Tomatoes, globally cherished and pivotal to diverse cuisines, face substantial threats to their quality and quantity due to various diseases. This research paper applies a deep learning approach for the precise detection of tomato leaf diseases. Our methodology incorporates a range of classifiers, including Random Forest (R.F), Inception V3, DenseNet, ResNet50, Xception, and MobileNet. Our results showcase the proficiency of these classifiers in distinguishing among nine distinct disease classes and one healthy class. Random Forest classifier exhibits an accuracy of 68.00%. Inception V3 excels with an impressive accuracy of 97%, coupled with high precision (98%), recall (96%), and an overall F1-Score of 97.50%. DenseNet demonstrates robust performance with an accuracy of 94.00%, precision of 98%, recall of 89%, and an F1-Score of 93%. ResNet50 closely follows with an accuracy of 93.30%, precision of 97%, recall of 91%, and an F1-Score of 94%. Xception maintains a well-balanced performance, achieving an accuracy of 95%, precision of 93%, recall of 99%, and F1-Score of 96%. Lastly, MobileNet, while achieving a moderate accuracy of 76%, demonstrates precision, recall, and F1-Score of 66%, 90%, and 76%, respectively. These experimental findings not only underscore the varied performance of each classifier concerning different disease classes but also emphasize the significant potential of deep learning to enhance the accuracy and efficiency of tomato leaf disease detection. This contribution supports ongoing endeavors to improve crop yield and quality through the application of advanced machine learning techniques in agriculture.