-
mouth_mask = list(range(94, 114)) + list(range(146, 178)) + list(range(183, 192))
upper_mask = [x for x in range(192) if x not in mouth_mask]
In the evalution of the code, I looked for how to calcul…
-
作者您好，我是中国科学技术大学的研究生，我想在我的工作中引用您的论文corrtalk并对结果进行比较，如果您不方便公开代码和checkpoint的话，可以将您生成的biwi以及vocaset的结果npy文件发给我吗？我保证仅用于学术研究且不会泄露。希望得到您的回复。
-
We want to ran the test.py of your code. And there are three dataset paths in the test.py, such as ‘Dataset/BIWI/face_dataset_large’.
In fact, I could not find these dataset there. So would you be ab…
-
The previous link didn't work, So I wrote to the author and she sent me a working link for vocaset.pth and biwi.pth
https://wormhole.app/8Lr4b#tS8QVcPTSSMt2NH1LogSGA
-
Hello,
First of all, thank you for this excellent work. I am very confused about annotations. In your paper, Table 1, there is "free from extra annotations". What does it mean? There are .mat files…
-
Hi, I trained the "BIWI" dataset according to your solution, but I found that the results are not as expected. the current loss does not decrease and the test set does not predict well,so I wonder if …
-
If you have the validation/test dataset output .
1. can you upload here
2. what is the max and the min value of the scale value for cauchy and laplace
-
Data Preparation
Place your vertices data (.npy files) and audio data (.wav files) in /vertices_npy and /wav folders, respectively.
Save the templates of all subjects to a templates.pkl file and…
-
Evaluation score between my retraining and CodeTalker paper is not the same.
The first stage model was reused and the second stage model was retrained, but the final score were inconsistent with th…
-
Hi,
Thanks for your nice work, I am wondering why the annotations are sampled differently than the original ETH?
For example, in ETH: your dataset contains annotations for frames (780, 790, 800.…