What is the simplest syntax to transform 2D tensor
A B
C D
into
A A B B
A A B B
C C D D
C C D D
Note they are parameter tensors, so I need autograd to back propagate gradient from latter into former.
Thanks!
What is the simplest syntax to transform 2D tensor
A B
C D
into
A A B B
A A B B
C C D D
C C D D
Note they are parameter tensors, so I need autograd to back propagate gradient from latter into former.
Thanks!
I found a numpy.repeat()-like function in latest pytorch (1.1), but it is needed to be called twice:
z = x.repeat_interleave(2,dim=0).repeat_interleave(2,dim=1)
mat1 = np.random.rand(3,3)
mat2 = np.ones(3,3)
out = np.kron(mat1,mat2)
Thanks for the hint! Kronecker product seems to be exactly what I need. But there seems no such corresponding function in Pytorch