tf.contrib.estimator.regression_head(
weight_column=None,
label_dimension=1,
loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE,
loss_fn=None,
inverse_link_fn=None,
name=None
)
Creates a _Head
for regression using the mean_squared_error
loss.
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]
.
Supports custom loss_fn
. loss_fn
takes (labels, logits)
or
(labels, logits, features)
as arguments and returns unreduced loss with
shape [D0, D1, ... DN, label_dimension]
.
Also supports custom inverse_link_fn
, also known as 'mean function'.
inverse_link_fn
is only used in PREDICT
mode. It takes logits
as
argument and returns predicted values. This function is the inverse of the
link function defined in
https://en.wikipedia.org/wiki/Generalized_linear_model#Link_function
Namely, for poisson regression, set inverse_link_fn=tf.exp
.
The head can be used with a canned estimator. Example:
my_head = tf.contrib.estimator.regression_head()
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.contrib.estimator.regression_head()
logits = tf.keras.Model(...)(features)
return my_head.create_estimator_spec(
features=features,
mode=mode,
labels=labels,
optimizer=tf.AdagradOptimizer(learning_rate=0.1),
logits=logits)
my_estimator = tf.estimator.Estimator(model_fn=_my_model_fn)
Args:
weight_column
: A string or a_NumericColumn
created bytf.feature_column.numeric_column
defining feature column representing weights. It is used to down weight or boost examples during training. It will be multiplied by the loss of the example.label_dimension
: Number of regression labels per example. This is the size of the last dimension of the labelsTensor
(typically, this has shape[batch_size, label_dimension]
).loss_reduction
: One oftf.losses.Reduction
exceptNONE
. Describes how to reduce training loss over batch and label dimension. Defaults toSUM_OVER_BATCH_SIZE
, namely weighted sum of losses divided bybatch size * label_dimension
. Seetf.losses.Reduction
.loss_fn
: Optional loss function. Defaults tomean_squared_error
.inverse_link_fn
: Optional inverse link function, also known as 'mean function'. Defaults to identity.name
: name of the head. If provided, summary and metrics keys will be suffixed by"/" + name
. Also used asname_scope
when creating ops.
Returns:
An instance of _Head
for linear regression.
Raises:
ValueError
: Iflabel_dimension
orloss_reduction
is invalid.