tensorflow / tensorflow/models

How to quantize the lstm object detection model

Open
#9,674 2 comments 0 reactions 3 assignees View on GitHub

Nobody has claimed this yet.

models:research:odapi type:support
Dominant language
Python
Stars
77.7k
Forks
44.8k
No merged PRs in 30d

Description

Hi, I have trained the lstm object detection, and deploy to mobile Huawei mate 20 pro. the inference runtime is 20 FPS, which is far below the paper result 72.3 FPS. I found the paper use Quantization Aware Training to optimize model. but the code of this part is missing. Any one knows how to revise the code to adopt QAT.
Thanks

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.