Abstract: Deep learning is the most widely used image recognition technology today, and it provides more insight into how computers can understand and learn from data. In deep learning, artificial neural networks analyze a large set of data to automatically detect patterns. In this article, well introduce some of these techniques to see how we can use deep learning to create our own model for diagnosing eye disease. When we talk about determining a diagnosis by medical imaging, we mean that we are going to explain some of the main areas of computer vision and how we can classify images data using convolutional neural net-works, one of most important idea is the evaluation of model performance using ensemble learning.