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,.,.) =
#> 1.1741 0.2559 2.1010 0.6791 -1.0063
#> 0.7230 -0.4138 -1.4034 -2.1578 -0.4895
#> 1.5710 -1.2876 -0.0107 0.0330 5.4184
#>
#> (2,.,.) =
#> 0.8388 1.9660 -1.0262 -1.2845 0.1872
#> -1.8714 -0.5525 -0.2344 1.1003 -0.2241
#> 0.3883 -2.4709 1.6875 0.9729 -0.3365
#>
#> (3,.,.) =
#> 1.2832 -1.9016 -0.3001 0.8860 1.2404
#> 1.2865 -1.1586 -2.4160 0.1655 1.4697
#> 0.4389 -0.8549 1.6662 0.6197 -0.9461
#>
#> (4,.,.) =
#> 0.9855 -1.6766 -4.0700 -4.0975 4.0677
#> 3.6440 -3.8734 -1.2834 -0.9540 0.8312
#> 1.8192 0.8728 1.5987 3.2078 -0.5403
#>
#> (5,.,.) =
#> -4.1807 3.4626 2.6183 -4.4766 1.8168
#> -0.2935 -1.0232 1.7067 2.0395 0.8639
#> 1.1046 -8.8380 0.8910 0.0105 -0.9801
#>
#> (6,.,.) =
#> -1.4214 -0.2557 0.7621 -2.0962 1.5151
#> -2.0770 -0.0136 0.9170 -0.4942 2.2183
#> -1.0848 -0.4747 -0.1055 0.8999 1.6079
#>
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{10,3,5} ]