Matmul — torch_matmul • torch

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,.,.) = 
#>   0.7460  0.6429 -2.2981  1.1007 -0.8882
#>   0.4028  0.2293 -2.2601 -1.0417  0.2696
#>   0.4428  1.0245  1.0811  0.6305 -2.3190
#> 
#> (2,.,.) = 
#>   0.4344  0.4525  0.0217  1.2605 -1.5103
#>   0.3009  0.1593  0.0042 -0.3794 -1.0311
#>   0.2879  0.5997  0.9439  1.2910 -1.6845
#> 
#> (3,.,.) = 
#>  -0.1025  0.0202 -1.0318 -1.0637  1.1033
#>   0.8092  0.4052 -0.1798 -0.2162 -2.6361
#>  -0.8710  0.5978  3.6105  2.5247  0.3231
#> 
#> (4,.,.) = 
#>  -0.1914  0.6312 -2.2367 -1.8273  2.2736
#>  -0.7006  0.9832 -0.5136  1.3260  2.7392
#>  -0.3681  0.0248 -0.1657 -1.3316  1.3797
#> 
#> (5,.,.) = 
#>  -0.0805 -0.9444  0.5724 -2.5830 -0.1149
#>   0.5353 -1.5956 -2.3768 -2.0726 -0.0577
#>  -0.2912  0.7820  5.8870  2.9461 -3.3156
#> 
#> (6,.,.) = 
#>  -0.0365  0.1440  1.9602  1.0294 -1.3080
#>   0.5767  0.3401  1.7709  2.8735 -3.2712
#>   0.2113  0.6800 -1.3332  1.2957  0.2318
#> 
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{10,3,5} ]