Baddbmm — torch_baddbmm • torch

Baddbmm

Usage

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

Arguments

self: (Tensor) the tensor 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 ( $β$ )
alpha: (Number, optional) multiplier for $batch1 @ batch2$ ( $α$ )

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

Performs a batch matrix-matrix product of matrices in batch1 and batch2. 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, then input must be broadcastable with a $(b \times n \times p)$ tensor and out will be a $(b \times n \times p)$ tensor. Both alpha and beta mean the same as the scaling factors used in torch_addbmm.

${out}_{i} = β {input}_{i} + α ({batch1}_{i} @ {batch2}_{i})$ 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(10, 3, 5))
batch1 = torch_randn(c(10, 3, 4))
batch2 = torch_randn(c(10, 4, 5))
torch_baddbmm(M, batch1, batch2)
}
#> torch_tensor
#> (1,.,.) = 
#>   2.5668 -0.4237 -2.9404  1.3825 -1.3862
#>  -0.6745  1.4488  1.6203 -1.6715  0.3611
#>  -3.2829 -3.6264 -1.0860 -0.0391 -1.4816
#> 
#> (2,.,.) = 
#>   0.9901 -1.3908  0.0594 -0.0992 -3.2152
#>   1.6730 -1.8321 -0.7380  2.6288 -4.1835
#>  -1.0785 -3.8915  0.1029  0.1313 -4.7576
#> 
#> (3,.,.) = 
#>   1.4986  1.2973  1.7373 -1.9960  3.4302
#>  -4.2607 -1.2940  0.6256  2.7559  7.3600
#>  -2.4782  0.4995 -1.8852  1.9486  5.8216
#> 
#> (4,.,.) = 
#>  -2.7854 -1.9376  0.6116 -0.5304 -2.7533
#>   7.3231  2.4280  0.7276  2.5102  2.7631
#>  -1.4774 -0.9340  0.5800  0.3354 -2.6695
#> 
#> (5,.,.) = 
#>  -3.1803  1.0826 -1.9716 -0.6409  0.4772
#>   1.5822  0.5086  0.8684  0.4020  0.1475
#>   2.3245  0.8159 -0.1406 -0.9883 -1.2855
#> 
#> (6,.,.) = 
#>   0.5705  1.1246  0.2826  0.3696  0.0717
#>   0.7779  1.0982  2.0234 -0.6402 -4.6686
#>   2.7589 -0.8088 -0.5637  2.0045 -0.7080
#> 
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{10,3,5} ]