TingsongYu / TingsongYu/PyTorch_Tutorial
建议
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
在_viewer/_visual_weights 中，不需要重写Net再加载net_params.pkl的state_dict啊，直接
pre_trained_dict = torch.load('../2_model/net_params.pkl')
就已经得到想要的state_dict了。
建议删除冗余的部分
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 in _viewer/_visual_weights and inspect how net_params.pkl is loaded. Remove the redundant Net reconstruction and use the state dictionary returned by torch.load('../2_model/net_params.pkl'); done when the viewer still loads the model parameters correctly without the extra step.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Refactor
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 55/100