L-YeZhu / D2M-GAN

[ECCV2022] D2M-GAN for music generation from dance videos
85 stars 14 forks source link

dataset #9

Open DisgustedALL opened 1 year ago

DisgustedALL commented 1 year ago

What should I do if I want to use my own audio/video moves, etc.?

L-YeZhu commented 1 year ago

Hi,

In order to use a customized dataset, you will need to mainly change the dataloader and do the data preprocessing. To be more specific, you will need to first separate the audio and visual track, parse the audio signals into chunks, and prepare the video frames for motion feature extraction. Afterward, it shouldn't be much work to fit the current dataloader to your own files.

kunkunsheng commented 1 year ago

Hello, if my audio and video are all 10 second files and I want to generate 10 second files, what should I do