torch.mv

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

Performs a matrix-vector product of the matrix input and the vector vec.

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

Note

This function does not broadcast.

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])