Using my own video frames

[Itzikefraim]

Hi!

I am trying to use my own video frames. I am using the demo script and I can't find where I can change the input to make it my own frames. is there a way to do it?

[nixczhou]

I think you need to write it by yourself, here is the steps:

1. Prepare your testset_videos and run the two-GAN inference.
2. Obtain testset_features from two-GAN (e.g. you can save it to .mat like what the Author did)
3. Then, you can make them as the input in the demo_uot.py

[srikanth-midde]

I think you need to write it by yourself, here is the steps:

1. Prepare your testset_videos and run the two-GAN inference.
2. Obtain testset_features from two-GAN (e.g. you can save it to .mat like what the Author did)
3. Then, you can make them as the input in the demo_uot.py

I tried this step for my own image to get test_features but when I convert the Two GAN output edge image into .mat format. It does not consists of properties in the .mat file edge_distances: (180, 320, 1, 186) edge_map: (720, 1280, 1, 186) features: (16, 186)