The dataset comprises labeled maize leaf images categorized into four classes: Blight, Common Rust, Gray Leaf Spot, and Healthy.

It includes train.csv, val.csv, and test.csv files. Each CSV contains ID (image filename), with label included in train and validation sets.

The training and validation images are stored in class-specific subdirectories, while the test set contains unlabeled images for prediction.

This structured format supports supervised learning, model validation, and final evaluation. All images are in .jpg or .JPG format, enabling deep learning pipelines to process disease features for accurate classification and diagnostic model development.