Uses of Package
org.deeplearning4j.nn.conf.layers
-
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.api Class Description Layer A neural network layer. -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf Class Description ConvolutionLayer.AlgoMode The "PREFER_FASTEST" mode will pick the fastest algorithm for the specified parameters from theConvolutionLayer.FwdAlgo,ConvolutionLayer.BwdFilterAlgo, andConvolutionLayer.BwdDataAlgolists, but they may be very memory intensive, so if weird errors occur when using cuDNN, please try the "NO_WORKSPACE" mode.Layer A neural network layer. -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.inputs Class Description Convolution3D.DataFormat An optional dataFormat: "NDHWC" or "NCDHW". -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.layers.convolutional Class Description Layer A neural network layer.Layer.Builder NoParamLayer -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.layers.misc Class Description BaseLayer A neural network layer.BaseLayer.Builder FeedForwardLayer FeedForwardLayer.Builder Layer A neural network layer.Layer.Builder -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.layers.objdetect Class Description Layer A neural network layer.Layer.Builder -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.layers.recurrent Class Description BaseLayer A neural network layer.BaseLayer.Builder BaseRecurrentLayer BaseRecurrentLayer.Builder FeedForwardLayer FeedForwardLayer.Builder Layer A neural network layer.Layer.Builder -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.layers.samediff Class Description Layer A neural network layer.Layer.Builder -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.layers.util Class Description Layer A neural network layer.Layer.Builder NoParamLayer -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.layers.variational Class Description BaseLayer A neural network layer.BaseLayer.Builder BasePretrainNetwork BasePretrainNetwork.Builder FeedForwardLayer FeedForwardLayer.Builder Layer A neural network layer.Layer.Builder -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.layers.wrapper Class Description Layer A neural network layer.Layer.Builder -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.ocnn Class Description BaseLayer A neural network layer.BaseLayer.Builder BaseOutputLayer BaseOutputLayer.Builder FeedForwardLayer FeedForwardLayer.Builder Layer A neural network layer.Layer.Builder -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.preprocessor Class Description Convolution3D.DataFormat An optional dataFormat: "NDHWC" or "NCDHW". -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.conf.serde Class Description BaseLayer A neural network layer.BaseOutputLayer Layer A neural network layer. -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.layers Class Description BaseLayer A neural network layer.BaseOutputLayer BasePretrainNetwork Layer A neural network layer. -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.layers.convolution Class Description Convolution1DLayer ConvolutionLayer.AlgoMode The "PREFER_FASTEST" mode will pick the fastest algorithm for the specified parameters from theConvolutionLayer.FwdAlgo,ConvolutionLayer.BwdFilterAlgo, andConvolutionLayer.BwdDataAlgolists, but they may be very memory intensive, so if weird errors occur when using cuDNN, please try the "NO_WORKSPACE" mode.ConvolutionLayer.BwdDataAlgo The backward data algorithm to use whenConvolutionLayer.AlgoModeis set to "USER_SPECIFIED".ConvolutionLayer.BwdFilterAlgo The backward filter algorithm to use whenConvolutionLayer.AlgoModeis set to "USER_SPECIFIED".ConvolutionLayer.FwdAlgo The forward algorithm to use whenConvolutionLayer.AlgoModeis set to "USER_SPECIFIED". -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.layers.convolution.subsampling Class Description PoolingType Pooling type:
MAX: Max pooling - output is the maximum value of the input values
AVG: Average pooling - output is the average value of the input values
SUM: Sum pooling - output is the sum of the input values
PNORM: P-norm pooling -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.layers.mkldnn Class Description ConvolutionLayer.AlgoMode The "PREFER_FASTEST" mode will pick the fastest algorithm for the specified parameters from theConvolutionLayer.FwdAlgo,ConvolutionLayer.BwdFilterAlgo, andConvolutionLayer.BwdDataAlgolists, but they may be very memory intensive, so if weird errors occur when using cuDNN, please try the "NO_WORKSPACE" mode.ConvolutionLayer.BwdDataAlgo The backward data algorithm to use whenConvolutionLayer.AlgoModeis set to "USER_SPECIFIED".ConvolutionLayer.BwdFilterAlgo The backward filter algorithm to use whenConvolutionLayer.AlgoModeis set to "USER_SPECIFIED".ConvolutionLayer.FwdAlgo The forward algorithm to use whenConvolutionLayer.AlgoModeis set to "USER_SPECIFIED".PoolingType Pooling type:
MAX: Max pooling - output is the maximum value of the input values
AVG: Average pooling - output is the average value of the input values
SUM: Sum pooling - output is the sum of the input values
PNORM: P-norm pooling -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.layers.ocnn Class Description Layer A neural network layer. -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.layers.recurrent Class Description AbstractLSTM BaseRecurrentLayer FeedForwardLayer GravesBidirectionalLSTM Deprecated. -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.layers.util Class Description Layer A neural network layer. -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.params Class Description Layer A neural network layer. -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.nn.transferlearning Class Description ConvolutionLayer.AlgoMode The "PREFER_FASTEST" mode will pick the fastest algorithm for the specified parameters from theConvolutionLayer.FwdAlgo,ConvolutionLayer.BwdFilterAlgo, andConvolutionLayer.BwdDataAlgolists, but they may be very memory intensive, so if weird errors occur when using cuDNN, please try the "NO_WORKSPACE" mode.Layer A neural network layer. -
Classes in org.deeplearning4j.nn.conf.layers used by org.deeplearning4j.util Class Description Convolution3D.DataFormat An optional dataFormat: "NDHWC" or "NCDHW".Layer A neural network layer.PoolingType Pooling type:
MAX: Max pooling - output is the maximum value of the input values
AVG: Average pooling - output is the average value of the input values
SUM: Sum pooling - output is the sum of the input values
PNORM: P-norm pooling