W3cubDocs

/TensorFlow Python

Module: tf.contrib.losses.metric_learning

Defined in tensorflow/contrib/losses/python/metric_learning/__init__.py.

Ops for building neural network losses.

See Losses (contrib).

Functions

cluster_loss(...): Computes the clustering loss.

contrastive_loss(...): Computes the contrastive loss.

lifted_struct_loss(...): Computes the lifted structured loss.

npairs_loss(...): Computes the npairs loss.

npairs_loss_multilabel(...): Computes the npairs loss with multilabel data.

triplet_semihard_loss(...): Computes the triplet loss with semi-hard negative mining.

Other Members

__cached__

__loader__

__spec__

© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/contrib/losses/metric_learning