Problems with the MOT17 dataset when testing

[zhoutianxiang-coder]

When I ran track.py to test the MOT17 dataset, I found that it was just testing the data in the train. What can I do to test the test dataset in MOT17

[timmeinhardt]

The default setting in track.yaml is to run MOT17 train and test for all three sets of public detections MOT17-ALL-ALL.

But you will only see metric evaluations for train cause the ground truth for test is not published. You have to take the prediction files and submit them to the MOTChaellenge evaluation server.