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

[feature request] involution 3D #32

Open
baibaidj opened this issue Apr 9, 2021 · 2 comments
Open

[feature request] involution 3D #32

baibaidj opened this issue Apr 9, 2021 · 2 comments

Comments

@baibaidj
Copy link

baibaidj commented Apr 9, 2021

Hi. The work on involution is awesome and I'd like to try them on medical imaging that requires 3D operation.
I was wondering if you could spare some time to implement the 3D version fo involution_cuda?
I found the involution_naive could not be extended to 3D because the torch.fold and torch.unfold only support 4d tensor.
In previous issues, authors also mentioned that the naive version was slower and consumed more memory. I guess that the problem will be aggravated for 3D version.
Looking forward to trying this new ops. Thank you.

@ChristophReich1996
Copy link

@memmelma and I implemented a pure PyTorch version of a 3D Involution which you could try out. However, the native PyTorch implementation is kinda GPU memory hungry due to the unfold operation, which was also pointed out by the author in issue #1. Very awesome work by the way @d-li14!

@baibaidj
Copy link
Author

@memmelma and I implemented a pure PyTorch version of a 3D Involution which you could try out. However, the native PyTorch implementation is kinda GPU memory hungry due to the unfold operation, which was also pointed out by the author in issue #1. Very awesome work by the way @d-li14!

Wonderful work. I will try it.

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

2 participants