tensorflow / tensorflow/model-optimization

Quantized wrapped layer non-trainable

Open
#527 1 comment 0 reactions 1 assignee View on GitHub

@Xhark is already working on this.

Since Apr 18, 2021.

feature request technique:qat
Dominant language
Python
Stars
1.6k
Forks
349
Avg merge
3d 2h
Merged PRs (30d)
1

Description

Hello all,

I am working on trying some logic on top of QAT where i will make few of the layers during QAT non-trainable based on some logic. I am currently seeing there is no such support in QAT (as of now Quantize Wrapper on top of a layer will ensure layer weights will be trainable during model training). I can see some layer trainable functions defined for Quantized wrapped layer in quantize_wrapper.py but this is not achieving the objective what i have mentioned above. Is there anyway i can achieve this.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.