How can we specify the segmentation class number?

[JunMa11]

Dear @kanezaki ,

Thanks for sharing the great work.

It seems the number of classes is determined by SLIC.

pytorch-unsupervised-segmentation/demo.py

Lines 74 to 77 in 8dbde70

	u_labels = np.unique(labels)
	l_inds = []
	for i in range(len(u_labels)):
	l_inds.append( np.where( labels == u_labels[ i ] )[ 0 ] )

How can we manually specify the segmentation class number?
e.g., I only want the method segments the input image into 3 classes.

Best regards,
Jun

[kanezaki]

Dear @JunMa11

Sorry for confusion, but the number of classes is actually not determined by SLIC. As you will see when you run the code, the number gradually decreases during training. The training stops when it reaches the minimum number of classes, which can be given by "--minLabels" command option. It is set to 3 by default, so I expect you would get your desired results by just running the code. :)

Best regards,
Asako

[JunMa11]

Got it. Thanks for your reply very much.