Skip to contents

Matmul

Usage

torch_matmul(self, other)

Arguments

self

(Tensor) the first tensor to be multiplied

other

(Tensor) the second tensor to be multiplied

Note

The 1-dimensional dot product version of this function does not support an `out` parameter.

matmul(input, other, out=NULL) -> Tensor

Matrix product of two tensors.

The behavior depends on the dimensionality of the tensors as follows:

  • If both tensors are 1-dimensional, the dot product (scalar) is returned.

  • If both arguments are 2-dimensional, the matrix-matrix product is returned.

  • If the first argument is 1-dimensional and the second argument is 2-dimensional, a 1 is prepended to its dimension for the purpose of the matrix multiply. After the matrix multiply, the prepended dimension is removed.

  • If the first argument is 2-dimensional and the second argument is 1-dimensional, the matrix-vector product is returned.

  • If both arguments are at least 1-dimensional and at least one argument is N-dimensional (where N > 2), then a batched matrix multiply is returned. If the first argument is 1-dimensional, a 1 is prepended to its dimension for the purpose of the batched matrix multiply and removed after. If the second argument is 1-dimensional, a 1 is appended to its dimension for the purpose of the batched matrix multiple and removed after. The non-matrix (i.e. batch) dimensions are broadcasted (and thus must be broadcastable). For example, if input is a \((j \times 1 \times n \times m)\) tensor and other is a \((k \times m \times p)\) tensor, out will be an \((j \times k \times n \times p)\) tensor.

Examples

if (torch_is_installed()) {

# vector x vector
tensor1 = torch_randn(c(3))
tensor2 = torch_randn(c(3))
torch_matmul(tensor1, tensor2)
# matrix x vector
tensor1 = torch_randn(c(3, 4))
tensor2 = torch_randn(c(4))
torch_matmul(tensor1, tensor2)
# batched matrix x broadcasted vector
tensor1 = torch_randn(c(10, 3, 4))
tensor2 = torch_randn(c(4))
torch_matmul(tensor1, tensor2)
# batched matrix x batched matrix
tensor1 = torch_randn(c(10, 3, 4))
tensor2 = torch_randn(c(10, 4, 5))
torch_matmul(tensor1, tensor2)
# batched matrix x broadcasted matrix
tensor1 = torch_randn(c(10, 3, 4))
tensor2 = torch_randn(c(4, 5))
torch_matmul(tensor1, tensor2)
}
#> torch_tensor
#> (1,.,.) = 
#>  -0.4077  0.2451 -0.1143 -0.7054 -0.5042
#>  -1.2226  0.6981 -0.6811 -1.8699 -0.6471
#>   1.0530  1.0960  0.5336 -0.1148  1.0540
#> 
#> (2,.,.) = 
#>   5.2976  1.9356  1.0881  1.4976  5.1379
#>   2.4158 -3.4833  0.9209  6.8367  2.8771
#>   0.0648 -0.7560  1.6180  3.2594  0.3732
#> 
#> (3,.,.) = 
#>   1.8713 -0.6972  0.3407  2.1596  1.8692
#>  -1.7630 -1.4168 -0.3854  0.0093 -2.2281
#>   3.5056 -3.5043  1.2135  7.1145  3.0974
#> 
#> (4,.,.) = 
#>  -0.6596 -2.5338 -1.4705  0.9647 -0.4396
#>   0.2672 -1.0593  2.3533  4.2034 -0.0557
#>  -0.8705 -0.2677 -0.1221 -0.5649 -1.2931
#> 
#> (5,.,.) = 
#>  -1.7278 -1.0653 -0.3426  0.9913 -0.3978
#>   0.5915 -1.2822 -1.5748  0.8444  2.0462
#>  -0.6534  2.0247  0.2464 -2.7995 -1.1858
#> 
#> (6,.,.) = 
#>  -2.6976 -0.1377 -3.0839 -4.1184 -1.3508
#>  -0.9115  1.5129 -2.3088 -5.0526 -0.6699
#>   0.8071  1.2670 -1.6677 -3.7896  0.1341
#> 
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{10,3,5} ]