CosineSimilarity¶

class torch.nn.CosineSimilarity(dim=1, eps=1e-08)[source]¶

Returns cosine similarity between \(x_1\) and \(x_2\), computed along dim.

\[\text{similarity} = \dfrac{x_1 \cdot x_2}{\max(\Vert x_1 \Vert _2 \cdot \Vert x_2 \Vert _2, \epsilon)}. \]

Parameters:

dim (int, optional) – Dimension where cosine similarity is computed. Default: 1
eps (float, optional) – Small value to avoid division by zero. Default: 1e-8

Shape:

Input1: \((\ast_1, D, \ast_2)\) where D is at position dim
Input2: \((\ast_1, D, \ast_2)\), same number of dimensions as x1, matching x1 size at dimension dim,
and broadcastable with x1 at other dimensions.
Output: \((\ast_1, \ast_2)\)

Examples::

>>> input1 = torch.randn(100, 128)
>>> input2 = torch.randn(100, 128)
>>> cos = nn.CosineSimilarity(dim=1, eps=1e-6)
>>> output = cos(input1, input2)

Docs