tf.contrib.losses.metric_learning.contrastive_loss

View source on GitHub

Computes the contrastive loss.

tf.contrib.losses.metric_learning.contrastive_loss(
    labels,
    embeddings_anchor,
    embeddings_positive,
    margin=1.0
)

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.int32 Tensor with shape [batch_size] of binary labels indicating positive vs negative pair.
• embeddings_anchor: 2-D float Tensor of embedding vectors for the anchor images. Embeddings should be l2 normalized.
• embeddings_positive: 2-D float Tensor 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.