Prototypical-Networks-for-Few-shot-Learning-PyTorch
Prototypical-Networks-for-Few-shot-Learning-PyTorch copied to clipboard
query in loading images
Hi.
Thanks for the repo. I have a couple of queries in the load_img function.
https://github.com/orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch/blob/5e18a5e5b369903092f683d434efb12c7c40a83c/src/omniglot_dataset.py#L166-L181
-
Is it necessary to do x = 1.0 - torch.from_numpy(x) ? I understand this is to have 1s in the region of interest (the character) but does it really help?
-
Why do you take the transpose (rotates the image again) at the end?
Thanks!
hi, did you find any answer?
nope