Save the date! Google I/O returns May 18-20 Register now


Computes the lifted structured loss.

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.

lifted_loss float scalar with dtype of embeddings.