weka.dl4j.zoo

Class Dl4jVGG

java.lang.Object

weka.dl4j.zoo.AbstractZooModel

weka.dl4j.zoo.Dl4jVGG

All Implemented Interfaces:

java.io.Serializable, weka.core.OptionHandler

public class Dl4jVGG
extends AbstractZooModel

A WEKA version of DeepLearning4j's VGG16 ZooModel. Pretrained weights notes: VGG16 CIFAR10 - Download link possibly broken on DL4J end? The downloaded zip for these weights is only 10mb vs 513mb for Imagenet

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
Dl4jVGG() Instantiate the model.

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.dataset.api.preprocessor.ImagePreProcessingScaler	getImagePreprocessingScaler() Get the preprocessor to process this model's data with
int[]	getInputShape() Get the input shape of this zoomodel
VGG.VARIATION	getVariation() Get the current variation of the zoo model (e.g., Resnet50 or Resnet101)
org.deeplearning4j.nn.graph.ComputationGraph	init(int numLabels, long seed, int[] shape, boolean filterMode) Initialize the ZooModel as MLP.
void	setPretrainedType(PretrainedType pretrainedType)
void	setVariation(VGG.VARIATION var)

Methods inherited from class weka.dl4j.zoo.AbstractZooModel

getChannelsLast, getDefaultGraph, getExtraLayersToRemove, getFeatureExtractionLayer, getNumFExtractOutputs, getOptions, getOutputlayer, getPretrainedType, getPrettyName, initZooModel, isPretrained, isRequiresPooling, listOptions, requiresPreProcessing, setChannelsLast, setExtraLayersToRemove, setFeatureExtractionLayer, setNumFExtractOutputs, setOptions, setOutputLayer, setRequiresPooling

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface weka.core.OptionHandler

makeCopy

Constructor Detail

Dl4jVGG

public Dl4jVGG()

Instantiate the model.

Method Detail

getVariation

@OptionMetadata(description="The model variation to use.",
                displayName="Model Variation",
                commandLineParamName="variation",
                commandLineParamSynopsis="-variation <String>")
public VGG.VARIATION getVariation()

Description copied from class: AbstractZooModel

Get the current variation of the zoo model (e.g., Resnet50 or Resnet101)

Specified by:

getVariation in class AbstractZooModel

Returns:

Variation

getImagePreprocessingScaler

public org.nd4j.linalg.dataset.api.preprocessor.ImagePreProcessingScaler getImagePreprocessingScaler()

Description copied from class: AbstractZooModel

Get the preprocessor to process this model's data with

Specified by:

getImagePreprocessingScaler in class AbstractZooModel

Returns:

DataSetPreprocessor

setVariation

public void setVariation(VGG.VARIATION var)

setPretrainedType

public void setPretrainedType(PretrainedType pretrainedType)

Overrides:

setPretrainedType in class AbstractZooModel

init

public org.deeplearning4j.nn.graph.ComputationGraph init(int numLabels,
                                                         long seed,
                                                         int[] shape,
                                                         boolean filterMode)

Description copied from class: AbstractZooModel

Initialize the ZooModel as MLP.

Specified by:

init in class AbstractZooModel

Parameters:

numLabels - Number of labels to adjust the output

seed - Seed

shape - shape

filterMode - True if creating for feature extraction

Returns:

MultiLayerNetwork of the specified ZooModel

getInputShape

public int[] getInputShape()

Description copied from class: AbstractZooModel

Get the input shape of this zoomodel

Specified by:

getInputShape in class AbstractZooModel

Returns:

Input shape of this zoomodel