LostTech.TensorFlow : API Documentation

Type RegressionHead

Namespace tensorflow_estimator.python.estimator.api.estimator

Parent Head

Interfaces IRegressionHead

Methods

Properties

Public instance methods

IDictionary<string, Tensor> predictions(IEnumerable<IGraphNodeBase> logits)

IDictionary<string, Tensor> predictions(ValueTuple<PythonClassContainer, PythonClassContainer> logits)

IDictionary<string, Tensor> predictions(IndexedSlices logits)

IDictionary<string, Tensor> predictions(IGraphNodeBase logits)

IDictionary<string, Tensor> predictions(object logits)

IDictionary<string, Tensor> predictions(string logits)

object predictions_dyn(object logits)

Add operations to compute predictions by the model.

If logistic_loss is being used, predicted probabilities are returned. If poisson_loss is being used, predictions are exponentiated. Otherwise, (raw) linear predictions (w*x) are returned.
Returns
object
An Operation that computes the predictions for examples.

Public static methods

RegressionHead NewDyn(ImplicitContainer<T> label_dimension, object weight_column, ImplicitContainer<T> loss_reduction, object loss_fn, object inverse_link_fn, object name)

Public properties

int logits_dimension get;

object logits_dimension_dyn get;

string loss_reduction get;

object loss_reduction_dyn get;

IList<object> name get;

object name_dyn get;

object PythonObject get;