> **Important Warning**: This competition has an experimental format and submission style (images as submission). Competitors **must** use generative methods to create their submission images and are not permitted to make submissions that include any images already classified as dogs or altered versions of such images. 

> To enforce and prevent cheating, we reserve the right to: (a) Visually inspect all participants' submitted images, (b) review any submitted source code, (c) use these reviews to identify violators or determine winners, and (d) disqualify participants from the competition who are found in violation. This is also specified in the [competition's rules](https://www.kaggle.com/c/generative-dog-images/overview)





### How to Make a Submission

 1. Click on "New Kernel" from either the Kernels Page or "Submit Predictions" flow.
 
 2. This will fire up a **Kaggle kernel**, our cloud-hosted notebook/script platform. You must submit your code through this environment.

 3. The "Data" page and Kernels environment will contain the eligible external dataset to use (Stanford Dogs Dataset). No other external data can be introduced.

 4. Your kernel must run within the defined [Kernels Requirements](https://www.kaggle.com/c/generative-dog-images/overview/kernels-requirements) constraints.

 5. Your kernel's output file must be named `images.zip` and contain 10,000 64x64 images. Also refer to the [Evaluation](https://www.kaggle.com/c/generative-dog-images/overview/evaluation) page for details of how the submission is evaluated.

 6. **Commit** your kernel. It may take some time for the kernel to run, but you can close the browser while it runs and return to it later.

 7. If the Commit is successful and your code has generated an `images.zip` file, it will be shown in the kernel's **Output** tab.

 8. On the **Output** tab, click "Submit to Competition." If an Output has been generated but the button is not available, then your kernel has enabled some setting that is not permitted (i.e. external data sources, custom docker images, internet access). View the [Kernels Requirements](https://www.kaggle.com/c/generative-dog-images/overview/kernels-requirements) page for the detailed constraints.

 9. Your submission may take some time to process. Once it kicks off, you can close your browser and return to see your standing on the Public Leaderboard when it finishes! The submission will not re-run your original kernel. It will be running your `images.zip` file synchronously through both the public and private metrics.

 10. The Private Leaderboard is revealed at the end of the competition. At this time, you will see final scores calculated against the private metric. You can expect these scores to be intentionally different. Details can be reviewed on the [Evaluation page](https://www.kaggle.com/c/generative-dog-images/overview/evaluation).

### More Resources
 - Check out the [starter submission kernel](https://www.kaggle.com/wendykan/gan-dogs-starter) Wendy published for of this competition. This is a basic DCGAN submission generating the necessary `images.zip` output format.

 - If you're curious about how the public leaderboard version of the metric is calculated, Wendy has also created a [kernel demo of the public metric](https://www.kaggle.com/wendykan/demo-mifid-metric-for-dog-image-generation-comp).