This principal aim of this work is to leverage the potentials within deep learning, particularly utilizing Convolutional Neural Networks (CNNs), in order to automate the classification of plant diseases. The PlantVillage dataset is employed for training, validation, and testing purposes. The workflow encompasses data loading, exploration, and preprocessing, including the use of TensorFlow and Keras for building and training a CNN model. The model is designed to classify images into distinct plant disease categories, and the training process is visualized and evaluated using metrics such as accuracy and loss. Furthermore, data augmentation techniques are implemented to augment the dataset and improve the model’s robustness. The final trained model is saved for potential future use. The project provides insights into the application of deep learning in plant pathology for efficient disease diagnosis and monitoring.