This paper presents a deep learning algorithm for the diagnosis of eye diseases, which is taken from cats and dogs, using data augmentation. The database of eye images was collected from cell phone cameras, and with data augmentation techniques were used to increase the number of samples. The performance of the algorithms was evaluated on the original dataset of 146 diseased and 255 healthy images. The results showed that the VGG16 algorithm achieved a classification accuracy of 99.25% before data augmentation, which was significantly higher than the accuracy of existing methods. Furthermore, after the data augmentation again VGG16 model has significant performance metrics that are 99.9% than other algorithms. The proposed algorithm can be used to accurately diagnose various eye diseases, which can potentially improve the quality of care for patients.