pytorch / pytorch/executorch

NXP backend: Update atol in `test_hardtanh_converter.py` tests

Open
#12,951 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

module: nxp
Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

This test suffers from non-ideal testing random quantization, because we always use range <0,1>. This should be updated (decrease atol) when we have custom calibration dataset definition in place.

cc @digantdesai @JakeStevens @robert-kalmar

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

Start in test_hardtanh_converter.py and inspect the NXP backend tests that use the current atol. Confirm whether the custom calibration dataset definition is available; once it is, update the test tolerance and run the affected tests to verify the new tolerance passes.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
testing-qa
Issue type
Refactor
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.