|View source on GitHub|
Adds a cosine-distance loss to the training procedure. (deprecated arguments) (deprecated)
tf.contrib.losses.cosine_distance( predictions, labels=None, axis=None, weights=1.0, scope=None, dim=None )
Note that the function assumes that
labels are already
predictions: An arbitrary matrix.
Tensorwhose shape matches 'predictions'
axis: 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
scope: The scope for the operations performed in computing the loss.
dim: The old (deprecated) name for
Tensor representing the loss value.
predictionsshape doesn't match