How are qparams (scale and zero_point) determined after fusing Conv and BN layers?
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 13.4k
- Forks
- 2.4k
- Avg merge
- 5d 3h
- Merged PRs (30d)
- 2
Description
During quantization (using pytorch_quantization), the qparams (scale and zero_point) of old Conv is computed using Calibrator. However, when the Conv and Batch Normalization (BN) layers are fused, the weights and biases of the fused Conv change. In this case, the original qparams may not be applicable anymore. Could you please explain how to correctly determine the new qparams (scale and zero_point) after this fusion?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No file, test, or entry point is identified. Start by tracing the pytorch_quantization calibration and Conv/BN fusion behavior described in the issue, then document how qparams should be determined after fusion. Done means a clear, project-supported explanation covering scale and zero_point.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100