There was a bug when I continued to train the model. RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #4 'other'
Open
- Dominant language
- Python
- Stars
- 969
- Forks
- 220
- PR merge metrics
- No merged PRs in 30d
Description
when i try to resume to train the model ：
RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #4 'other'
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing the resume-training flow described in the issue and trace where CPU and CUDA tensors are combined. Done means continuing training no longer raises the reported FloatTensor versus cuda.FloatTensor RuntimeError.
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