Package org.deeplearning4j.nn.conf

Interface Summary

Interface	Description
DataFormat
InputPreProcessor	Input pre processor used for pre processing input before passing it to the neural network.

Class Summary

Class	Description
ComputationGraphConfiguration	ComputationGraphConfiguration is a configuration object for neural networks with arbitrary connection structure.
ComputationGraphConfiguration.GraphBuilder
MultiLayerConfiguration	Configuration for a multi layer network
MultiLayerConfiguration.Builder
NeuralNetConfiguration	A Serializable configuration for neural nets that covers per layer parameters
NeuralNetConfiguration.Builder	NeuralNetConfiguration builder, used as a starting point for creating a MultiLayerConfiguration or ComputationGraphConfiguration. Note that values set here on the layer will be applied to all relevant layers - unless the value is overridden on a layer's configuration
NeuralNetConfiguration.ListBuilder	Fluent interface for building a list of configurations

Enum Summary

Enum	Description
BackpropType	Defines the type of backpropagation.
CacheMode
CNN2DFormat	CNN2DFormat defines the format of the activations (including input images) in to and out of all 2D convolution layers in Deeplearning4j.
ConvolutionMode	ConvolutionMode defines how convolution operations should be executed for Convolutional and Subsampling layers, for a given input size and network configuration (specifically stride/padding/kernel sizes). Currently, 3 modes are provided: Strict: Output size for Convolutional and Subsampling layers are calculated as follows, in each dimension: outputSize = (inputSize - kernelSize + 2*padding) / stride + 1.
GradientNormalization	Gradient normalization strategies.
RNNFormat	NCW = "channels first" - arrays of shape [minibatch, channels, width] NWC = "channels last" - arrays of shape [minibatch, width, channels] "width" corresponds to sequence length and "channels" corresponds to sequence item size.
Updater	All the possible different updaters
WorkspaceMode	Workspace mode to use.