"YOU CAN FIND THE DATASET IN THE MASTER BRANCH" Plant disease identification by visual way is more laborious task and at the same time less accurate and can be done only in limited areas. Whereas if automatic detection technique is used it will take less efforts, less time and more accurately. In plants, some general diseases are brown and yellow spots, or early and late scorch, and other fungal, viral and bacterial diseases. The given Training code is made with the help of Convolutional neural network and for the training purpose, I've taken only tomato leaves for the classes Healthy and Disease the images which are used are of tomato plant. For better accuracy you may increase the epochs and dataset by adding more pictures of tomato plant in their respective classes according to it. Number of epochs and number of stages_per_epochs are set less to avoid overfitting of the model due to less no. images in training and validation dataset. In the test code I've used camera input for testing wheather the leaf is healthy or infected.