Running training using my current segmentation masks without making and saving the segmentation masks

[cjfghddl0206]

It is divided into training and test files, so only the mask file and the image file are in jpg format, and the other files are not. So, I want to train without having to convert it to a mask file, but I wonder if it can work without using the Bitmasks part that saves the segmentation mask as a single image.

[yufeng89]

I met same problem,have you solved it?