|View source on GitHub|
Adds a cosine-distance loss to the training procedure. (deprecated arguments)
tf.losses.cosine_distance( labels, predictions, axis=None, weights=1.0, scope=None, loss_collection=tf.GraphKeys.LOSSES, reduction=Reduction.SUM_BY_NONZERO_WEIGHTS, dim=None )
Note that the function assumes that
labels are already
Tensorwhose shape matches 'predictions'
predictions: An arbitrary matrix.
axis: The dimension along which the cosine distance is computed.
Tensorwhose rank is either 0, or the same rank as
labels, and must be broadcastable to
labels(i.e., all dimensions must be either
1, or the same as the corresponding
scope: The scope for the operations performed in computing the loss.
loss_collection: collection to which this loss will be added.
reduction: Type of reduction to apply to loss.
dim: The old (deprecated) name for
Weighted loss float
NONE, this has the same
labels; otherwise, it is scalar.
predictionsshape doesn't match
loss_collection argument is ignored when executing eagerly. Consider
holding on to the return value or collecting losses via a