google-research / google-research/sam
Something wrong before the second loss backward
Open
- Dominant language
- Python
- Stars
- 646
- Forks
- 81
- PR merge metrics
- No merged PRs in 30d
Description
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [64, 1]], which is output 0 of TBackward, is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!
Contributor guide
Assessment
This issue has not been assessed yet.