Nan loss
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 198
- Forks
- 21
- PR merge metrics
- No merged PRs in 30d
Description
I change the input resolution to 416*416 when I train custom datasets. When the network is trained for 49 epochs, the print loss is nan.What could be the reason for this?
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 training on the custom dataset at 416*416 and identify the epoch where the printed loss first becomes NaN. Inspect the training configuration and data inputs involved in that run; done means determining and documenting the cause, with a reproducible fix or clear diagnosis.
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
- 20/100