search

Lingchen-chen / Dynamic-Hair

Other
80 stars 12 forks source link

How should I prepare my input? #2

Open qiqigit opened 3 years ago

qiqigit commented 3 years ago

Thank you so much for releasing the code of the project! I have a problem preparing the input data.

I put a mp4 video file into test_video_dir but it didn't work out. Then I converted the video into a sequence of 130 jpg images, starting from "frame001.jpg", which also ended in "ValueError: invalid literal for int() with base 10: '001.jpg'".

So my question is: what kind of input should I prepare exactly?

Lingchen-chen commented 3 years ago

Hi, the networks should be trained. You need to collect the dataset according to the data loader's format. Sorry for the inconvenience. For example, you need to prepare a 2D orientation map and a bust depth map for each frame.