Megvii-BaseDetection / Megvii-BaseDetection/YOLOX

poor accuracy after tensorrt int8 calibration

Open
#641 0 comments 3 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
10.6k
Forks
2.5k
PR merge metrics
No merged PRs in 30d

Description

When I calibrate with tensorrt int8, the accuracy is equivalent to 50% reduction of fp16.Has anyone ever encountered this situation

Contributor guide

No contributing guide indexed for this repository

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

No files, model, calibration dataset, command, or reproduction steps are provided. Start by documenting the TensorRT INT8 calibration invocation and comparing it with the FP16 baseline; done means a reproducible case with environment details and a confirmed accuracy regression or clarified calibration issue.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.