Yihong Xu
Dear all, I also had the 'out of memory' problem. My problem is that the volatile flag for tensors is now deprecated (torch>=0.4). So the network keeps gradient while doing...
Hi, try to add `torch.set_grad_enabled(False)` inside test_oneimage() function (at the beginning of the function) if your torch version is >= 0.4. It works for me.
Hi, Thank you so much for your open source code which is really rare in MOT community. However I ran into the same issue as @SpyderXu , I used the...
Did you try to submit your results for MOT challenge. If so, could you indicate please the name of your method from the ranking board of MOT17 ?
> I trained model again with Pytorch=0.4.1, then I got the adaptation result from Market to Duke, as 53.3/72.4(mAP/R1), it's almost the same with the results reported in the paper....
Hi, Would you mind telling me which parameters did you use for getting Mean AP: 54.3% and top1: 77.3% (best) ? And which version of pytorch did you use? You...
> The parameters are the same as described in the code, I use pytorch=0.4.1 with two gpus. Hi thanks for your reply. I'll go try pytorch=0.4.1, torchvision=0.2.0, and as the...
Hi, Thanks for your comment. No, we don't use any motion model. The motion hyperparameters are inherited from the code of Tracktor and it is not used in this work.
Hi, The models for testset submission are trained on full MOT 17/20 dataset while the models for validation are trained with first 50% of the train set and validated on...
Hi, You can go to the branch oldTransCenter for the previous version.