Pest outbreaks have a significant impact on plants and crops, important to a reduction in national agricultural productivity. Conventionally, farmers and specialists rely on physical observation, and it can be timeconsuming, more expensive, and prone to errors, to classify diseases in plants. Though, by employing leading-edge image processing techniques, an instinctive detection system can be established, providing rapid and precise results. This paper aims to produce a Tomato Leaf Disease identification model with different categorizing leaf images and utilizing deep neural networks. The development of specific plant protection has the potential for substantial growth and improvement, with computer vision applications in the precision agriculture market also showing promising growth. This discussion about outlines all the critical stages for implementing the disease recognition model, initial from the image database group, assessment by agricultural specialists, and applying a deep learning framework to conduct the training of deep CNNs. By using this CNN, we will apply Max pooling layer, Multiple implementations are applied and finally we will get more accuracy.