chemicalchecker.tool.adanet.dnn_extend_generator.ExtendDNNBuilder

class ExtendDNNBuilder(optimizer, layer_sizes, num_layers, layer_block_size, learn_mixture_weights, dropout, seed, activation, previous_ensemble, input_shape, nan_mask_value=0.0)

Bases: Builder

Builds a DNN subnetwork for AdaNet.

Initializes a _DNNBuilder.

Parameters:

• optimizer – An Optimizer instance for training both the subnetwork and the mixture weights.

• layer_size – The number of nodes to output at each hidden layer.

• num_layers – The number of hidden layers.

• learn_mixture_weights – Whether to solve a learning problem to find best mixture weights, or use their default value according to the mixture weight type. When False, the subnetworks will return a no_op for the mixture weight train op.

• dropout – The dropout rate, between 0 and 1. E.g. “rate=0.1” would drop out 10% of input units.

• activation – The activation function to be used.

• seed – A random seed.

Returns:

An instance of ExtendDNNBuilder.

Methods

build_mixture_weights_train_op	See adanet.subnetwork.Builder.
build_subnetwork	See adanet.subnetwork.Builder.
build_subnetwork_report	Returns a subnetwork.Report to materialize and record.
build_subnetwork_train_op	See adanet.subnetwork.Builder.

Attributes

name	See adanet.subnetwork.Builder.

build_mixture_weights_train_op(loss, var_list, logits, labels, iteration_step, summary)

See adanet.subnetwork.Builder.

build_subnetwork(features, logits_dimension, training, iteration_step, summary, previous_ensemble=None)

See adanet.subnetwork.Builder.

build_subnetwork_report()

Returns a subnetwork.Report to materialize and record.

This method will be called once after build_subnetwork(). Do NOT depend on variables created in build_subnetwork_train_op(), because they are not called before build_subnetwork_report() is called.

If it returns None, AdaNet records the name and standard eval metrics.

build_subnetwork_train_op(subnetwork, loss, var_list, labels, iteration_step, summary, previous_ensemble)

See adanet.subnetwork.Builder.

property name

See adanet.subnetwork.Builder.