torch.nn.functional.cosine_similarity

torch.nn.functional.cosine_similarity(x1, x2, dim=1, eps=1e-8) → Tensor

Returns cosine similarity between x1 and x2, computed along dim. x1 and x2 must be broadcastable to a common shape. dim refers to the dimension in this common shape. Dimension dim of the output is squeezed (see torch.squeeze()), resulting in the output tensor having 1 fewer dimension.

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

Supports type promotion.

Parameters:

• x1 (Tensor) – First input.

• x2 (Tensor) – Second input.

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

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

Example:

>>> input1 = torch.randn(100, 128)
>>> input2 = torch.randn(100, 128)
>>> output = F.cosine_similarity(input1, input2)
>>> print(output)