showlab / MotionDirector

MotionDirector: Motion Customization of Text-to-Video Diffusion Models.
https://showlab.github.io/MotionDirector/
Apache License 2.0
762 stars 44 forks source link

Not able to save spatial and temporal data #20

Open lakshmi-priya-ramisetty opened 5 months ago

lakshmi-priya-ramisetty commented 5 months ago

Hi, I am not able to see the spatial and temporal data saved when I am trying to train a single image and single video. Is there anything I am missing in the config file that I need to change?

This is the output at present.

Screenshot 2024-02-04 at 10 29 24 PM
ruizhaocv commented 5 months ago

I think you can just directly un the demo config file without any changes. Have you solved this problem?

lakshmi-priya-ramisetty commented 5 months ago

Hey, I have not yet solved this issue. It is still an empty folder. Am I missing something?

Screenshot 2024-02-24 at 5 59 43 PM
ruizhaocv commented 5 months ago

It's possible that the training has not been completed yet. Can you monitor the progress of the training process from the console?

lakshmi-priya-ramisetty commented 5 months ago

This is what it shows when I run the training code.

Screenshot 2024-02-27 at 10 38 20 AM
ruizhaocv commented 4 months ago

It seems that you didn't finish the training. When the training begins, there will be more information printed out, which is not shown in your screenshot.