Open RuiqiGeng opened 2 years ago
The add_identity
parameter has been removed in recent versions since it's now assumed that the affine is always 'over' the identity. If you remove that from your code, do things run correctly?
I came along same issue. Removing add_identity
worked. Additionally, got Transformation matrix size mismatch later down the line which was fixed by sending the appropriate matrix
Hey, thank you for sharing this great codebase! When I ran your small tutorial on warping annotations together with images, I got the following error:
TypeError Traceback (most recent call last) in ()
5
6 # warp image
----> 7 im_warped = vxm.layers.SpatialTransformer(add_identity=False)([im_keras, aff_keras])
8 im_warped = im_warped[0, ..., 0]
9
3 frames /usr/local/lib/python3.7/dist-packages/keras/utils/generic_utils.py in validate_kwargs(kwargs, allowed_kwargs, error_message) 1172 for kwarg in kwargs: 1173 if kwarg not in allowed_kwargs: -> 1174 raise TypeError(error_message, kwarg) 1175 1176
TypeError: ('Keyword argument not understood:', 'add_identity')