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

resnet20 architecture #14

Closed
blueardour opened this issue Jun 13, 2019 · 2 comments
Closed

resnet20 architecture #14

blueardour opened this issue Jun 13, 2019 · 2 comments

Comments

@blueardour
Copy link

Hi,

Thanks for sharing the code. I noticed that the resnet20 was employed in the CIFAR10 quantization. However, I didn't find the architecture. I ever saw two versions of resnet20. One is for small dataset such as CIFAR, another is for bigger dataset, such as imagenet. The difference is the width of the channel count. I wonder if it is possible for you to share detail definition of resnet20? Thanks

@blueardour blueardour changed the title resnet20 resnet20 architecture Jun 13, 2019
@EowinYe
Copy link
Collaborator

EowinYe commented Jun 15, 2019

Hi,
we did not release the architecture code for resnet-cifar. You can check tensorflow models or tensorpack resnet for references. You could simply modify the network architecture by replace the conv2d op with our conv2dquant op.

@blueardour
Copy link
Author

ok, thanks very much

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