cos_sim¶

paddle.fluid.layers.nn. cos_sim ( X, Y ) [source]

Cosine Similarity Operator

$Out = frac{X^T * Y}{(sqrt{X^T * X} * sqrt{Y^T * Y})}$

The input X and Y must have the same shape, except that the 1st dimension of input Y could be just 1 (different from input X), which will be broadcasted to match the shape of input X before computing their cosine similarity.

Parameters

• X (Tensor) – The 1st input of cos_sim op, Tensor with shape [N_1, N_2, ..., N_k], the data type is float32.

• Y (Tensor) – The 2nd input of cos_sim op, Tensor with shape [N_1 or 1, N_2, ..., N_k], the data type is float32.

Returns

A Tensor representing the output of cosine(X, Y).

Examples

import paddle

x = paddle.rand(shape=[3, 7], dtype='float32')
y = paddle.rand(shape=[1, 7], dtype='float32')
out = paddle.fluid.layers.cos_sim(x, y)
print(out)