zero is not none
zero is not none
> Sounds good to me. > > If you're interested there's also a not-that-difficult optimization that might lead to a 100x performance increase. Right now it is inefficiently O(n^2) in...
> I uploaded the checkpoint to Google Drive: > https://drive.google.com/file/d/1_xTqfk-cjouOEjZ3gkDyYwdq7mYeiAji/view?usp=sharing > But notice, the model requires huge amount of training. My checkpoint is of limited training, 7 days on 4...
大佬这里好像有点小bug， video_array = [img_as_float32(io.imread(os.path.join(args.driving, frames[idx]))) for idx in range(num_frames)] 这个应该是用来获取视频帧列表的吧，直接输入视频的话会报错
> Hi @nopeiyu, this is an interesting question. As we directly use Voxceleb2 for training, the quality of the generated results is similar to the training set. It possible if...
> For me, I just write a new dataset like original dataset. In this new dataset.py, there is only video list in the *.pkl. And it works for me. 你好可以分享一下如何处理数据集吗？我这边没明白到底应该如何去处理，谢谢啦
Thanks
> > hi ,thansks for your nice work! > > Would you tell how to preprocess the data (Extract landmark and crop the image by dlib)? > > I checked...
> > hi ,thansks for your nice work! > > Would you tell how to preprocess the data (Extract landmark and crop the image by dlib)? > > I checked...
Hi, I try to use custom dataset retrain AT net model, I found maybe the landmark is only use mouth area. Becasue all attention highlight area is in mouth area....
> > Hi, > > I try to use custom dataset retrain AT net model, I found maybe the landmark is only use mouth area. > > Becasue all attention...