We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Hello!
I am trying to augment a batch of one
If I provide a tensor with shape (1,3,320,320): augmented_image = transformer.augment_image(img_t.unsqueeze_(0)) I get:
augmented_image = transformer.augment_image(img_t.unsqueeze_(0))
ttach\functional.py:47, in scale(x, scale_factor, interpolation, align_corners) 45 def scale(x, scale_factor, interpolation="nearest", align_corners=None): 46 """scale batch of images by scale_factor with given interpolation mode""" ---> 47 h, w = x.shape[2:] 48 new_h = int(h * scale_factor) 49 new_w = int(w * scale_factor) ValueError: too many values to unpack (expected 2)
scale_factor
If I provide a tensor with shape (3,320,320): augmented_image = transformer.augment_image(img_t) I get:
augmented_image = transformer.augment_image(img_t)
ttach\functional.py:7, in rot90(x, k) 5 def rot90(x, k=1): 6 """rotate batch of images by 90 degrees k times""" ----> 7 return torch.rot90(x, k, (2, 3)) RuntimeError: Rotation dim1 out of range, dim1 = 3
What to do?
Thank you!
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Hello!
I am trying to augment a batch of one
If I provide a tensor with shape (1,3,320,320):
augmented_image = transformer.augment_image(img_t.unsqueeze_(0))
I get:
If I provide a tensor with shape (3,320,320):
augmented_image = transformer.augment_image(img_t)
I get:
What to do?
Thank you!
The text was updated successfully, but these errors were encountered: