Optimized Deep learning Architecture for Tomato Leaf Disease Classification

One of the rapidly developing and trending sectors contributing towards the economic growth of any nation, is agriculture. There are various limitations and damage-causing factors in the process of cultivation including biological hazards, climatical changes, extreme weather conditions, and shortage of natural resources. This causes diseases in plants which can adversely impact the production of crops. These diseases may have similar appearances concerning color, shape, and texture. The categorization of tomato leaf diseases is done using an image collection that has been gathered and processed. This research explores the application of machine learning (ML) algorithms for the automated detection and diagnosis of tomato leaf diseases. The study focuses on ML and deep learning models for leaf disease. The model Convolutional Neural Networks (CNNs) is used to compare the efficiency and accuracy of the classification of image dataset of leaf disease. Selecting the model and implementing the different epochs (10, 30), and different optimizers (Adam, SGD, AdaGrad) calculating the accuracy and finding the best one.