NeuralNetConfiguration (deeplearning4j-nn 1.0.0-alpha API)

java.lang.Object
- org.deeplearning4j.nn.conf.NeuralNetConfiguration

All Implemented Interfaces:

Serializable, Cloneable
```
public class NeuralNetConfiguration
extends Object
implements Serializable, Cloneable
```
A Serializable configuration for neural nets that covers per layer parameters

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes
Modifier and Type	Class and Description
`static class`	`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
`static class`	`NeuralNetConfiguration.ListBuilder` Fluent interface for building a list of configurations

Field Summary

Fields
Modifier and Type	Field and Description
`protected CacheMode`	`cacheMode`
`static String`	`CUSTOM_FUNCTIONALITY` System property for custom layers, preprocessors, graph vertices etc.
`protected int`	`epochCount`
`protected int`	`iterationCount`
`protected Map<String,Double>`	`l1ByParam`
`protected Map<String,Double>`	`l2ByParam`
`protected Layer`	`layer`
`protected int`	`maxNumLineSearchIterations`
`protected boolean`	`miniBatch`
`protected boolean`	`minimize`
`protected OptimizationAlgorithm`	`optimizationAlgo`
`protected boolean`	`pretrain`
`protected long`	`seed`
`protected StepFunction`	`stepFunction`
`protected List<String>`	`variables`

Constructor Summary

Constructors
Constructor and Description

NeuralNetConfiguration()

Constructors
Constructor and Description
`NeuralNetConfiguration()`

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`void`	`addVariable(String variable)`
`void`	`clearVariables()`
`NeuralNetConfiguration`	`clone()` Creates and returns a deep copy of the configuration.
`static NeuralNetConfiguration`	`fromJson(String json)` Create a neural net configuration from json
`static NeuralNetConfiguration`	`fromYaml(String json)` Create a neural net configuration from json
`double`	`getL1ByParam(String variable)`
`double`	`getL2ByParam(String variable)`
`static org.nd4j.shade.jackson.databind.ObjectMapper`	`mapper()` Object mapper for serialization of configurations
`static org.nd4j.shade.jackson.databind.ObjectMapper`	`mapperYaml()` Object mapper for serialization of configurations
`static org.nd4j.shade.jackson.databind.ObjectMapper`	`reinitMapperWithSubtypes(Collection<org.nd4j.shade.jackson.databind.jsontype.NamedType> additionalTypes)` Reinitialize and return the Jackson/json ObjectMapper with additional named types.
`void`	`resetVariables()`
`void`	`setLayerParamLR(String variable)`
`String`	`toJson()` Return this configuration as json
`String`	`toYaml()` Return this configuration as json
`List<String>`	`variables()`
`List<String>`	`variables(boolean copy)`

Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - CUSTOM_FUNCTIONALITY
```
public static final String CUSTOM_FUNCTIONALITY
```
    System property for custom layers, preprocessors, graph vertices etc. Enabled by default. Run JVM with "-Dorg.deeplearning4j.config.custom.enabled=false" to disable classpath scanning for Overriding the default (i.e., disabling) this is only useful if (a) no custom layers/preprocessors etc will be used, and (b) minimizing startup/initialization time for new JVMs is very important. Results are cached, so there is no cost to custom layers after the first network has been constructed.
    
    See Also:
    
    Constant Field Values
  - layer
```
protected Layer layer
```
  - miniBatch
```
protected boolean miniBatch
```
  - maxNumLineSearchIterations
```
protected int maxNumLineSearchIterations
```
  - seed
```
protected long seed
```
  - optimizationAlgo
```
protected OptimizationAlgorithm optimizationAlgo
```
  - variables
```
protected List<String> variables
```
  - stepFunction
```
protected StepFunction stepFunction
```
  - minimize
```
protected boolean minimize
```
  - l1ByParam
```
protected Map<String,Double> l1ByParam
```
  - l2ByParam
```
protected Map<String,Double> l2ByParam
```
  - pretrain
```
protected boolean pretrain
```
  - cacheMode
```
protected CacheMode cacheMode
```
  - iterationCount
```
protected int iterationCount
```
  - epochCount
```
protected int epochCount
```
- Constructor Detail
  - NeuralNetConfiguration
```
public NeuralNetConfiguration()
```
- Method Detail
  - clone
```
public NeuralNetConfiguration clone()
```
    Creates and returns a deep copy of the configuration.
    
    Overrides:
    
    clone in class Object
  - variables
```
public List<String> variables()
```
  - variables
```
public List<String> variables(boolean copy)
```
  - addVariable
```
public void addVariable(String variable)
```
  - clearVariables
```
public void clearVariables()
```
  - resetVariables
```
public void resetVariables()
```
  - setLayerParamLR
```
public void setLayerParamLR(String variable)
```
  - getL1ByParam
```
public double getL1ByParam(String variable)
```
  - getL2ByParam
```
public double getL2ByParam(String variable)
```
  - toYaml
```
public String toYaml()
```
    Return this configuration as json
    
    Returns:
    
    this configuration represented as json
  - fromYaml
```
public static NeuralNetConfiguration fromYaml(String json)
```
    Create a neural net configuration from json
    
    Parameters:
    
    json - the neural net configuration from json
    
    Returns:
  - toJson
```
public String toJson()
```
    Return this configuration as json
    
    Returns:
    
    this configuration represented as json
  - fromJson
```
public static NeuralNetConfiguration fromJson(String json)
```
    Create a neural net configuration from json
    
    Parameters:
    
    json - the neural net configuration from json
    
    Returns:
  - mapperYaml
```
public static org.nd4j.shade.jackson.databind.ObjectMapper mapperYaml()
```
    Object mapper for serialization of configurations
    
    Returns:
  - mapper
```
public static org.nd4j.shade.jackson.databind.ObjectMapper mapper()
```
    Object mapper for serialization of configurations
    
    Returns:
  - reinitMapperWithSubtypes
```
public static org.nd4j.shade.jackson.databind.ObjectMapper reinitMapperWithSubtypes(Collection<org.nd4j.shade.jackson.databind.jsontype.NamedType> additionalTypes)
```
    Reinitialize and return the Jackson/json ObjectMapper with additional named types. This can be used to add additional subtypes at runtime (i.e., for JSON mapping with types defined outside of the main DL4J codebase)

Class NeuralNetConfiguration

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

CUSTOM_FUNCTIONALITY

layer

miniBatch

maxNumLineSearchIterations

seed

optimizationAlgo

variables

stepFunction

minimize

l1ByParam

l2ByParam

pretrain

cacheMode

iterationCount

epochCount

Constructor Detail

NeuralNetConfiguration

Method Detail

clone

variables

variables

addVariable

clearVariables

resetVariables

setLayerParamLR

getL1ByParam

getL2ByParam

toYaml

fromYaml

toJson

fromJson

mapperYaml

mapper

reinitMapperWithSubtypes