New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
The output video is messy and disorganized #28
Comments
This situation should not occur. Could you provide me with a copy of the data you're running? |
I just modified the following two lines in the configs/conference.yaml file Then copy 'motions/motion-09' to 'motion-009', and enter each subdirectory in 'motion-009'. Delete all files after the 101st one to ensure that only the first 100 frames of actions are generated. Github unable to upload the zip package of the entire directory here. I can only take a screenshot to show it. I did not do anything else, just deleted the file and left the first 100 frames The result of the processed motion-009 subdirectory is shown in the screenshot |
Have you solved this problem? The image you provided does not show all input files. Please zip all input images into a file and attach it in this issue. |
not resolved yet ... |
I take the configs/conference.yaml file for testing, and my graphics memory is only 20GB. Therefore I deleted a lot of the action images of motion-09, leaving only the first 100 images with an output resolution of 512x512. But the output video had serious errors, what is the reason for this? I tested a total of 4 images and actions in example_data, but none of them yielded the correct results
The text was updated successfully, but these errors were encountered: