Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

A PyTorch version #36

Open
bearpaw opened this issue Aug 17, 2017 · 5 comments
Open

A PyTorch version #36

bearpaw opened this issue Aug 17, 2017 · 5 comments

Comments

@bearpaw
Copy link

bearpaw commented Aug 17, 2017

Thanks for sharing your code!

I wrote a pytorch version of hourglass network. Hope this could be helpful for who are not familiar with Torch. Many codes for data processing are brought from your code (src/pypose). Thank the author again!

However, the code cannot reproduce the results perfectly (83.58 [email protected] score for the simplified 4-stack hourglass). Some details might be missed, especially the post processing part (e.g., coordinates mapping, etc). Anyone interested in this project is welcomed to contribute to this project!

@wangzheallen
Copy link

Do u have comparison experiments on using different number of hourglass?

@obwang49
Copy link

obwang49 commented Mar 2, 2018

I noticed in both lua and pytorch implementation, the residual modules structure is bn->relu->conv. But the resnet modules are conv->bn->relu. Is there any particular reason why you modify the sequence this way?

@obwang49
Copy link

obwang49 commented Mar 2, 2018

Okay, so actually, this repo's residual module is not the same as the demo residual module. I feel the final demo version makes more sense, since it is the same with resnet implementations.

@anewell
Copy link
Collaborator

anewell commented Mar 5, 2018

The change in the resnet module is based on this paper: https://arxiv.org/pdf/1603.05027.pdf which discusses the effects of switching between pre- and post-activation. Can't remember now if there was much difference when I changed the code.

@obwang49
Copy link

obwang49 commented Mar 5, 2018

Thanks for the note! I was wondering why resent in pytorch model zoo didn't adopt the bn->relu->conv which everybody else seems to be using.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants