torch.addmm
-
torch.addmm(input, mat1, mat2, *, beta=1, alpha=1, out=None) → Tensor
-
Performs a matrix multiplication of the matrices
mat1
andmat2
. The matrixinput
is added to the final result.If
mat1
is a tensor,mat2
is a tensor, theninput
must be broadcastable with a tensor andout
will be a tensor.alpha
andbeta
are scaling factors on matrix-vector product betweenmat1
andmat2
and the added matrixinput
respectively.If
beta
is 0, theninput
will be ignored, andnan
andinf
in it will not be propagated.For inputs of type
FloatTensor
orDoubleTensor
, argumentsbeta
andalpha
must be real numbers, otherwise they should be integers.This operator supports TensorFloat32.
- Parameters
- Keyword Arguments
-
-
beta (Number, optional) – multiplier for
input
( ) - alpha (Number, optional) – multiplier for ( )
- out (Tensor, optional) – the output tensor.
-
beta (Number, optional) – multiplier for
Example:
>>> M = torch.randn(2, 3) >>> mat1 = torch.randn(2, 3) >>> mat2 = torch.randn(3, 3) >>> torch.addmm(M, mat1, mat2) tensor([[-4.8716, 1.4671, -1.3746], [ 0.7573, -3.9555, -2.8681]])
© 2019 Torch Contributors
Licensed under the 3-clause BSD License.
https://pytorch.org/docs/1.8.0/generated/torch.addmm.html