Skip to content

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

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
Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

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

wants to merge 2 commits into from

Conversation

@zk1998
Copy link
Collaborator

@zk1998 zk1998 commented Feb 24, 2023

No description provided.

@zk1998
Copy link
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.

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

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@zk1998