Talking-Face-Generation-DAVS

Talking-Face-Generation-DAVS copied to clipboard

checkpoint

2

I can not download the model checkpoint. How can I deal with the problem.

chenshi3

result file

2

I got two kinds of photos as result: test_sample1_fake_audio_B_0_x.png and test_sample1_real_A_x.png. what do they mean? And how to use them to get the final video?

TahoeWang

Non-human Characters

1

您好，请问卡通人物的唇音是怎么合成视频的，业需要添加额外的数据训练吗？

birdflies

No change

5

I run the following command: "python test_all.py --test_root ./0572_0019_0003/audio --test_type audio --test_audio_video_length 98 --test_resume_path ./101_DAVS_checkpoint.pth.tar" But in the end, the pictures generated in the "results" folder are exactly the same...

178581399

Hi, Why you use Variable(self.lip_embedding_norm.data) instead of direct use self.lip_embedding_norm here? And why denominator is 2*batch_size instead of batch_size^2?  

Pixie8888

I downloaded pretrain checkpoint from the link: https://drive.google.com/file/d/1UW22xm4r9AewNoySyPd2fyUab0nqymBR/view. But when I tried to extract it, it report the following error: tar: This does not look like a tar archive tar:...

la0216

About preprocess

3

Thanks for your sharing! There was a problem when I was reading the code. Do you need to generate "young / val_filenames. txt", "lrw_.txt", “_mouth.txt”, and "_filenames.txt" before you running...

lzkzls

大家好，想跟大家请教一下关于mouth.txt 的数据处理过程，mouth.txt 的数据分别表示什么，多少维度的，我没有下载作者使用的数据集，我想使用新闻主持人的数据，但是我不知道如果生成mouth.txt 文件。如果有人处理处mouth.txt的数据，希望能告诉我mouth.txt的数据是多少维度的 分别表示什么意思，谢谢@liuziwei7 @liuyuisanai @Hangz-nju-cuhk

love112358

:100:

coralexbadea

Thank you for your questions and solutions for your great help. Now, I have successfully got test_all (video and audio) output result, the question now is how to combine the...

love112358