.html) ├── classes/ # English HTML info pages (0.html - 19.html + unknown.html) ├── images/ # Optional images (e.g., icons, UI assets) ├── templates/ │ └── index.html # Upload form (image + language selector) └── uploads/ # Auto-created, stores uploaded images temporarily ``` --- ## ✅ Setup Instructions (Run Locally) ### 1. Extract the Project Unzip the project folder to a known location on your computer. --- ### 2. Open Terminal and Navigate to the Project ```bash cd path_to_project/Medicinal\ Plant\ Detction ``` --- ### 3. Create and Activate a Python Virtual Environment ```bash python -m venv venv ``` - **Windows:** ```bash venv\Scripts\activate ``` - **Linux/macOS:** ```bash source venv/bin/activate ``` --- ### 4. Install Required Dependencies ```bash pip install flask torch torchvision pillow beautifulsoup4 ``` --- ### 5. Verify Required Files and Pages Make sure these exist: - `model.pt` (your trained model) - `classes/0.html` to `classes/19.html` - `ass_plant_details/0.html` to `ass_plant_details/19.html` - `classes/unknown.html` — shown when model confidence is low - `templates/index.html` — the upload for …