Hi, thanks for the great work!
I retrained the model twice using the same data and code on the DanceTrack val set. One run reproduces the pretrained results, while the other shows noticeable differences in IDF1 and IDs (see screenshot).
While checking the code, I noticed that the default seed is None, which makes training stochastic:
parser.add_argument("--seed", default=None, type=int, help="eval seed")
Could this be the reason for the variation?
If so, which seed was used to obtain the pretrained results?
Hi, thanks for the great work!
I retrained the model twice using the same data and code on the DanceTrack val set. One run reproduces the pretrained results, while the other shows noticeable differences in IDF1 and IDs (see screenshot).
While checking the code, I noticed that the default seed is
None, which makes training stochastic:Could this be the reason for the variation?
If so, which seed was used to obtain the pretrained results?