tensorflow / tensorflow/model-optimization

How to preform progressive quantization aware training using this framework?

Open
#525 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hi,
I would like to know how can I perform a progressive quantization aware training using this framework?

For example, if I have to training my model in the below order

  1. Training the model by quantizing the activation outputs
  2. Then following that, I have to training weights with various bit widths
    Can anyone please help me on how do I utilise this framework for that purpose?

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.

Research direction

Start by reviewing the framework's quantization-aware training entry points and documentation for activation and weight quantization. Determine whether the requested two-stage progressive sequence is supported, and document the supported procedure or its limitation with a concrete example.

Written by the indexing model from the issue text.

Assessment

Tech stack
keras, python, tensorflow
Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.