Package org.deeplearning4j.nn.conf.inputs

Class Summary

Class	Description
InputType	The InputType class is used to track and define the types of activations etc used in a ComputationGraph.
InputType.InputTypeConvolutional
InputType.InputTypeConvolutional3D
InputType.InputTypeConvolutionalFlat
InputType.InputTypeFeedForward
InputType.InputTypeRecurrent

Enum Summary

Enum

Description

InputType.Type

The type of activations in/out of a given GraphVertex FF: Standard feed-foward (2d minibatch, 1d per example) data RNN: Recurrent neural network (3d minibatch) time series data CNN: 2D Convolutional neural network (4d minibatch, [miniBatchSize, channels, height, width]) CNNFlat: Flattened 2D conv net data (2d minibatch, [miniBatchSize, height * width * channels]) CNN3D: 3D convolutional neural network (5d minibatch, [miniBatchSize, channels, height, width, channels])

Exception Summary

Exception	Description
InvalidInputTypeException	InvalidInputTypeException: Thrown if the GraphVertex cannot handle the type of input provided.