tensorflow / tensorflow/model-optimization

Disable quantization range during training

Open
#777 1 comment 0 reactions 1 assignee View on GitHub

@Xhark is already working on this.

Since Aug 9, 2021.

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

Description

Hi,

As the paper (https://arxiv.org/pdf/1712.05877.pdf) refereed by Tensforflow states:

"we found it useful to completely disable activation quantization at the start of training (say, for 50 thousand to 2 million steps). This allows the network to enter a more stable state where activation quantization ranges do not exclude a significant fraction of values."

I would like to disable activation during the first iterations, Is there a way to do it in Tensorflow?

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.