Hello, thank you very much for your work sharing. I encountered a problem when running demo, as follows:
(ttk) lehom@lehom-Ubuntu:~/code/TransTrack-main$ python3 demo.py --video_input scene-0553.mp4 --demo_output output/ --resume crowdhuman_mothalf.pth --with_box_refine
Traceback (most recent call last):
File "demo.py", line 244, in <module>
main(args)
File "demo.py", line 178, in main
_, _ = model.load_state_dict(checkpoint['model'], strict=False)
File "/home/lehom/anaconda3/envs/ttk/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1223, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DeformableDETR:
size mismatch for query_embed.weight: copying a param with shape torch.Size([300, 512]) from checkpoint, the shape in current model is torch.Size([500, 512]).
Hello, thank you very much for your work sharing. I encountered a problem when running demo, as follows:
Would you have any idea?