Bmm
Note
This function does not broadcast .
For broadcasting matrix products, see torch_matmul.
bmm(input, mat2, out=NULL) -> Tensor
Performs a batch matrix-matrix product of matrices stored in input
and mat2.
input and mat2 must be 3-D tensors each containing
the same number of matrices.
If input is a \((b \times n \times m)\) tensor, mat2 is a
\((b \times m \times p)\) tensor, out will be a
\((b \times n \times p)\) tensor.
$$ \mbox{out}_i = \mbox{input}_i \mathbin{@} \mbox{mat2}_i $$
Examples
if (torch_is_installed()) {
input = torch_randn(c(10, 3, 4))
mat2 = torch_randn(c(10, 4, 5))
res = torch_bmm(input, mat2)
res
}
#> torch_tensor
#> (1,.,.) =
#> -1.5200 0.8593 -1.1707 1.6902 -0.9924
#> -0.7422 -1.4382 -0.8673 -1.8808 -4.6933
#> -0.8345 1.2811 -1.1514 2.5961 0.3439
#>
#> (2,.,.) =
#> -0.7616 -5.7221 3.8999 -1.3435 3.3716
#> -0.0716 -2.7815 1.2658 -2.1683 -0.2960
#> 0.6019 1.4019 -2.3965 -0.7504 -2.5028
#>
#> (3,.,.) =
#> -0.3227 -0.9582 -2.4072 -1.1488 0.0948
#> -3.0888 -0.4607 -0.2627 -0.9151 0.4471
#> -0.4101 3.0929 -1.3338 -1.6710 2.4936
#>
#> (4,.,.) =
#> -0.6440 -1.1372 -0.2937 1.4547 0.7481
#> 1.0010 0.6649 2.7118 -1.2833 2.3551
#> -1.7462 -1.6712 -1.2059 -1.7180 0.6536
#>
#> (5,.,.) =
#> 0.0984 -0.4216 -2.5258 -2.4128 2.9396
#> 0.7843 0.2789 2.5225 0.6975 -1.2594
#> -2.2007 -0.1722 -1.7133 -2.9386 3.4515
#>
#> (6,.,.) =
#> 0.4993 -2.0282 0.0999 3.4336 2.9142
#> 0.7751 2.2512 1.6117 -3.5616 0.9717
#> -0.8284 2.5424 0.3490 -4.6505 -5.1805
#>
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{10,3,5} ]