The dataset for this project contains 109,309 retinal optical coherence tomography images. The dataset is divided into training, validation, and test sets as follows:

- Training: 97,477
- Validation: 10,832
- Testing (not yet posted): 1000

All images are in grayscale with dimensions of 28 x 28 pixels. Labels for each image are provided in separate files. These labels pertain to one of four classes (0 - Choroidal Neovascularization, 1 - Diabetic Macular Edema, 2 - Drusen, 3 - Normal). All dataset files are numpy binaries (.npy). Thus, they cannot be easily viewed outside of a python program, but are extremely easy and fast to import otherwise. The code required to import them can be found in the starter notebook.

Review the starter notebook early and ask questions often. The cells where you are meant to provide your own code are clearly delineated, though you can freely modify the rest of the notebook at your own risk. **Code examples we review in class will be very helpful for filling out the starter notebook.**