leap-stc / leap-stc/Integration_team
FTorch having issue with torch.nn.Sigmoid (possibly an edge case)
Open
Nobody has claimed this yet.
- Dominant language
- Fortran
- Stars
- 4
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
During implementation of my NN air-sea flux algorithm, I observed that the code would throw an floating point error, which was fixed by manually code a sigmoid function in place of the torch.nn.Sigmoid function.
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 floating-point error in the NN air-sea flux algorithm when using torch.nn.Sigmoid, then compare it with the manually coded sigmoid mentioned in the report. Done means identifying the cause and documenting or implementing a validated resolution, with a reproducible test or example if the project provides one.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- fortran, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100