Maskrcnn num_image_candidates compliance
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 43
- Forks
- 60
- Avg merge
- 19h 56m
- Merged PRs (30d)
- 3
Description
training rule described in https://github.com/mlcommons/training_policies/blob/master/training_rules.adoc#91-hyperparameters require num_image_candidates to be (1000 or 2000) or (1000 * batches per chip).
Current check only looks for multiple of 1000: https://github.com/mlcommons/logging/blob/master/mlperf_logging/compliance_checker/training_2.0.0/closed_maskrcnn.yaml#L64
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
Compare the rule in training_rules.adoc section 9.1 with the check at line 64 of training_2.0.0/closed_maskrcnn.yaml. Confirm that the compliance check accepts only the listed num_image_candidates forms and rejects other multiples of 1000; completion means the checker matches the policy.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, testing-qa
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 48/100