MRzzm / DINet

The source code of "DINet: deformation inpainting network for realistic face visually dubbing on high resolution video."
999 stars 174 forks source link

讨论一下 DINet微调的问题 #102

Closed tailangjun closed 7 months ago

tailangjun commented 7 months ago

DINet要训练的模型有 5个:Syncnet、Frame64、Frame128、Frame256和Clip256。如果想在一组底模上微调,需要微调哪几个模型呢?

不知道我的理解对不对,欢迎大家一起讨论哈

There are 5 models to be trained by DINet: Syncnet, Frame64, Frame128, Frame256 and Clip256. If you want to fine-tune a set of base models, which models need to be fine-tuned?

I don’t know if my understanding is correct, everyone is welcome to discuss it together.

xiao-keeplearning commented 7 months ago

针对专用人物的要嘴部更像的话,微调时可以基于 Clip256预训练模型调Frame64,128,256,最后clip256,这是可行的

tailangjun commented 7 months ago

针对专用人物的要嘴部更像的话,微调时可以基于 Clip256预训练模型调Frame64,128,256,最后clip256,这是可行的

好的,谢谢大佬