Cosine_similarity

Usage

torch_cosine_similarity(x1, x2, dim = 2L, eps = 1e-08)

Arguments

x1: (Tensor) First input.
x2: (Tensor) Second input (of size matching x1).
dim: (int, optional) Dimension of vectors. Default: 1
eps: (float, optional) Small value to avoid division by zero. Default: 1e-8

cosine_similarity(x1, x2, dim=1, eps=1e-8) -> Tensor

Returns cosine similarity between x1 and x2, computed along dim.

$similarity = \frac{x_{1} \cdot x_{2}}{max (‖ x_{1} ‖_{2} \cdot ‖ x_{2} ‖_{2}, ϵ)}$

Examples

if (torch_is_installed()) {

input1 = torch_randn(c(100, 128))
input2 = torch_randn(c(100, 128))
output = torch_cosine_similarity(input1, input2)
output
}
#> torch_tensor
#> -0.0109
#>  0.1864
#>  0.1400
#>  0.1101
#> -0.0260
#>  0.0457
#> -0.0791
#> -0.0797
#>  0.0573
#>  0.1426
#> -0.0411
#> -0.0690
#>  0.0023
#> -0.2670
#> -0.0099
#>  0.0596
#> -0.0527
#>  0.0587
#>  0.0378
#> -0.0902
#> -0.0113
#>  0.0550
#> -0.0705
#>  0.0101
#> -0.1094
#> -0.0458
#>  0.1526
#> -0.0457
#> -0.0750
#>  0.0340
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{100} ]