Bmm
Arguments
- self
(Tensor) the first batch of matrices to be multiplied
- mat2
(Tensor) the second batch of matrices to be multiplied
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,.,.) =
#> -0.6668 -0.7527 -1.5229 1.4966 2.5872
#> 0.4386 -1.5797 -0.1287 -0.0617 0.5446
#> 0.0078 0.2735 1.2906 -0.2431 -1.9352
#>
#> (2,.,.) =
#> 0.6210 -3.7027 0.2292 0.1662 -2.1485
#> 0.7773 1.2278 -3.1853 -1.3366 -2.5568
#> 0.7020 2.1114 -2.6958 -1.5855 -1.9494
#>
#> (3,.,.) =
#> 2.4366 2.1640 2.4777 -4.3598 2.3854
#> -0.9496 -1.4892 -2.0137 3.2990 -0.7943
#> 2.1103 -0.3613 -0.1985 0.2844 2.0784
#>
#> (4,.,.) =
#> 0.5756 -0.2154 0.2895 -0.3379 -0.7951
#> 1.7087 -0.5048 0.4555 0.6827 0.8221
#> -0.6560 2.1476 -0.4176 1.1168 -0.8709
#>
#> (5,.,.) =
#> -5.3473 -1.3028 1.3888 0.6719 2.5425
#> -1.9673 -0.6747 1.1727 0.1568 0.8675
#> 1.5578 2.4624 -2.5518 0.0249 0.8560
#>
#> (6,.,.) =
#> -0.4996 -0.4467 -0.3228 -0.5470 0.6067
#> -0.4206 1.2013 -0.9708 -2.0033 -1.1624
#> 0.3929 0.3060 1.5993 -1.8301 0.4189
#>
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{10,3,5} ]