tf.contrib.losses.metric_learning.contrastive_loss(
labels,
embeddings_anchor,
embeddings_positive,
margin=1.0
)
Defined in tensorflow/contrib/losses/python/metric_learning/metric_loss_ops.py
.
Computes the contrastive loss.
This loss encourages the embedding to be close to each other for the samples of the same label and the embedding to be far apart at least by the margin constant for the samples of different labels. See: http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf
Args:
labels
: 1-D tf.int32Tensor
with shape [batch_size] of binary labels indicating positive vs negative pair.embeddings_anchor
: 2-D floatTensor
of embedding vectors for the anchor images. Embeddings should be l2 normalized.embeddings_positive
: 2-D floatTensor
of embedding vectors for the positive images. Embeddings should be l2 normalized.margin
: margin term in the loss definition.
Returns:
contrastive_loss
: tf.float32 scalar.