Potato Blight Disease Prediction Model

Overview

This repository contains a TensorFlow Keras Convolutional Neural Network (CNN) model for predicting Potato Blight Disease. The model is trained to classify images of potato plants as either healthy or affected by blight disease.

Dataset

The dataset used for training and evaluation consists of images of potato plants collected from various sources. Each image is labeled as either "healthy" or "blight" to facilitate supervised learning.

Model Architecture

The CNN model architecture used for this task consists of multiple convolutional and pooling layers followed by fully connected layers. The architecture is designed to effectively capture spatial patterns and features in the input images.

Usage

Training

To train the model, use the provided script train.py. Make sure to specify the appropriate paths for the dataset and any desired hyperparameters.

bash Copy code python train.py --dataset_path /path/to/dataset --epochs 50 --batch_size 32 Evaluation You can evaluate the trained model using the evaluate.py script. This script computes accuracy metrics on a separate test dataset.

bash Copy code python evaluate.py --model_path /path/to/saved_model --test_dataset_path /path/to/test_dataset Inference To make predictions on new images using the trained model, utilize the predict.py script.

bash Copy code python predict.py --model_path /path/to/saved_model --image_path /path/to/image Pretrained Model

A pretrained version of the model is available for download here. You can use this model directly for inference or fine-tuning on your own dataset.

Results

The model achieves an accuracy of X% on the test dataset, demonstrating its effectiveness in predicting potato blight disease.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements

We would like to thank the contributors to the dataset used for training this model.