Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error while running clipit.do_init(settings) #30

Open
hritikb27 opened this issue Aug 15, 2022 · 1 comment
Open

Error while running clipit.do_init(settings) #30

hritikb27 opened this issue Aug 15, 2022 · 1 comment

Comments

@hritikb27
Copy link

213         if return_transform is not None:
    214             raise ValueError(
--> 215                 "`return_transform` is deprecated. Please access the transformation matrix with "
    216                 "`.transform_matrix`. For chained matrices, please use `AugmentationSequential`."
    217             )

ValueError: `return_transform` is deprecated. Please access the transformation matrix with `.transform_matrix`. For chained matrices, please use `AugmentationSequential`.
@Borkanie
Copy link

Borkanie commented Oct 25, 2022

hey man I got the same error too and I was able to bypass it by using AugmentationSequential and adding all the auguments as parameters to the constructor.
Like this:
augmentations = AugmentationSequential(K.ColorJitter(hue=0.1, saturation=0.1, p=0.8), K.RandomResizedCrop(size=(self.cut_size,self.cut_size), scale=(0.1,0.75), ratio=(0.85,1.2), cropping_mode='resample', p=0.7), MyRandomPerspective(distortion_scale=0.40, p=0.7), K.RandomCrop(size=(self.cut_size,self.cut_size), p=1.0, cropping_mode="resample") )

But that will lead into naother issue where :
batch1, transforms1 = self.augs_zoom(torch.cat(cutouts[:self.cutn_zoom], dim=0)) batch2, transforms2 = self.augs_wide(torch.cat(cutouts[self.cutn_zoom:], dim=0))
is calling for a variable as a method and it just falls apart there for me...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants