tf.estimator.PoissonRegressionHead

View source on GitHub

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

Inherits From: RegressionHead

tf.estimator.PoissonRegressionHead(
    label_dimension=1, weight_column=None,
    loss_reduction=losses_utils.ReductionV2.SUM_OVER_BATCH_SIZE,
    compute_full_loss=True, name=None
)

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 https://en.wikipedia.org/wiki/Generalized_linear_model.

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

my_head = tf.estimator.PoissonRegressionHead()
my_estimator = tf.estimator.DNNEstimator(
    head=my_head,
    hidden_units=...,
    feature_columns=...)

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.create_estimator_spec(
      features=features,
      mode=mode,
      labels=labels,
      optimizer=tf.keras.optimizers.Adagrad(lr=0.1),
      logits=logits)

my_estimator = tf.estimator.Estimator(model_fn=_my_model_fn)

Args:

Attributes:

Methods

create_estimator_spec

View source

create_estimator_spec(
    features, mode, logits, labels=None, optimizer=None, trainable_variables=None,
    train_op_fn=None, update_ops=None, regularization_losses=None
)

Returns EstimatorSpec that a model_fn can return.

It is recommended to pass all args via name.

Args:

Returns:

EstimatorSpec.

loss

View source

loss(
    labels, logits, features=None, mode=None, regularization_losses=None
)

Return predictions based on keys. See base_head.Head for details.

metrics

View source

metrics(
    regularization_losses=None
)

Creates metrics. See base_head.Head for details.

predictions

View source

predictions(
    logits
)

Return predictions based on keys. See base_head.Head for details.

Args:

Returns:

A dict of predictions.

update_metrics

View source

update_metrics(
    eval_metrics, features, logits, labels, regularization_losses=None
)

Updates eval metrics. See base_head.Head for details.