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.

Sign up for GitHub

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

Jump to bottom

question about insert BN before QAT #98

Open

zhaoxin111 opened this issue Aug 25, 2022 · 0 comments

zhaoxin111 commented Aug 25, 2022

In quantization，“We insert BN after the converted 3x3 conv layers because QAT with torch.quantization requires BN”.

I wonder why QAT must need BN after conv, if we don't have BN,just fuse_modules with conv, relu mode, Right?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment