larq / larq/compute-engine

DoReFa quantizer with higher number of MACs/Ops, Grouped convs as custom ops on LCE 0.7.0

Open
#745 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
258
Forks
35
PR merge metrics
No merged PRs in 30d

Description

Hello, I have a couple of questions regarding quantizer options for Larq and LCE.

I am designing a BNN using the DoReFa quantizer, however, I noticed a very high number of estimated MACs and Ops when converting the model for ARM64. Changing the quantizer to "ste_sign" dramatically lowered the number of MACs and Ops.

I was wondering if there is a way to use the DoReFa quantizer for training without the serious overhead of operations when converting and running the model for inference in LCE? Is the "ste_sign" quantizer the only viable option for efficient inference?

Thank you for the excellent work and for your attention.

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

The issue names no file, test, or entry point to inspect. Start by clarifying whether this requests implementation of DoReFa inference support or an explanation of current quantizer behavior; the work is complete only when the supported approach and its inference impact are documented or an agreed implementation scope is defined.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, tensorflow
Domain
machine-learning, performance
Issue type
Feature
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.