How to run trained network on own images?

[cborelc]

How would I apply the ENet to my own images or videos? I don't see an example in your code. I tried to add images to the test directory and test.txt in VamVid but they were not picked up during testing.

[davidtvs]

There is no way to do it from the command line directly, but a function to generate predictions exists here. The arguments are the model, images you want to segment, and the mapping from class integers to RGB which is defined in the dataset class.