tfa.losses.npairs_loss

Computes the npairs loss between y_true and y_pred.

@tf.function
tfa.losses.npairs_loss(
    y_true: tfa.types.TensorLike,
    y_pred: tfa.types.TensorLike
) -> tf.Tensor

Npairs loss expects paired data where a pair is composed of samples from the same labels and each pairs in the minibatch have different labels. The loss takes each row of the pair-wise similarity matrix, y_pred, as logits and the remapped multi-class labels, y_true, as labels.

The similarity matrix y_pred between two embedding matrices a and b with shape [batch_size, hidden_size] can be computed as follows:

a = tf.constant([[1, 2],
                [3, 4],
                [5, 6]], dtype=tf.float16)
b = tf.constant([[5, 9],
                [3, 6],
                [1, 8]], dtype=tf.float16)
y_pred = tf.matmul(a, b, transpose_a=False, transpose_b=True)
y_pred
<tf.Tensor: shape=(3, 3), dtype=float16, numpy=
array([[23., 15., 17.],
   [51., 33., 35.],
   [79., 51., 53.]], dtype=float16)>

<... Note: constants a & b have been used purely for example purposes and have no significant value ...>

See: http://www.nec-labs.com/uploads/images/Department-Images/MediaAnalytics/papers/nips16_npairmetriclearning.pdf

y_true 1-D integer Tensor with shape [batch_size] of multi-class labels.
y_pred 2-D float Tensor with shape [batch_size, batch_size] of similarity matrix between embedding matrices.

npairs_loss float scalar.