tf.keras.losses.Poisson

View source on GitHub

Class Poisson

Computes the Poisson loss between y_true and y_pred.

Aliases:

loss = y_pred - y_true * log(y_pred)

Usage:

p = tf.keras.losses.Poisson()
loss = p([1., 9., 2.], [4., 8., 12.])
print('Loss: ', loss.numpy())  # Loss: -0.35702705

Usage with the compile API:

model = tf.keras.Model(inputs, outputs)
model.compile('sgd', loss=tf.keras.losses.Poisson())

__init__

View source

__init__(
    reduction=losses_utils.ReductionV2.AUTO,
    name='poisson'
)

Initialize self. See help(type(self)) for accurate signature.

Methods

tf.keras.losses.Poisson.__call__

View source

__call__(
    y_true,
    y_pred,
    sample_weight=None
)

Invokes the Loss instance.

Args:

  • y_true: Ground truth values. shape = [batch_size, d0, .. dN]
  • y_pred: The predicted values. shape = [batch_size, d0, .. dN]
  • sample_weight: Optional sample_weight acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If sample_weight is a tensor of size [batch_size], then the total loss for each sample of the batch is rescaled by the corresponding element in the sample_weight vector. If the shape of sample_weight is [batch_size, d0, .. dN-1] (or can be broadcasted to this shape), then each loss element of y_pred is scaled by the corresponding value of sample_weight. (Note ondN-1: all loss functions reduce by 1 dimension, usually axis=-1.)

Returns:

Weighted loss float Tensor. If reduction is NONE, this has shape [batch_size, d0, .. dN-1]; otherwise, it is scalar. (Note dN-1 because all loss functions reduce by 1 dimension, usually axis=-1.)

Raises:

  • ValueError: If the shape of sample_weight is invalid.

tf.keras.losses.Poisson.from_config

View source

from_config(
    cls,
    config
)

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

Args:

  • config: Output of get_config().

Returns:

A Loss instance.

tf.keras.losses.Poisson.get_config

View source

get_config()