mindspore.nn.CosineEmbeddingLoss

class mindspore.nn.CosineEmbeddingLoss(margin=0.0, reduction='mean')[source]

CosineEmbeddingLoss creates a criterion to measure the similarity between two tensors using cosine distance.

Given two tensors \(x1\), \(x2\), and a Tensor label \(y\) with values 1 or -1:

\[\begin{split}loss(x_1, x_2, y) = \begin{cases} 1-cos(x_1, x_2), & \text{if } y = 1\\ \max(0, cos(x_1, x_2)-margin), & \text{if } y = -1\\ \end{cases}\end{split}\]
Parameters
  • margin (float) – Should be in [-1.0, 1.0]. Default: 0.0 .

  • reduction (str, optional) –

    Apply specific reduction method to the output: 'none' , 'mean' , 'sum' . Default: 'mean' .

    • 'none': no reduction will be applied.

    • 'mean': compute and return the mean of elements in the output.

    • 'sum': the output elements will be summed.

Inputs:
  • logits_x1 (Tensor) - Tensor of shape \((N, *)\) where \(*\) means, any number of additional dimensions.

  • logits_x2 (Tensor) - Tensor of shape \((N, *)\), same shape and dtype as logits_x1.

  • labels (Tensor) - Contains value 1 or -1. Suppose the shape of logits_x1 is \((x_1, x_2, x_3, ..., x_R)\), then the shape of labels must be \((x_1, x_3, x_4, ..., x_R)\).

Outputs:

Tensor or Scalar, if reduction is "none", its shape is the same as labels. Otherwise, a scalar value will be returned.

Raises
  • TypeError – If margin is not a float.

  • ValueError – If reduction is not one of 'none', 'mean', 'sum'.

  • ValueError – If margin is not in range [-1.0, 1.0].

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore as ms
>>> import mindspore.nn as nn
>>> import numpy as np
>>> logits_x1 = ms.Tensor(np.array([[0.3, 0.8], [0.4, 0.3]]), ms.float32)
>>> logits_x2 = ms.Tensor(np.array([[0.4, 1.2], [-0.4, -0.9]]), ms.float32)
>>> labels = ms.Tensor(np.array([1, -1]), ms.int32)
>>> cosine_embedding_loss = nn.CosineEmbeddingLoss()
>>> output = cosine_embedding_loss(logits_x1, logits_x2, labels)
>>> print(output)
0.0003425479