Chain_matmul

Usage

torch_chain_matmul(matrices)

Arguments

matrices

(Tensors...) a sequence of 2 or more 2-D tensors whose product is to be determined.

TEST

Returns the matrix product of the $$N$$ 2-D tensors. This product is efficiently computed using the matrix chain order algorithm which selects the order in which incurs the lowest cost in terms of arithmetic operations ([CLRS]_). Note that since this is a function to compute the product, $$N$$ needs to be greater than or equal to 2; if equal to 2 then a trivial matrix-matrix product is returned. If $$N$$ is 1, then this is a no-op - the original matrix is returned as is.

Examples

if (torch_is_installed()) {

a = torch_randn(c(3, 4))
b = torch_randn(c(4, 5))
c = torch_randn(c(5, 6))
d = torch_randn(c(6, 7))
torch_chain_matmul(list(a, b, c, d))
}
#> torch_tensor
#>  -4.9114  11.1095  -3.5044  14.9431  17.5463  -4.6954  -8.2067
#>  -4.2924   2.9680  -1.0878   3.3883   7.5599  -2.4557  -3.2995
#>   5.2357  -3.2431   5.0502  -2.0051  -8.0577  -1.0972   1.1601
#> [ CPUFloatType{3,7} ]