WeianMao

For the training code, we only checked the mbn v2 model, the model acc is lower than our paper. but we didn't checked other model, including resnet-50. maybe you can...

i fix the bug, please refer to this link https://github.com/modelscope/modelscope/issues/51 @guolinke @lhatsk

@lhatsk @guolinke i succuss yesterday, but failed today. it seems like the sever is unstable. is it possible to download the dataset from baidu drive? the issue exists too long.

the name of TFpose is modified into poseur. please move to the repo: https://github.com/aim-uofa/Poseur

the name of TFpose is modified into poseur. please move to the repo: https://github.com/aim-uofa/Poseur

we are still improving the performance of TFPose. once we finish this, we will release the code. thanks!

I'm on the commit:97d1abb2bca0b5daff6d434c4bb340d3bb702e86