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×1×n×m) tensor and other is a (k×m×p) tensor, out will be an (j×k×n×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,.,.) = 
#>  -3.8287 -1.6401  2.7681  2.3792  0.2675
#>   3.0191  0.1886  2.8494 -2.8350  0.3874
#>  -0.9092 -0.5810  0.5582  1.0235  0.2518
#> 
#> (2,.,.) = 
#>  -4.3422  0.5163 -2.5975  1.0504 -0.1999
#>  -0.0228  1.2363 -3.3343 -0.3416 -1.0374
#>   9.2242  1.1177 -2.0860 -1.1601 -3.0752
#> 
#> (3,.,.) = 
#>  -0.7372 -0.7448  0.9900  1.3846 -0.5252
#>   2.0256  0.2312 -0.1447 -0.5936 -0.2234
#>   1.9218 -0.4748  1.9894  0.0181 -1.1935
#> 
#> (4,.,.) = 
#>   2.6770  1.6137  1.6500 -5.1558 -0.3090
#>  -0.3202  0.4507  3.0137 -3.3752  0.8325
#>  -0.1189 -0.8678  1.1918  1.6684 -1.0595
#> 
#> (5,.,.) = 
#>   4.5889 -0.1922  0.3740  0.3436 -1.7510
#>  -3.1980 -0.8469  4.6970 -0.9635  0.4744
#>   1.4599 -0.9769  3.3400 -0.2807  0.5983
#> 
#> (6,.,.) = 
#>   0.7696 -0.4145  3.6545 -1.9645  1.1509
#>  -4.6367  1.1093 -2.7054 -0.5513  0.5958
#>   1.5427  0.2866  0.1432 -0.9288 -0.0557
#> 
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{10,3,5} ]