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,.,.) = 
#>  -1.1001  0.7552 -3.3802  0.9889 -0.5060
#>   3.9004  0.2481 -1.5327 -2.1009  3.2656
#>  -1.2878  0.0020  1.4947  1.2510 -2.6341
#> 
#> (2,.,.) = 
#>   1.4413 -4.3586 -0.9760 -0.4607 -2.5707
#>   0.4550 -2.4910  0.1114 -1.2042 -4.2250
#>  -0.5545  0.1002  0.1043  0.3360  1.6588
#> 
#> (3,.,.) = 
#>   1.1137  0.0375 -2.6468  2.9447  3.3930
#>  -0.3208  0.8786 -0.6220  1.8655 -0.5127
#>  -5.8664 -1.3465 -0.4836 -1.1213  2.0625
#> 
#> (4,.,.) = 
#>  -1.0890  4.2098 -4.6076  0.2430 -3.8767
#>   2.3953 -3.3443  3.5276  0.2865 -0.6888
#>  -0.6316  2.4203 -0.5888  0.7332 -1.1303
#> 
#> (5,.,.) = 
#>  -0.0388 -1.6542 -0.7763 -0.5889 -0.2215
#>   2.3043  0.1464  3.2428  4.3219  1.0653
#>   0.6359 -0.4460  2.4775  2.6263  2.3618
#> 
#> (6,.,.) = 
#>  -0.7956  0.5339 -0.8440 -1.7119 -0.5565
#>  -2.7606  1.6186  0.6894 -0.7590 -2.1902
#>   0.1447 -0.1125 -1.2370 -0.1133 -0.3476
#> 
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{10,3,5} ]