Interface and Description |
---|
org.deeplearning4j.datasets.iterator.DataSetFetcher |
org.deeplearning4j.datasets.iterator.DataSetIterator
Use
DataSetIterator |
org.deeplearning4j.datasets.iterator.DataSetPreProcessor
Use @deprecated Use
DataSetPreProcessor |
org.deeplearning4j.nn.api.SequenceClassifier |
Class and Description |
---|
org.deeplearning4j.nn.conf.layers.setup.ConvolutionLayerSetup
Use
MultiLayerConfiguration.Builder.setInputType(InputType) to set nIns
and add preprocessors as required. This can be done using builder.setInputType(InputType.convolutional(height, width, channels)) |
org.deeplearning4j.util.NetSaverLoaderUtils |
org.deeplearning4j.nn.conf.preprocessor.ReshapePreProcessor |
Constructor and Description |
---|
org.deeplearning4j.nn.conf.layers.setup.ConvolutionLayerSetup(MultiLayerConfiguration.Builder, int, int, int)
Use
MultiLayerConfiguration.Builder.setInputType(InputType) to set nIns
and add preprocessors as required. This can be done using builder.setInputType(InputType.convolutional(height, width, channels))
For image data that has been flattened into a row vector per example (shape [minibatchSize,depth*height*width])
instead use InputType.convolutionalFlat(height,width,depth) . |
org.deeplearning4j.nn.conf.graph.PreprocessorVertex(InputPreProcessor, InputType)
This constructor (and the "InputType override" functionality previously used is no longer necessary.
|
Enum Constant and Description |
---|
org.deeplearning4j.nn.weights.WeightInit.NORMALIZED |
org.deeplearning4j.nn.weights.WeightInit.SIZE |
org.deeplearning4j.nn.weights.WeightInit.VI |
Copyright © 2016. All Rights Reserved.