Closed joihn closed 3 months ago
moreover there is a discrepancy with the jupyter notebook, where unormalized ints (1,2,3,4
)are used fot the mask
nevermind, actually the method multi_to_single_mask
bring the mask back to [0-255]
def multi_to_single_mask(self, mask):
mask=(mask*255).int()
Hello, thanks for this repo
issue location
ref :
https://github.com/marcoaversa/diffinfinite/blob/4d2309606e5ce6190828b96f436cfa962ec5d1ec/dataset.py#L394
ref
https://github.com/marcoaversa/diffinfinite/blob/4d2309606e5ce6190828b96f436cfa962ec5d1ec/dm.py#L646
issue summary
the
T.ToTensor()
will normalise your image and mask between 0 and 1. are you sure it is a good idea for the mask ? maybe it would be better to keep as an int [0-255]