For simplicity, the evaluation metric for this competition is root mean square error, or [RMSE](https://en.wikipedia.org/wiki/Root-mean-square_deviation). RMSE is a common regression metric that penalizes the deviance from ground truth for both overestimates and underestimates. For each of the ids in the test csv (which correspond to the images in the test folder), you must output a prediction for the number of human heads larger than 50px by 50px and not facing away from the viewer that are present in the image.

## Submission Format

**For every image in the test folder**, submission files should contain two columns: `Id` and `guess`. 

The file should contain a header and have the following format (see `sample_submission.csv` for a more in-depth example):
```
Id,guess
034abc,1
```