ROCm / ROCm/AMDMIGraphX

Use different default tolerance for fp16 in ORT accuracy_checker script

Open
#2,318 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bugfix
Dominant language
C++
Stars
333
Forks
150
Avg merge
4d 19h
Merged PRs (30d)
54

Description

This issue has no description.

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

Start by locating the ORT accuracy_checker script and inspect how its default tolerance is selected for fp16 inputs. Confirm the intended fp16 tolerance with project context, then update or add coverage so the checker uses the different default and verify the accuracy-checking behavior.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning, testing-qa
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.