tf.contrib.losses.get_regularization_losses(scope=None) Gets the regularization losses. Args:

tf.contrib.losses.cosine_distance(predictions, targets, dim, weight=1.0, scope=None) Adds a cosine-distance loss to the training

tf.contrib.losses.mean_squared_error(*args, **kwargs) Adds a Sum-of-Squares loss to the training procedure. (deprecated)

tf.contrib.losses.get_losses(scope=None, loss_collection='losses') Gets the list of losses from the loss_collection.

tf.contrib.losses.sparse_softmax_cross_entropy(logits, labels, weight=1.0, scope=None) Cross-entropy loss using tf.nn.sparse_

tf.contrib.losses.get_total_loss(add_regularization_losses=True, name='total_loss') Returns a tensor whose value represents the

tf.contrib.losses.hinge_loss(logits, target, scope=None) Method that returns the loss tensor for hinge loss.

tf.contrib.losses.add_loss(*args, **kwargs) Adds a externally defined loss to the collection of losses.

tf.contrib.losses.softmax_cross_entropy(logits, onehot_labels, weight=1.0, label_smoothing=0, scope=None) Creates a cross-entropy

tf.contrib.losses.sigmoid_cross_entropy(logits, multi_class_labels, weight=1.0, label_smoothing=0, scope=None) Creates a cross-entropy