# tf.contrib.losses.metric_learning.lifted_struct_loss

tf.contrib.losses.metric_learning.lifted_struct_loss(
labels,
embeddings,
margin=1.0
)


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.int32 Tensor with shape [batch_size] of multiclass integer labels.
• embeddings: 2-D float Tensor of embedding vectors. Embeddings should not be l2 normalized.
• margin: Float, margin term in the loss definition.

#### Returns:

• lifted_loss: tf.float32 scalar.