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

About BatchNorm QAT 's problems #5704

Open

typhoonlee opened this issue Oct 30, 2023 · 0 comments

typhoonlee commented Oct 30, 2023 •

edited

Describe the bug:
when i use QAT_Quantizer() to qat my model，i got a wrap_model.pt，then i test with this model，encounter this bug：

Environment: linux

NNI version: version = '999.dev0'
Training service (local|remote|pai|aml|etc): remote
Python version: 3.7.10
PyTorch version: 1.12.0 + cu113
Cpu or cuda version: GPU version GeForce RTX 3090

Reproduce the problem

Code|Example:

and my model arch is :

How to reproduce:

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