| Class and Description |
|---|
| MultiLayerConfiguration
Configuration for a multi layer network
|
| Class and Description |
|---|
| CacheMode |
| GradientNormalization
Gradient normalization strategies.
|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and 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.
|
| ComputationGraphConfiguration
ComputationGraphConfiguration is a configuration object for neural networks with arbitrary connection structure.
|
| ComputationGraphConfiguration.GraphBuilder |
| 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. |
| DataFormat |
| GradientNormalization
Gradient normalization strategies.
|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| 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
|
| NeuralNetConfiguration.ListBuilder.InputTypeBuilder
Helper class for setting input types
|
| 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.
|
| Class and Description |
|---|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| CNN2DFormat
CNN2DFormat defines the format of the activations (including input images) in to and out of all 2D convolution layers in
Deeplearning4j.
|
| DataFormat |
| 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. |
| Class and Description |
|---|
| 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. |
| DataFormat |
| GradientNormalization
Gradient normalization strategies.
|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| 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 |
| 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
|
| Class and Description |
|---|
| CNN2DFormat
CNN2DFormat defines the format of the activations (including input images) in to and out of all 2D convolution layers in
Deeplearning4j.
|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| GradientNormalization
Gradient normalization strategies.
|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| 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. |
| Class and Description |
|---|
| GradientNormalization
Gradient normalization strategies.
|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| GradientNormalization
Gradient normalization strategies.
|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| 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. |
| Class and Description |
|---|
| GradientNormalization
Gradient normalization strategies.
|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| 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 |
| Class and Description |
|---|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| GradientNormalization
Gradient normalization strategies.
|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| Class and Description |
|---|
| CacheMode |
| Class and Description |
|---|
| GradientNormalization
Gradient normalization strategies.
|
| Class and Description |
|---|
| ComputationGraphConfiguration.GraphBuilder |
| Class and Description |
|---|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| CNN2DFormat
CNN2DFormat defines the format of the activations (including input images) in to and out of all 2D convolution layers in
Deeplearning4j.
|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| 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. |
| Class and Description |
|---|
| ComputationGraphConfiguration
ComputationGraphConfiguration is a configuration object for neural networks with arbitrary connection structure.
|
| MultiLayerConfiguration
Configuration for a multi layer network
|
| Class and Description |
|---|
| DataFormat |
| Class and Description |
|---|
| CacheMode |
| ComputationGraphConfiguration
ComputationGraphConfiguration is a configuration object for neural networks with arbitrary connection structure.
|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| CacheMode |
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| 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. |
| Class and Description |
|---|
| 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. |
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| 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. |
| Class and Description |
|---|
| CNN2DFormat
CNN2DFormat defines the format of the activations (including input images) in to and out of all 2D convolution layers in
Deeplearning4j.
|
| Class and Description |
|---|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| 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. |
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| CNN2DFormat
CNN2DFormat defines the format of the activations (including input images) in to and out of all 2D convolution layers in
Deeplearning4j.
|
| Class and Description |
|---|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| CacheMode |
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| 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. |
| Class and Description |
|---|
| CacheMode |
| Class and Description |
|---|
| CacheMode |
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| CacheMode |
| MultiLayerConfiguration
Configuration for a multi layer network
|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| BackpropType
Defines the type of backpropagation.
|
| ComputationGraphConfiguration
ComputationGraphConfiguration is a configuration object for neural networks with arbitrary connection structure.
|
| 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.
|
| InputPreProcessor
Input pre processor used
for pre processing input before passing it
to the neural network.
|
| MultiLayerConfiguration
Configuration for a multi layer network
|
| 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 |
| Updater
All the possible different updaters
|
| WorkspaceMode
Workspace mode to use.
|
| Class and Description |
|---|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| Class and Description |
|---|
| 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. |
| NeuralNetConfiguration
A Serializable configuration
for neural nets that covers per layer parameters
|
| 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. |
Copyright © 2020. All rights reserved.