BiSeNet
BiSeNet copied to clipboard
why do not set the ignore index 255 to 0??
trafficstars
the code pad image through: im = np.pad(im, ((pad_h, pad_h), (pad_w, pad_w), (0, 0))) lb = np.pad(lb, ((pad_h, pad_h), (pad_w, pad_w)), 'constant', constant_values=255)
my doubt is, why we not set the padded pixes to 0, corresponding to the backgroung ?? like: lb = np.pad(lb, ((pad_h, pad_h), (pad_w, pad_w)), 'constant', constant_values=0)
Hi,
I used the trainId following this: https://github.com/mcordts/cityscapesScripts/blob/aeb7b82531f86185ce287705be28f452ba3ddbb8/cityscapesscripts/helpers/labels.py#L64
Here it said ignored trainId is 255.