Tomatoes (Solanum lycopersicum), which originated in South America, are now widely grown around the world. India is one of the largest producers and consumers of tomatoes. But also, this crop is widely affected by various diseases like bacterial spots, early blight, and late blight, which result in huge loss for cultivators. So early detection and preventive measures can have a good result in increasing the yield of tomatoes. In this study, we have proposed CNN (convolutional neural networks). A model involving image preprocessing and data augmentation by taking a dataset that comprises a total of 10000 images belonging to 10 different classes, which resulted in an overall 98.6% train accuracy and 97.78% test accuracy This study will be useful for the early detection of disease, making it user-friendly and cost-efficient for all farmers.