torch.mv#

torch.mv(input,vec,*,out=None)→Tensor#

Performs a matrix-vector product of the matrixinput and the vectorvec.

Ifinput is a$(n\times m)$(n×m) tensor,vec is a 1-D tensor ofsize$m$m,out will be 1-D of size$n$n.

Note

This function does notbroadcast.

Parameters

• input (Tensor) – matrix to be multiplied

• vec (Tensor) – vector to be multiplied

Keyword Arguments

out (Tensor,optional) – the output tensor.

Example:

>>>mat=torch.randn(2,3)>>>vec=torch.randn(3)>>>torch.mv(mat,vec)tensor([ 1.0404, -0.6361])