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
#>  0.0949
#>  0.0194
#> -0.1097
#>  0.0712
#> -0.0409
#>  0.0385
#>  0.1187
#>  0.0047
#> -0.0886
#> -0.0146
#>  0.1420
#>  0.1234
#>  0.0955
#> -0.0307
#> -0.2110
#> -0.0898
#> -0.1660
#>  0.0222
#> -0.1334
#>  0.0068
#> -0.0689
#>  0.0312
#>  0.1573
#> -0.0273
#> -0.1179
#> -0.0114
#> -0.0153
#>  0.0173
#>  0.0982
#>  0.0696
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{100} ]