deepmodeling / deepmodeling/Uni-Mol
[BUG] the saved model only have parameters of classification head
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 181
- PR merge metrics
- No merged PRs in 30d
Description
### Describe the bug
training with task='regression',but the save model only has the parametrs of 'classification_head.out_proj.weight'
### Uni-Mol Version
unimolv1 and v2
### Expected behavior
the saved model should hace 'regression_head'
### To Reproduce
_No response_
### Environment
pyhton 3.10
### Additional Context
_No response_
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing training with task='regression' on Uni-Mol v1 or v2 using Python 3.10, then inspect the saved model parameters. Confirm whether the checkpoint contains only classification_head.out_proj.weight; done means a regression_head is saved for regression tasks.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100