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

[quantizer] fix weight quant_min/quant_max specification failure when using tflite as backend #186

Open

zk1998 wants to merge 2 commits into main from pr/check_quant_minmax

Collaborator

zk1998 commented Feb 24, 2023

No description provided.


[quantizer] fix weight quant_min/quant_max specification failure when…

d487609

… using tflite as backend

Collaborator Author

zk1998 commented Feb 24, 2023

TFLite backend : Per-axis (aka per-channel in Conv ops) or per-tensor weights are represented by int8 two’s complement values in the range [-127, 127] with zero-point equal to 0.

The quant_min/quant_max of weight qconfig should be set by user‘s backend.


[tests] add win32 quantizer config

210900c

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