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.

$$ \mbox{similarity} = \frac{x_1 \cdot x_2}{\max(\Vert x_1 \Vert _2 \cdot \Vert x_2 \Vert _2, \epsilon)} $$

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
#>  0.0466
#> -0.1372
#> -0.0302
#>  0.0493
#>  0.0217
#>  0.0185
#>  0.1085
#> -0.1180
#> -0.0297
#>  0.0583
#> -0.0547
#>  0.0357
#>  0.0243
#>  0.0327
#>  0.0973
#> -0.0581
#> -0.1382
#>  0.0273
#>  0.1538
#> -0.0739
#> -0.0360
#>  0.0212
#> -0.0070
#> -0.0633
#> -0.0089
#> -0.0807
#> -0.0778
#> -0.0124
#>  0.1215
#> -0.1192
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{100} ]