tf.contrib.losses.metric_learning.lifted_struct_loss(
labels,
embeddings,
margin=1.0
)
Defined in tensorflow/contrib/losses/python/metric_learning/metric_loss_ops.py
.
Computes the lifted structured loss.
The loss encourages the positive distances (between a pair of embeddings with the same labels) to be smaller than any negative distances (between a pair of embeddings with different labels) in the mini-batch in a way that is differentiable with respect to the embedding vectors. See: https://arxiv.org/abs/1511.06452.
Args:
labels
: 1-D tf.int32Tensor
with shape [batch_size] of multiclass integer labels.embeddings
: 2-D floatTensor
of embedding vectors. Embeddings should not be l2 normalized.margin
: Float, margin term in the loss definition.
Returns:
lifted_loss
: tf.float32 scalar.