class oneflow.nn.CosineSimilarity(dim: Optional[int] = 1, eps: Optional[float] = 1e-08)

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

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

The interface is consistent with PyTorch. The documentation is referenced from:

  • dim (int, optional) – Dimension where cosine similarity is computed. Default: 1

  • eps (float, optional) – Small value to avoid division by zero. Default: 1e-8

  • 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: \((\ast_1, \ast_2)\)

For example:

>>> import oneflow as flow
>>> from oneflow import nn
>>> input1 = flow.randn(100, 128)
>>> input2 = flow.randn(100, 128)
>>> cos = nn.CosineSimilarity(dim=1, eps=1e-6)
>>> output = cos(input1, input2)