tf.keras.losses.CosineSimilarity

View source on GitHub

Class CosineSimilarity

Computes the cosine similarity between y_true and y_pred.

Aliases:

Usage:

cosine_loss = tf.keras.losses.CosineSimilarity(axis=1)
loss = cosine_loss([[0., 1.], [1., 1.]], [[1., 0.], [1., 1.]])
# l2_norm(y_true) = [[0., 1.], [1./1.414], 1./1.414]]]
# l2_norm(y_pred) = [[1., 0.], [1./1.414], 1./1.414]]]
# l2_norm(y_true) . l2_norm(y_pred) = [[0., 0.], [0.5, 0.5]]
# loss = mean(sum(l2_norm(y_true) . l2_norm(y_pred), axis=1))
       = ((0. + 0.) +  (0.5 + 0.5)) / 2

print('Loss: ', loss.numpy())  # Loss: 0.5

Usage with the compile API:

model = tf.keras.Model(inputs, outputs)
model.compile('sgd', loss=tf.keras.losses.CosineSimilarity(axis=1))

Args:

  • axis: (Optional) Defaults to -1. The dimension along which the cosine similarity is computed.
  • reduction: (Optional) Type of tf.keras.losses.Reduction to apply to loss. Default value is AUTO. AUTO indicates that the reduction option will be determined by the usage context. For almost all cases this defaults to SUM_OVER_BATCH_SIZE. When used with tf.distribute.Strategy, outside of built-in training loops such as tf.keras compile and fit, using AUTO or SUM_OVER_BATCH_SIZE will raise an error. Please see https://www.tensorflow.org/alpha/tutorials/distribute/training_loops for more details on this.
  • name: Optional name for the op.

__init__

View source

__init__(
    axis=-1,
    reduction=losses_utils.ReductionV2.AUTO,
    name='cosine_similarity'
)

Initialize self. See help(type(self)) for accurate signature.

Methods

tf.keras.losses.CosineSimilarity.__call__

View source

__call__(
    y_true,
    y_pred,
    sample_weight=None
)

Invokes the Loss instance.

Args:

  • y_true: Ground truth values. shape = [batch_size, d0, .. dN]
  • y_pred: The predicted values. shape = [batch_size, d0, .. dN]
  • sample_weight: Optional sample_weight acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If sample_weight is a tensor of size [batch_size], then the total loss for each sample of the batch is rescaled by the corresponding element in the sample_weight vector. If the shape of sample_weight is [batch_size, d0, .. dN-1] (or can be broadcasted to this shape), then each loss element of y_pred is scaled by the corresponding value of sample_weight. (Note ondN-1: all loss functions reduce by 1 dimension, usually axis=-1.)

Returns:

Weighted loss float Tensor. If reduction is NONE, this has shape [batch_size, d0, .. dN-1]; otherwise, it is scalar. (Note dN-1 because all loss functions reduce by 1 dimension, usually axis=-1.)

Raises:

  • ValueError: If the shape of sample_weight is invalid.

tf.keras.losses.CosineSimilarity.from_config

View source

from_config(
    cls,
    config
)

Instantiates a Loss from its config (output of get_config()).

Args:

  • config: Output of get_config().

Returns:

A Loss instance.

tf.keras.losses.CosineSimilarity.get_config

View source

get_config()