Defined in tensorflow/contrib/distributions/python/ops/

Creates a Head for regression under a generic distribution. (deprecated)

THIS FUNCTION IS DEPRECATED. It will be removed after 2018-10-01. Instructions for updating: The TensorFlow Distributions library has moved to TensorFlow Probability ( You should update all references to use tfp.distributions instead of tf.contrib.distributions.


  • make_distribution_fn: Python callable which returns a tf.Distribution instance created using only logits.
  • label_dimension: Number of regression labels per example. This is the size of the last dimension of the labels Tensor (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 logits Tensor (typically, this has shape [batch_size, logits_dimension]). Default value: label_dimension.
  • label_name: Python str, name of the key in label dict. Can be None if label is a Tensor (single headed models).
  • weight_column_name: Python str 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: Python bool. If True, estimator will learn a centered bias variable for each class. Rest of the model structure learns the residual after centered bias.
  • head_name: Python str, name of the head. Predictions, summary and metrics keys are suffixed by "/" + head_name and the default variable scope is head_name.


An instance of Head for generic regression.