Ground Truth shape and data format for 2 class segmentation

[kabbas570]

Hello, thanks for the great work and nice code.

I am wondering how to provide the ground truth data in case of a 2-class segmentation problem.
I used a segmentation mask of size 1024 x 1024 x 3, where it has;
0 --> for background
1 --> for Class-1 pixels
2--> for Class-2 pixels

Can you please confirm if this approach is correct? As It didn't generate any error to adjust the number of classes in the network output as mentioned by #24

Thanks
cheers
Abbas