benchopt / benchopt/benchmark_resnet_classif
Move to tensorflow/models implementation of ResNet
Open
- Dominant language
- Python
- Stars
- 12
- Forks
- 4
- PR merge metrics
- No merged PRs in 30d
Description
I think it should be much more flexible in order to align it with PyTorch, especially after [this PR](https://github.com/tensorflow/models/pull/10584) is merged.
Contributor guide
No contributing guide indexed for this repository
Research direction
Read tensorflow/models PR #10584 and inspect the benchmark's current ResNet implementation alongside its PyTorch implementation. First clarify which flexibility and alignment are required; done should mean the benchmark uses the intended tensorflow/models implementation and matches the agreed PyTorch behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch, tensorflow
- Domain
- machine-learning
- Issue type
- Refactor
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100