Haoyu Ma

> > Thanks a lot! > > Do you use the specific masks for image patche in training set? Besides, in your code, a pertained imagebert is used for initializing...

Same question. May I ask have you fixed it yet? Thanks!

Hi, thanks for your asking. Yes, you are correct. We will loss some limb structure in this setting, thus I think it may affect the pose module, but this is...

We evaluate our method on two datasets separately, i.e., we train it on the CMU hand and evaluate it on the CMU hand, and we train it on the Onehand10K...

> Thank you very much for your work. I have a problem: if **nn. MSELoss ()** is used as the loss function, and the Heatmap output from the network is...

> I used your trained model and ran the "inference.py" , > but the output is different from yours, > like this >  > what can I modify? >...

> > > just found the solution, in `inference.py` change to: > > > ``` > > > if __name__ == "__main__": > > > # *********************** Parameter *********************** >...

It should be 3+3, as in the [code](https://github.com/HowieMa/NSRMhand/blob/master/model/cpm_limb.py#L85) 

Sorry, but you may misunderstand the code. Please note that class Stage1 is just two 1x1 Conv layers, which follows [OpenPose](https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/models/hand/pose_deploy.prototxt) You can find that the output channels of stages...

Oops. It seems that our figure is incorrect. Thanks for pointing out this issue. the "Structure Stage 2" and "Structure Stage 3" should have the same structure as Statge t...