#### scoring functions
There are two evaluation metrics for the challenge:
**p10 accuracy** and **mean euclidean distances**.

The p10 accuracy is defined as the percentage of the predictions that are within 10 pixels of the ground truths (in the downsampled 80x60 spatial space). The mean Euclidean distance is defined as the average Euclidean distance between the predictions and the ground truths. 


## Submission File
Please reference the test.py to load your model checkpoint and generate the submission csv file. The file should contain a header (already included in the script) and have the following format:

    x, y
    35.20940399169922,22.15359878540039
    34.5449104309082,25.2341251373291
    40.37540817260742,21.507827758789062
    37.30218505859375,23.70339012145996
    etc.