Plant disease recognition is very important to crops’ healthy growth. Deep learning is quickly becoming one of the most important tools for image classification. This technology is now beginning to be applied to the tasks of plant disease classification and recognition. In this chapter, transfer learning model (Alexnet, GoogLeNet, VGG16) was developed to perform tomato disease detection and diagnosis using simple leaves’ healthy and diseased images. Training of the models was performed with the use of an open database of 18,160 images, containing healthy and nine different diseases of tomato. Three model architectures were trained, with the best performance reaching a 97.98% success rate in identifying the tomato diseases using GoogLeNet network. To verify the general adaptability of the model, we use other eight plant images to test this model. The test accuracy of the network is above 95%. The approach of training transfer learning method on increasingly large and publicly available image datasets presents a clear path toward smartphone-assisted crop disease diagnosis on a massive global scale.