How to test the model on single video or a sequence of moving pictures, without ground truth?

[catmasteryip]

[antonilo]

you can just divide the video in frames, create a "fake" mask, uniformly black, for each image, and run it on our model! Very easy to do! However, you will not be able to validate the model (since you have not GT). Hope it helps!

[MasahiroOgawa]

I added the automatic inference script for any video in this pull request.