关于模型的泛化性能
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1k
- Forks
- 131
- PR merge metrics
- No merged PRs in 30d
Description
您好！ @hzwer
我尝试使用了4.25的训练代码从头训练模型，使用的是vimeo_septuplet+ATD12k+adobe240fps的训练集，验证集使用的是vimeo_septuplet的test_list.虽然指标和您在https://github.com/hzwer/ECCV2022-RIFE/issues/293 的类似，但是在验证集以外的场景上做推理效果却很差，远远比不上您发布的4.25预训练模型。
请问您是有其他的数据集，或者有别的训练方法提高了模型的泛化性能了吗？
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
Start by comparing the 4.25 training setup, including Vimeo Septuplet, ATD12k, Adobe240fps, and the Vimeo test_list, with the setup discussed in issue 293 and the published 4.25 model. Evaluate both the listed validation scenes and scenes outside that set. Done requires identifying a reproducible training or data difference that explains the generalization gap.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100