zhanghang1989 / zhanghang1989/PyTorch-Encoding
Slow training and validation loss doesn’t decrease when using encoding.nn.SyncBatchNorm
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 448
- PR merge metrics
- No merged PRs in 30d
Description
Slow training and validation loss doesn’t decrease when using encoding.nn.SyncBatchNorm
Contributor guide
No contributing guide indexed for this repository
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
Start by reproducing the reported slow training and non-decreasing validation loss with encoding.nn.SyncBatchNorm, recording the training setup and observed behavior. Compare the SyncBatchNorm run with a baseline that does not use it, then document a confirmed cause or a reproducible failure case as the definition of done.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100