about augmentations
Opened this issue · 0 comments
zou-yawen commented
hello, I read the source code data_list.py , I'm a little confused.
`def getitem(self, index):
path, target = self.imgs[index]
img = self.loader(path)
if self.transform is not None:
img_w = self.transform0
img_s = self.transform1
img_s1 = self.transform1
if self.target_transform is not None:
target = self.target_transform(target)
# We train the DaC model with two strong augmentations, you can choose to use only one strong augmentation
return img_w, img_s, img_s1, target, index`
you train the DaC model with two strong augmentations, but img_s and img_s1 use the same strong augmentation methods.
Could you please help me.
Thanks!