tensorflow / tensorflow/model-optimization
Tracking TFMOT 1.0.0 Release
Open
Nobody has claimed this yet.
technique:all
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 349
- Avg merge
- 3d 2h
- Merged PRs (30d)
- 1
Description
This issue tracks potential changes that would be made in a 1.0.0 release.
This should be quite far off at this point.
Pruning:
- see how pruning the kernel in DepthwiseConv2D influences converging accuracy. If not significant, prune by default. (prune_registry.py)
- use only tf.math.divide instead of tf.div for 1.XX (pruning_schedule.py > PolynomialDecay > call )
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
Review prune_registry.py and pruning_schedule.py, especially PolynomialDecay.call, and determine which release changes are still required. The issue names no tests or acceptance criteria, so completion would require a concrete 1.0.0 scope and verification plan.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning, release
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100