Rene-Twizerimana/Potato-Tomato-Disease-Detector2

This is the CNN deep learning model trained on pretrained datasets for Rwanda case and worldwide for identifying and mitigating the diseases that Potatoes and Tomatoes face --- Potato & Tomato Disease Detector This repository contains a Deep Learning model and a web application designed to identify common diseases in potato and tomato plants using leaf imagery. 🌿 Project Overview In many agricultural settings, early detection of plant diseases is critical for food security. This project provides an automated, accessible tool to help farmers and researchers diagnose plant health issues instantly. Model Type: Convolutional Neural Network (CNN). Target Crops: Potatoes and Tomatoes. Diseases Detected: Healthy, Early Blight, Late Blight, and Powdery Mildew. Accuracy: Approximately 83%. 🛠️ Technology Stack Framework: TensorFlow / Keras. Deployment Format: TensorFlow Lite (.tflite) for efficient performance. Web Interface: Gradio (app.py). Hosting: Hugging Face Spaces. File Structure app.py: The main application script that runs the Gradio interface. crop_model.tflite: The trained and optimized deep learning model. crop_classes.pkl: A pickle file containing the disease labels for classification. requirements.txt: Lists the Python libraries needed to run the project (e.g., gradio, tensorflow). How to Use Live Demo: You can try the live application on Hugging Face Spaces. Local Setup: Clone the repository. Install dependencies: pip install -r requirements.txt. Run the app: python app.py. License This project is licensed under the MIT License. Check out the configuration reference at huggingface.co