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

How to use CKConv and FlexConv to replace standard convolution #9

Open
CV-ZhangXin opened this issue May 13, 2024 · 2 comments
Open

Comments

@CV-ZhangXin
Copy link

No description provided.

@CV-ZhangXin
Copy link
Author

Dear Mr. @dwromero
Thank you for your outstanding work.
Recently, I want to use the CKConv and FlexConv to replace the 3×3 convolution operation in YOLOv8. In this case, how to set the corresponding hyperparameters in CKConv and Flexconv. Looking forward to your reply.

@CV-ZhangXin CV-ZhangXin changed the title How to use CKConv How to use CKConv and FlexConv to replace standard convolution May 13, 2024
@dwromero
Copy link
Collaborator

Hi Zhang Xin,

apologies for my late response. I can quickly create an "standalone" convolutional neural network, e.g., ResNet-18, where I replace all convolutions with CKConv / FlexConv. Would that be useful? :)

In the meantime, you can also look at our demo:
https://github.com/rjbruin/flexconv/blob/master/demo/flexconv.ipynb

Please let me know if this would help and I will get to it ASAP.

David

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