The evaluation page describes how submissions will be scored and how you should format your submissions. 

---

The evaluation metric for this competition is [Mean Squared Error](https://en.wikipedia.org/wiki/Mean_squared_error). The MSE score measures the average squared difference between the estimated values and the actual value. 


## Submission Format

You will make predictions for each scene in the test set, where only the input is provided. You will generate the prediction and submit your solution in a single csv file. In the solution file, each row starts with a ID of the scene, followed by 120 columns.  These 120 columns are the x and y coordinates for the future 60 time steps (6 seconds). The submission file has the following format.
```
# ID      v1   v2   v3  v4 ...
0_austin  x0   y0   x1  y1 ..
1_austin
```
The ID contains two parts. The prefix is the index in the input file, followed by the name of the city. You can also refer to the sample submission file as an example.