mv¶
- paddle. mv ( x, vec, name=None ) [source]
-
Performs a matrix-vector product of the matrix x and the vector vec.
- Parameters
-
x (Tensor) – A tensor with shape \([M, N]\) , The data type of the input Tensor x should be one of float32, float64.
vec (Tensor) – A tensor with shape \([N]\) , The data type of the input Tensor x should be one of float32, float64.
name (str, optional) – The default value is None. Normally there is no need for user to set this property. For more information, please refer to Name.
- Returns
-
The tensor which is producted by x and vec.
- Return type
-
Tensor
Examples
# x: [M, N], vec: [N] # paddle.mv(x, vec) # out: [M] import paddle x = paddle.to_tensor([[2, 1, 3], [3, 0, 1]]).astype("float64") vec = paddle.to_tensor([3, 5, 1]).astype("float64") out = paddle.mv(x, vec) print(out) # Tensor(shape=[2], dtype=float64, place=Place(cpu), stop_gradient=True, # [14., 10.])