developed to predict different plants diseases based on their images. Transfer learning using VGG16 with CNN used to build the model with 90% accuracy. This dataset consists of about 9K rgb images of healthy and diseased crop leaves which is categorized into 18 different classes. The total dataset is divided into 80/20 ratio of training and validation set preserving the directory structure. A new directory containing 30 test images is created later for prediction purpose.