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.