Package | Description |
---|---|
org.deeplearning4j.nn.conf.preprocessor | |
org.deeplearning4j.nn.modelimport.keras.preprocessors |
Class and Description |
---|
BaseInputPreProcessor |
Cnn3DToFeedForwardPreProcessor
A preprocessor to allow CNN and standard feed-forward network layers to be used together.
|
CnnToFeedForwardPreProcessor
A preprocessor to allow CNN and standard feed-forward network layers to be used together.
|
CnnToRnnPreProcessor
A preprocessor to allow CNN and RNN layers to be used together.
|
ComposableInputPreProcessor
Composable input pre processor
|
FeedForwardToCnn3DPreProcessor
A preprocessor to allow 3D CNN and standard feed-forward network layers to be used together.
|
FeedForwardToCnnPreProcessor
A preprocessor to allow CNN and standard feed-forward network layers to be used together.
|
FeedForwardToRnnPreProcessor
A preprocessor to allow RNN and feed-forward network layers to be used together.
|
RnnToCnnPreProcessor
A preprocessor to allow RNN and CNN layers to be used together
For example, time series (video) input -> ConvolutionLayer, or conceivable GravesLSTM -> ConvolutionLayer Functionally equivalent to combining RnnToFeedForwardPreProcessor + FeedForwardToCnnPreProcessor Specifically, this does two things: (a) Reshape 3d activations out of RNN layer, with shape [miniBatchSize, numChannels*inputHeight*inputWidth, timeSeriesLength]) into 4d (CNN) activations (with shape [numExamples*timeSeriesLength, numChannels, inputWidth, inputHeight]) (b) Reshapes 4d epsilons (weights. |
RnnToFeedForwardPreProcessor
A preprocessor to allow RNN and feed-forward network layers to be used together.
|
Class and Description |
---|
BaseInputPreProcessor |
CnnToFeedForwardPreProcessor
A preprocessor to allow CNN and standard feed-forward network layers to be used together.
|
Copyright © 2020. All rights reserved.