Zhongwei Qiu

code bug

1

in line 99: img_path = data_batch[0]['data_sample'].get('img_path') I find that data_batch is a dict, including #dict_keys(['inputs', 'data_samples']).

In your supply materials, you give the results on MuPoTS and 3dpw dataset. could you public the codes of evaluating BEV on 3dpw/human3.6 datasets?

testing problem

1

for the testing on crowdpose dataset, you use ground-truth bounding boxes?

about the position of cls token

2

Why the middle cls token is the best? if so, it seems that the cls token just captures the half tokens of sequence because the SSM is ordered while the...