Attend the Women in ML Symposium on December 7 Register now


Stay organized with collections Save and categorize content based on your preferences.

Computes pairwise logistic loss between y_true and y_pred.

For each list of scores s in y_pred and list of labels y in y_true:

loss = sum_i sum_j I[y_i > y_j] * log(1 + exp(-(s_i - s_j)))

Standalone usage:

y_true = [[1., 0.]]
y_pred = [[0.6, 0.8]]
loss = tfr.keras.losses.PairwiseLogisticLoss()
loss(y_true, y_pred).numpy()
# Using ragged tensors
y_true = tf.ragged.constant([[1., 0.], [0., 1., 0.]])
y_pred = tf.ragged.constant([[0.6, 0.8], [0.5, 0.8, 0.4]])
loss = tfr.keras.losses.PairwiseLogisticLoss(ragged=True)
loss(y_true, y_pred).numpy()

Usage with the compile() API:

model.compile(optimizer='sgd', loss=tfr.keras.losses.PairwiseLogisticLoss())


\[ \mathcal{L}(\{y\}, \{s\}) = \sum_i \sum_j I[y_i > y_j] \log(1 + \exp(-(s_i - s_j))) \]

reduction (Optional) The tf.keras.losses.Reduction to use (see tf.keras.losses.Loss).
name (Optional) The name for the op.
lambda_weight (Optional) A lambdaweight to apply to the loss. Can be one of tfr.keras.losses.DCGLambdaWeight, tfr.keras.losses.NDCGLambdaWeight, or, tfr.keras.losses.PrecisionLambdaWeight.
temperature (Optional) The temperature to use for scaling the logits.
ragged (Optional) If True, this loss will accept ragged tensors. If False, this loss will accept dense tensors.



View source

Instantiates a Loss from its config (output of get_config()).

config Output of get_config().

A Loss instance.


View source

Returns the config dictionary for a Loss instance.


View source

See tf.keras.losses.Loss.