How to check the video generated from the default weights #9
Unanswered
ReverseCache
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hello @lucidrains ! Thank you for the work done in making this implementation :)
May I ask what is the method to save the video to disk given the 'entire_video' ?
initially wanted to use torchvision.io.write_video(".", entire_video_reshaped.cpu(),30) but for some reason, there was the following error after trying to convert from the current format to the requested (T, H, W, C) by torchvision
File "av/container/core.pyx", line 219, in av.container.core.Container.__cinit__ ValueError: Could not determine output format "
So instead this is my current method :
the image I observed is just noise based on the preinstalled weights.
Have I made a mistake somewhere or is this the expected behaviour?
Beta Was this translation helpful? Give feedback.
All reactions