## Evaluation Details

Your network will be evaluated on its ability to produce predictions on test data with a high level of Categorical Accuracy. This simple metric will compare the predictions your network makes on the provided test data to the ground truth values held within Kaggle.

The competition leaderboard will highlight the accuracy of your predictions, based on your selected submission. As mentioned on the Description page, the starter notebooks will automatically format your submissions as required. *If you somehow break or need to modify this functionality, see below for submission format requirements*.

Note that test data for the competition will not be initially available. This is to prevent students from overfitting to the test data through repeated modifications to their network, or outright training on test data. Once test data is released (~72 hours prior to the end of the competition), you will then be able to apply your trained model to it and generate predictions. As a final measure to prevent overfitting to test data, you will only be permitted to make up to 5 submissions per day, once test data is released. Upon submission, your accuracy score will be reflected on the Public leaderboard for all to see.

Private leaderboard information, which is derived from your performance on a subset of test data, will be used to determine the final winners, and will not be visible until the competition officially concludes. While your final position on the Private leaderboard is impossible to predict, good performance on the Public leaderboard is indicative of likely success on the Private.

## Leaderboard Submission Format

Leaderboard submission files are simple .csv files containing two named columns: Id and Category. The Id column simply corresponds to the indexes of your predictions, so there should be no repeated values. The Category column will contain your network predictions for retinal disease (values 0 - 3, inclusive).

The .csv file should contain a header and have the following format:

    Id,Category
    0,[some value from 0 to 3, inclusive]

Use the provided function in the starter notebook to generate predictions and submit them using the 'Submission' link on the top right of the Kaggle Competition page.

## Project Submission Instructions

Zip your jupyter notebook (.ipynb), final model (.pt), and final Kaggle submission (.csv) to a single compressed file and submit via Canvas NLT 8 2359 DEC 2023. You can save your final model as a .pt file by adding the following line to the end of your Jupyter notebook: ```torch.save(model.state_dict(), 'your_model_name.pt')```

## Grading

Your grade for this assignment will be based on the following factors, in decreasing order of importance:

- Quality of your code. The techniques you employed should be clear, well documented, and your results must be easily reproducible.
- Your ability to beat the baseline grade benchmarks on the Public Leaderboard.
- Your final position on the Private Leaderboard (this will only be used to assess bonus points).