|View source on GitHub|
Computes the triplet loss with semi-hard negative mining.
tf.contrib.losses.metric_learning.triplet_semihard_loss( labels, embeddings, margin=1.0 )
The loss encourages the positive distances (between a pair of embeddings with the same labels) to be smaller than the minimum negative distance among which are at least greater than the positive distance plus the margin constant (called semi-hard negative) in the mini-batch. If no such negative exists, uses the largest negative distance instead. See: https://arxiv.org/abs/1503.03832.
labels: 1-D tf.int32
Tensorwith shape [batch_size] of multiclass integer labels.
embeddings: 2-D float
Tensorof embedding vectors. Embeddings should be l2 normalized.
margin: Float, margin term in the loss definition.
triplet_loss: tf.float32 scalar.