Open yeliudev opened 1 year ago
Thank you for your interest in our work. Maybe check out here https://github.com/Jingkang50/OpenPSG/issues/33 for log reference. Some potential issues could be different configs (num_gpu and lr), and the loading of pretrained models.
Thanks for your reply. I've changed the base lr from 1e-3 to 1e-4 (the paper said PSGTR uses 1e-4, but the config of PSGFormer uses 1e-3, not sure whether it is correct), and the results became R@20: 0.1550; R@50: 0.1829; R@100: 0.1845
, which are still worse than the reported ones.
Comparing my training log and your uploaded ones, I notice that several losses and the HTriMatcher
are modified/removed in your released config. Do these modifications affect the performances?
Left: The released config
& Right: The uploaded training log
@Jingkang50 The 60 epochs
schedule can not reproduce the results as well. Could you please share the codebase used for obtaining the checkpoints? It seems that the code used for obtaining checkpoints and the current release one are different. Thanks!
The released codebase is just the one that we get the final score (as a few participants from PSG challenges was able to get the corresponding results).
Are you using the config here? It seems the loss weight aligned with the Left: The released config
. For the difference in the config, we delete/change the lines either because some losses are unused or they don't matter much.
Hi @Jingkang50, thanks for your great work. I ran a 12-epoch training for PSGFormer by modifying the config from
40/60 epochs
to8/12 epochs
, and settingeval_pan_rels=False
according to your suggestion. Below are the evaluation results at the 12th epoch, which are largely different from the 12th epoch results in Table 2 in your paper. May I know if there are any further modifications to reproduce the results? Thanks.