tf.contrib.losses.cosine_distance(*args, **kwargs)

tf.contrib.losses.cosine_distance(*args, **kwargs)

See the guide: Losses (contrib) > Loss operations for use in neural networks.

Adds a cosine-distance loss to the training procedure. (deprecated)

THIS FUNCTION IS DEPRECATED. It will be removed after 2016-12-30. Instructions for updating: Use tf.losses.cosine_distance instead.

Note that the function assumes that predictions and labels are already unit-normalized.


  • predictions: An arbitrary matrix.
  • labels: A Tensor whose shape matches 'predictions'
  • dim: The dimension along which the cosine distance is computed.
  • weights: Coefficients for the loss a scalar, a tensor of shape [batch_size] or a tensor whose shape matches predictions.
  • scope: The scope for the operations performed in computing the loss.


A scalar Tensor representing the loss value.


  • ValueError: If predictions shape doesn't match labels shape, or weights is None.

Defined in tensorflow/python/util/