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,.,.) =
#> -1.7765 -0.1350 0.8466 0.8478 -0.7594
#> 1.6370 -0.2408 0.3351 2.2860 -0.6668
#> 1.9089 0.2050 -1.6219 -2.5549 1.7960
#>
#> (2,.,.) =
#> -1.8824 2.0253 -2.1206 -1.3713 0.0871
#> 2.8014 -0.8317 -0.6866 -1.2809 2.3431
#> 0.1755 -3.8833 0.2988 7.5040 -3.6713
#>
#> (3,.,.) =
#> 0.8480 -0.0850 1.4366 2.9513 -0.3949
#> -0.9064 -0.8385 1.3575 -7.3166 -7.2062
#> 0.5430 -0.3684 0.4283 0.9606 2.1168
#>
#> (4,.,.) =
#> -2.3839 1.7347 1.1756 -1.6514 0.6408
#> 1.6447 -1.2290 1.8483 1.1605 -3.7812
#> 1.8861 0.1105 0.4390 1.3200 -0.8549
#>
#> (5,.,.) =
#> 0.4684 1.1384 1.3886 1.1070 -1.7678
#> 3.1111 0.6010 1.0678 -0.0603 -2.4754
#> 1.0265 -0.3575 0.2944 -1.0106 -2.2023
#>
#> (6,.,.) =
#> 0.3164 -1.3392 0.5580 -1.6123 5.0994
#> 1.6859 -1.7957 -0.2757 0.7590 0.4473
#> -0.4207 0.6214 0.0980 0.1298 -0.7558
#>
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{10,3,5} ]