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

Do this work with the 'deformable convolution' as well? #115

Open
dheerajvarma24 opened this issue Sep 11, 2023 · 5 comments
Open

Do this work with the 'deformable convolution' as well? #115

dheerajvarma24 opened this issue Sep 11, 2023 · 5 comments
Labels
question Further information is requested

Comments

@dheerajvarma24
Copy link

If our model has a deformable convolution conv then can we still use this library?

@sovrasov
Copy link
Owner

That depends on implementation you're using

@sovrasov sovrasov added the question Further information is requested label Sep 12, 2023
@Koubunnkei
Copy link

I'd like to know the answer to that question as well. May I ask which implementation guarantees that complexity can be calculated using this library?

@dheerajvarma24
Copy link
Author

What worked for me is deepspeed's flops-profiler

@sovrasov
Copy link
Owner

I'd like to know the answer to that question as well. May I ask which implementation guarantees that complexity can be calculated using this library?

DeformConv2d from torchvision is supported

@pvti
Copy link

pvti commented May 13, 2024

What worked for me is deepspeed's flops-profiler

Thank you very much for your comment. I'm seeking a package that covers the torch.nn.functional.conv2d and found your comment. I tried deepspeed and it works like a charm.

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

No branches or pull requests

4 participants