![]() |
Creates a Head
for regression under a generic distribution. (deprecated)
tf.contrib.distributions.estimator_head_distribution_regression(
make_distribution_fn,
label_dimension=1,
logits_dimension=None,
label_name=None,
weight_column_name=None,
enable_centered_bias=False,
head_name=None
)
Args:
make_distribution_fn
: Pythoncallable
which returns atf.Distribution
instance created using only logits.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]
).logits_dimension
: Number of logits per example. This is the size of the last dimension of the logitsTensor
(typically, this has shape[batch_size, logits_dimension]
). Default value:label_dimension
.label_name
: Pythonstr
, name of the key in labeldict
. Can beNone
if label is aTensor
(single headed models).weight_column_name
: Pythonstr
defining feature column name representing weights. It is used to down weight or boost examples during training. It will be multiplied by the loss of the example.enable_centered_bias
: Pythonbool
. IfTrue
, estimator will learn a centered bias variable for each class. Rest of the model structure learns the residual after centered bias.head_name
: Pythonstr
, name of the head. Predictions, summary and metrics keys are suffixed by"/" + head_name
and the default variable scope ishead_name
.
Returns:
An instance of Head
for generic regression.