How do I convert back to a Torch Tensor or numpy ndarray with a particular dimension ordering? What I've done so far is look at ._tensor and see what the shape is and rearrange as necessary, but I'm sure there's a better way.
E.g., like:
namedtensor.numpy(('dim1', 'dim2'))
which would output a numpy array with dimensions along the requested. The same thing for back to regular torch.
Hi,
Great package.
How do I convert back to a Torch Tensor or numpy ndarray with a particular dimension ordering? What I've done so far is look at ._tensor and see what the shape is and rearrange as necessary, but I'm sure there's a better way.
E.g., like:
which would output a numpy array with dimensions along the requested. The same thing for back to regular torch.
Thanks, Miles