torch.mv — PyTorch 2.0 documentation (original) (raw)

• Docs >
• torch >
• torch.mv
• 

Shortcuts

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

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

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

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])

• torch.mv