-
Notifications
You must be signed in to change notification settings - Fork 1
Open
Description
Hi,
First of all, I'd like to thank you for your implementation of SegCaps in PyTorch, I wanted to try this model, but as I use Python, I did not found an implementation like yours.
In the Mask class (https://github.com/JensOverby/MatrixCaps/blob/master/SegCaps-tensorflow/capsule_layers_pytorch.py) you compute something with "kaj", e.g.:
mask = kaj*transforms.Resize([hei, wid], interpolation = Image.BICUBIC)(mask)
But kaj is never defined. In the tf implementation, there is only the transformation, should we just remove kaj?
Thanks,
Clément
Metadata
Metadata
Assignees
Labels
No labels