modelscope / modelscope/DiffSynth-Studio
wan2.2-I2V-A14B模型如何从已微调的权重中恢复训练？
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
请问像wan2.2-I2V-A14B这种大型的模型，我训练了几个epoch之后，想要继续恢复训练要怎么做？我看到在推理验证的脚本中是需要加载训练好的权重：
state_dict = load_state_dict("models/train/Wan2.2-I2V-A14B_high_noise_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)
state_dict = load_state_dict("models/train/Wan2.2-I2V-A14B_low_noise_full/epoch-1.safetensors")
pipe.dit2.load_state_dict(state_dict)
那么需要我在恢复训练的时候，加载权重的时候也要load这个state_dict就可以了吗？
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
Review the inference validation script and the training entry point involved in loading the epoch-1 safetensors files. Determine whether loading both state_dict values restores training state or only model weights, then document the supported resume procedure and its completion criteria.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100