Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

微调模型可以用动作文本描述来控制人物的手部动作吗? #487

Open
281LinChenjian opened this issue Oct 19, 2024 · 2 comments

Comments

@281LinChenjian
Copy link

如果对v1.3.0的模型进行一些微调实验,理论上,我可以以精确的手部动作的文本描述来驱动手部吗,是不是对于现有的预训练文本编码器模型来说太难了?

@LinB203
Copy link
Member

LinB203 commented Oct 20, 2024

我认为主要问题还是在于模型参数不够大。当然文本编码器也有点影响。

@281LinChenjian
Copy link
Author

主要问题还是在于模型参数不够大。当然文本编码器也有点影响。

感觉预训练的MT5或者CLIP模型在这种特定语料的任务上表现效果应该不好,除非把文本编码器重新训练一下。
如果想尝试一下用500个5-10秒左右的视频用两张A100微调的话,大概需要多久会有一个初步的效果呢?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants