### How do I make a submission?

In this unique code competition, you are writing code in a Kaggle notebook that generates an `images.zip` file containing 7,000-10,000 images sized 256x256. To submit from a notebook, you should:

 1. Click on "New Notebook" from either the [Competition's Notebooks Page](https://www.kaggle.com/c/gan-getting-started/notebooks) or "Submit Predictions" flow.
 
 2. This will fire up a **Kaggle Notebook**, our cloud-hosted notebook/script platform. You must submit your code through this environment.

 3. The "Data" page and notebook environment will contain the recommended external dataset to use (Monet paintings and Photos). You are welcome to bring in your own external data to experiment with!

 4. Your notebook must run within the defined [Code Requirements](https://www.kaggle.com/c/gan-getting-started/overview/code-requirements) constraints.

 5. Your notebook's output file must be named `images.zip` and contain 7,000-10,000 images sized 256x256. Also refer to the [Evaluation](https://www.kaggle.com/c/gan-getting-started/overview/evaluation) page for details of how the submission is evaluated.

 6. **Commit** your kernel. Click "Save Version" on the Notebook and choose "Save & Run All (Commit)". It may take some time for the notebook 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 notebook's **Output** section while in notebook viewer mode.

 8. To submit, choose "Make A Submission" from the right navigation of your committed notebook *or* click "Submit" from the noteboook's "Output". If an Output has been generated but submission is not available, then your kernel has enabled some setting that is not permitted per the [Code Requirements](https://www.kaggle.com/c/gan-getting-started/overview/code-requirements) page.

 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 notebook. It will be running your `images.zip` file through the classifier that determines how well your generative images match the Monet style and serves as this competition's evaluation metric.

### What is a Getting Started competition? 

Getting Started competitions were created by Kaggle data scientists for people who have little to no machine learning background. They are a great place to begin if you are new to data science or just finished a MOOC and want to get involved in Kaggle.

Getting Started competitions are a non-competitive way to get familiar with Kaggle’s platform, learn basic machine learning concepts, and start meeting people in the community. They have no cash prize and are on a rolling timeline.

### What’s the difference between a private and public leaderboard?

In this competition, because it is a Getting Started competition, there is no difference. And we will refresh the competition every three months, so the Private Leaderboard is irrelevant.

For non-Getting Started Kaggle competitions, there is the concept of a public and private leaderboard to prevent participants from “overfitting” to the leaderboard. If your model is “overfit” to a dataset then it is not generalizable outside of the dataset you trained it on. This means that your model would have low accuracy on another sample of data taken from a similar dataset.

### How do I create and manage a team?

When you accept the competition rules, a team will be created for you. You can invite others to your team, accept a merger with another team, and update basic information like team name by going to the [Team page](https://www.kaggle.com/c/gan-getting-started/team).

We've heard from many Kagglers that teaming up is the best way to learn new skills AND have fun. If you don't have a teammate already, consider asking if anyone wants to team up in the [discussion forum](https://www.kaggle.com/c/gan-getting-started/discussion).

### What are Notebooks?

Kaggle Notebooks is a cloud computational environment that enables reproducible and collaborative analysis. Kernels supports scripts in R and Python, Jupyter Notebooks, and RMarkdown reports. Go to the [Notebooks tab](https://www.kaggle.com/c/gan-getting-started/notebooks) to view all of the publicly shared code on this competition. For more on how to use Notebooks to learn data science, visit Kaggle's [Learn Courses](https://www.kaggle.com/learn/overview).

### Why did my team disappear from the leaderboard?

To keep with the spirit of getting-started competitions, we have implemented a three month rolling window on submissions. Once a submission is more than three months old, it will be invalidated and no longer count towards the leaderboard.

If your team has no submissions in the previous three months, the team will also drop from the leaderboard. This will keep the leaderboard at a manageable size, freshen it up, and prevent newcomers from getting lost in a sea of abandoned scores.

*"I worked so hard to get that score! Give it back!"* Read more about our decision to implement rolling leaderboards, covered in the [Titanic Getting Started Competition forum here](https://www.kaggle.com/c/titanic/discussion/6240).

### How do I contact Support?

Kaggle does not have a dedicated support team so you’ll typically find that you receive a response more quickly by asking your question in the appropriate forum. (For this competition, you’ll want to use [this competition's discussion forum](https://www.kaggle.com/c/gan-getting-started/discussion).

Support is only able to help with issues that are being experienced by all participants. Before contacting support, please check the discussion forum for information on your problem. If you can’t find it, you can post your problem in the forum so a fellow participant or a Kaggle team member can provide help. The forums are full of useful information on the data, metric, and different approaches. We encourage you to use the forums often. If you share your knowledge, you'll find that others will share a lot in turn!

If your problem persists or it seems to be effective all participants then please [contact us](https://www.kaggle.com/contact).