lightly-ai / lightly-ai/lightly-train

Custom distillation model using DinoVol3 does not achieve the required accuracy after int8 quantization

Open
#500 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.7k
Forks
116
Avg merge
2d 21h
Merged PRs (30d)
6

Description

I customized my own model according to the tutorial and trained it using distillation with dinov3/vits16 as the teacher. However, after exporting the model as ONNX and performing int8 quantization, the model accuracy dropped significantly.
This issue does not occur with models that have not undergone distillation.

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

No source file or test is named. Start by reproducing the tutorial's custom distillation flow with dinov3/vits16, then compare accuracy before and after ONNX export and int8 quantization. Done means identifying why the distilled model loses accuracy or documenting a verified fix with a regression check.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.