Yuhao Li
Yuhao Li
Dear Zelin, I compile DCN_v2 by using 'pip install -U torch==1.4 torchvision==0.5 -f https://download.pytorch.org/whl/cu101/torch_stable.html' as this url (https://github.com/CharlesShang/DCNv2/issues/63) said. And then I run 'bash configs/standard/v100_mot17_coco.sh',some errors accur like: `Traceback (most...
Hi,Zelin! I get some problems when I run the "sh configs/standard/v100_mot17_coco.sh " which remind me "ModuleNotFoundError: No module named 'MultiScaleDeformableAttention'". Then I find the answer at https://github.com/fundamentalvision/Deformable-DETR/issues/68. I change my...
Hi, do you use the linear interpolation when you compared your method with other SOTA methods as Tables 1 and 2 show? 
hi, I use the pre-trained models you released and follow the GET_STARTED.md to evaluate them on MOT17, MOT20, and dancetrack. However I can't get the performance as you said in...