Hangz-nju-cuhk / Talking-Face-Generation-DAVS

Code for Talking Face Generation by Adversarially Disentangled Audio-Visual Representation (AAAI 2019)

Hangz-nju-cuhk/Talking-Face-Generation-DAVS Issues

No change
Updated a year ago5
During the reproduction process, No module named 'lws'
Updated a year ago
checkpoint
Updated 3 years ago2
result file
Updated 3 years ago2
Non-human Characters
Updated 3 years ago1
question about computing contrastive loss
Updated 3 years ago
pretrain checkpoing tarball looks like not one tar file
Updated 3 years ago
Solution for ValueError: expected 2D or 3D input (got 4D input)
Closed 3 years ago
About preprocess
Updated 4 years ago3
请教一下关于mouth.txt数据的处理过程
Updated 4 years ago
How can I conviently convert audio files into .bin files
Updated 4 years ago
How to turn the output result of test_all into a video (image + audio) form
Updated 4 years ago
ValueError: expected 2D or 3D input (got 4D input)
Updated 4 years ago10
face_align
Updated 4 years ago1
Error in loading Checkpoint file : Missing keys error
Updated 4 years ago6
Problem with run model on CPU
Updated 4 years ago
May I ask about post processing detail?
Updated 4 years ago1
can I add new images into the demo_images folder for testing
Closed 5 years ago4
Chinese characters are spoken faster than English words, will this model work on Chinese?
Closed 4 years ago4
Questions about pretraining process and small errors in train.py
Closed 4 years ago1
语音特征提取的一些疑惑
Updated 4 years ago4
What's the meaning of the parameter --test_audio_video_length?
Closed 4 years ago1
no checkpoint found ?
Updated 4 years ago4
run test_all.py, use audio, get the image
Closed 4 years ago4
Code running without CUDA and pytorch version
Updated 4 years ago1
Pre-Processing Data
Closed 4 years ago5
Run testing script result not as good as demo
Updated 4 years ago2
How to generate a continuous mouth-to-audio matching video
Updated 4 years ago2
Hello
Closed 4 years ago1
raise exception on loading checkpoint file
Closed 5 years ago
'GPU' problem？
Updated 5 years ago1
Docker for this project
Updated 5 years ago
what dataset and data ID do U use to generate demo?
Updated 5 years ago
RuntimeError: cuda runtime error (2) : out of memory
Updated 5 years ago4
Unable to save the model using Train.py
Updated 5 years ago2
not found mfccs file:./0572_0019_0003/audio/100.bin
Updated 5 years ago2
Train Code
Closed 5 years ago2
issues about train and some train error
Closed 5 years ago2
Unzipping pretrained model issues
Closed 5 years ago2
Unable to convert pretrained model into tensorflow model.
Updated 5 years ago
A_select in training code
Updated 5 years ago1
Have you trained the part of eyes? There is no blink in our results. How can you achieve the performance in your demos.
Updated 5 years ago1
audio preprocess
Updated 5 years ago2
code
Updated 5 years ago
is the pretrained model broken?
Closed 5 years ago
Table 3: Audio-Visual Speech Recognition and 1:25000 audio-video retrieval results with different supervisions.
Updated 5 years ago1
Strange filterbank parameter value
Closed 5 years ago2
how to change to support none cuda pytorch?
Closed 5 years ago
Can I use some other audio for testing except for the example 0572_0019_0003.wav？
Closed 5 years ago1
Is audio video offset considered in LRW?
Closed 5 years ago1