Creates a Head for poisson regression using tf.nn.log_poisson_loss.

Inherits From: RegressionHead, Head

The loss is the weighted sum over all input dimensions. Namely, if the input labels have shape [batch_size, label_dimension], the loss is the weighted sum over both batch_size and label_dimension.

The head expects logits with shape [D0, D1, ... DN, label_dimension]. In many applications, the shape is [batch_size, label_dimension].

The labels shape must match logits, namely [D0, D1, ... DN, label_dimension]. If label_dimension=1, shape [D0, D1, ... DN] is also supported.

If weight_column is specified, weights must be of shape [D0, D1, ... DN], [D0, D1, ... DN, 1] or [D0, D1, ... DN, label_dimension].

This is implemented as a generalized linear model, see

The head can be used with a canned estimator. Example:

my_head = tf.estimator.PoissonRegressionHead()
my_estimator = tf.estimator.DNNEstimator(

It can also be used with a custom model_fn. Example:

def _my_model_fn(features, labels, mode):
  my_head = tf.estimator.PoissonRegressionHead()
  logits = tf.keras.Model(...)(features)

  return my_head.c