Xu Qu
Xu Qu
yes, I submitted the results from your pretrained models and get the same numbers. My GPU has 24 GB, thanks to the limited memory, I tried two methods to fit...
Thanks for your reply, I'm sorry for the trouble I brought you with my unclear presentation.I will try the method you mentioned. All in all, Thank you!
> Cause you changed the batch size to 1. :) A different batch size means you must find new optimal learning rates and training epochs. What should I change the...
> Hey, thanks for your excellent work! I train TrackFormer on your default setting (load from pretrained CrowdHuaman checkpoint) on the joint set of CrowdHuman and MOT17, and i get...
Thanks for your early reply, should I set all the LRs (includes `lr, lr_backbone, lr_track, lr_linear_proj_mult` in` train.yaml`)to half? And the `weight_decay` should I change? Why does it appear different...
> Only the learning rates not the multiplicators (`lr_linear_proj_mult `). The weight decay can remain as it is. > > What appears different with different batch sizes? You mean why...
I get it! Thanks for your enthusiastic answer anyway!