Class and Description |
---|
org.deeplearning4j.earlystopping.scorecalc.DataSetLossCalculatorCG
Use
DataSetLossCalculator instead for both MultiLayerNetwork and ComputationGraph |
org.deeplearning4j.nn.conf.layers.GravesBidirectionalLSTM
use
Bidirectional instead. With the
Bidirectional layer wrapper you can make any recurrent layer bidirectional, in particular GravesLSTM.
Note that this layer adds the output of both directions, which translates into "ADD" mode in Bidirectional.
Usage: .layer(new Bidirectional(Bidirectional.Mode.ADD, new GravesLSTM.Builder()....build())) |
org.deeplearning4j.nn.layers.recurrent.GravesLSTM
Will be eventually removed. Use
LSTM instead, which has similar prediction accuracy, but supports
CuDNN for faster network training on CUDA (Nvidia) GPUs |
org.deeplearning4j.nn.conf.layers.GravesLSTM
Will be eventually removed. Use
LSTM instead, which has similar prediction accuracy, but supports
CuDNN for faster network training on CUDA (Nvidia) GPUs |
org.deeplearning4j.optimize.api.IterationListener
Use
TrainingListener instead |
Field and Description |
---|
org.deeplearning4j.nn.conf.serde.JsonMappers.CUSTOM_REGISTRATION_PROPERTY |
Constructor and Description |
---|
org.deeplearning4j.nn.conf.layers.variational.ExponentialReconstructionDistribution(String) |
Enum Constant and Description |
---|
org.deeplearning4j.nn.conf.Updater.CUSTOM |
org.deeplearning4j.nn.conf.WorkspaceMode.SEPARATE
Use
WorkspaceMode.ENABLED instead |
org.deeplearning4j.nn.conf.WorkspaceMode.SINGLE
Use
WorkspaceMode.ENABLED instead |
Copyright © 2018. All rights reserved.