The fastest growing cause of blindness is diabetic retinopathy or DR. The purpose of this report was to develop a machine learning model to classify images of eyes according to the degree of diabetic retinopathy. The vision problems caused by this disease are due to high blood sugar causing damage to blood vessels in the retina. Therefore, there are five stages of DR that we attempted to classify including: no disease, mild non-proliferative, moderate non-proliferative, severe non-proliferative, and proliferative. The first model was a convolutional neural network. After building our own network and utilizing transfer learning the best accuracy on the test set was of 0.7166. The second model was a support vector machine which achieved a smaller accuracy of 0.633. The performance of these models does not reach the goal of 98% accuracy but we think it would be difficult to achieve that with this data set. In future projects, we suggest utilizing a data set with more images for each of the stages of the disease. Otherwise, building binary classification models instead of multi-class classification would probably yield better results.