请教作者大佬训练报错
Open
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
报错如下
这什么情况，怎么处理
感谢十分
我是听群里大佬说batch size调大可以更好的降LOSS
我调整到32不行16可以
Contributor guide
No contributing guide indexed for this repository
Research direction
The report mentions a training failure after changing batch size from 16 to 32 and includes a screenshot, but names no file, test, or entry point. Start by reading the screenshot and reproducing the training runs with batch sizes 16 and 32. Done would require identifying the reported failure and documenting or implementing a confirmed resolution.
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
- 12/100