Hello, I am trying to port my code from TensorFlow to PyTorch.
I was using tfa.image.transform
for transforming my image based on the given transformation matrix and found that torch.nn.functional.grid_sample
is the equivalent function.
However, in my previous code, I use wrap
mode for filling the outside boundary.
As a review, wrap mode will extend the input by wrapping around to the opposite edge (a b c d | a b c d | a b c d)
.
And on the PyTorch grid_sample
, I can only find the supported padding_mode
for zeros
, and border
. and reflection
.
Is there any alternative for implementing the wrap
padding mode?
Thank you