Addbmm

Addbmm

Usage

torch_addbmm(self, batch1, batch2, beta = 1L, alpha = 1L)

Arguments

self

(Tensor) matrix to be added

batch1

(Tensor) the first batch of matrices to be multiplied

batch2

(Tensor) the second batch of matrices to be multiplied

beta

(Number, optional) multiplier for input (\(\beta\))

alpha

(Number, optional) multiplier for batch1 @ batch2 (\(\alpha\))

addbmm(input, batch1, batch2, *, beta=1, alpha=1, out=NULL) -> Tensor

Performs a batch matrix-matrix product of matrices stored in batch1 and batch2, with a reduced add step (all matrix multiplications get accumulated along the first dimension). input is added to the final result.

batch1 and batch2 must be 3-D tensors each containing the same number of matrices.

If batch1 is a \((b \times n \times m)\) tensor, batch2 is a \((b \times m \times p)\) tensor, input must be broadcastable with a \((n \times p)\) tensor and out will be a \((n \times p)\) tensor.

$$ out = \beta\ \mbox{input} + \alpha\ (\sum_{i=0}^{b-1} \mbox{batch1}_i \mathbin{@} \mbox{batch2}_i) $$ For inputs of type FloatTensor or DoubleTensor, arguments beta and alpha must be real numbers, otherwise they should be integers.

Examples

if (torch_is_installed()) {

M = torch_randn(c(3, 5))
batch1 = torch_randn(c(10, 3, 4))
batch2 = torch_randn(c(10, 4, 5))
torch_addbmm(M, batch1, batch2)
}
#> torch_tensor
#>  3.3727 -5.2787  0.7149  0.8471  5.7292
#> -4.1041  1.4911  0.3756  1.3393  0.7743
#>  3.6581  6.1864 -5.2519 -7.9438 -5.1004
#> [ CPUFloatType{3,5} ]