A B C F G I L M N O R S V

A

ai.djl.basicmodelzoo - package ai.djl.basicmodelzoo

Contains the built-in BasicModelZoo.

ai.djl.basicmodelzoo.basic - package ai.djl.basicmodelzoo.basic

Contains the basic built-in models.

ai.djl.basicmodelzoo.cv.classification - package ai.djl.basicmodelzoo.cv.classification

Contains classes for the Application.CV.IMAGE_CLASSIFICATION models in the BasicModelZoo.

ai.djl.basicmodelzoo.cv.object_detection.ssd - package ai.djl.basicmodelzoo.cv.object_detection.ssd

Contains classes for the Application.CV.OBJECT_DETECTION models in the BasicModelZoo.

ai.djl.basicmodelzoo.nlp - package ai.djl.basicmodelzoo.nlp

Contains classes for the natural language processing section (Application.NLP) of the BasicModelZoo.

AlexNet - Class in ai.djl.basicmodelzoo.cv.classification

AlexNet contains a generic implementation of AlexNet adapted from [torchvision implmentation](https://github.com/pytorch/vision/blob/master/torchvision/models/alexnet.py)

alexNet(AlexNet.Builder) - Static method in class ai.djl.basicmodelzoo.cv.classification.AlexNet

Creates a AlexNet network block with the help of the AlexNet Builder.

AlexNet.Builder - Class in ai.djl.basicmodelzoo.cv.classification

The Builder to construct a AlexNet object.

B

BasicModelZoo - Class in ai.djl.basicmodelzoo

Model Zoo is a repository that contains all models for DJL.

BasicModelZoo() - Constructor for class ai.djl.basicmodelzoo.BasicModelZoo

BasicZooProvider - Class in ai.djl.basicmodelzoo

An imperative model zoo provider implements the ZooProvider interface.

BasicZooProvider() - Constructor for class ai.djl.basicmodelzoo.BasicZooProvider

build() - Method in class ai.djl.basicmodelzoo.cv.classification.AlexNet.Builder

Builds a AlexNet block.

build() - Method in class ai.djl.basicmodelzoo.cv.classification.GoogLeNet.Builder

Builds a GoogLeNet block.

build() - Method in class ai.djl.basicmodelzoo.cv.classification.LeNet.Builder

Builds a LeNet block.

build() - Method in class ai.djl.basicmodelzoo.cv.classification.NiN.Builder

Builds a NiN block.

build() - Method in class ai.djl.basicmodelzoo.cv.classification.ResNetV1.Builder

Builds a ResNetV1 block.

build() - Method in class ai.djl.basicmodelzoo.cv.classification.VGG.Builder

Builds a VGG block.

build() - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection.Builder

Builds a SingleShotDetection block.

builder() - Static method in class ai.djl.basicmodelzoo.cv.classification.AlexNet

Creates a builder to build a AlexNet.

builder() - Static method in class ai.djl.basicmodelzoo.cv.classification.GoogLeNet

Creates a builder to build a GoogLeNet.

builder() - Static method in class ai.djl.basicmodelzoo.cv.classification.LeNet

Creates a builder to build a LeNet.

builder() - Static method in class ai.djl.basicmodelzoo.cv.classification.NiN

Creates a builder to build a NiN.

builder() - Static method in class ai.djl.basicmodelzoo.cv.classification.ResNetV1

Creates a builder to build a ResNetV1.

builder() - Static method in class ai.djl.basicmodelzoo.cv.classification.VGG

Creates a builder to build a VGG.

Builder() - Constructor for class ai.djl.basicmodelzoo.cv.classification.VGG.Builder

builder() - Static method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection

Creates a builder to build a SingleShotDetection.

C

createModel(String, Device, Artifact, Map<String, Object>, String) - Method in class ai.djl.basicmodelzoo.cv.classification.MlpModelLoader

createModel(String, Device, Artifact, Map<String, Object>, String) - Method in class ai.djl.basicmodelzoo.cv.classification.ResNetModelLoader

createModel(String, Device, Artifact, Map<String, Object>, String) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SsdModelLoader

F

forwardInternal(ParameterStore, NDList, boolean, PairList<String, Object>) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection

forwardInternal(ParameterStore, NDList, boolean, PairList<String, Object>) - Method in class ai.djl.basicmodelzoo.nlp.SimpleTextDecoder

G

getAnchorPredictionBlock(int) - Static method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection

Creates a anchor prediction block used in an SSD.

getClassPredictionBlock(int, int) - Static method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection

Creates a class prediction block used in an SSD.

getDownSamplingBlock(int) - Static method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection

Creates a Block that reduces the size of a convolutional block by half.

getGroupId() - Method in class ai.djl.basicmodelzoo.BasicModelZoo

getModelZoo() - Method in class ai.djl.basicmodelzoo.BasicZooProvider

getOutputShapes(Shape[]) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection

getStates(NDList) - Method in class ai.djl.basicmodelzoo.nlp.SimpleTextEncoder

getSupportedEngines() - Method in class ai.djl.basicmodelzoo.BasicModelZoo

GoogLeNet - Class in ai.djl.basicmodelzoo.cv.classification

GoogLeNet uses a stack of a total of 9 inception blocks and global average pooling to generate its estimates.

googLeNet(GoogLeNet.Builder) - Static method in class ai.djl.basicmodelzoo.cv.classification.GoogLeNet

Creates a GoogLeNet network block with the help of the GoogLeNet Builder.

GoogLeNet.Builder - Class in ai.djl.basicmodelzoo.cv.classification

The Builder to construct a GoogLeNet object.

GROUP_ID - Static variable in class ai.djl.basicmodelzoo.BasicModelZoo

I

inceptionBlock(int, int[], int[], int) - Method in class ai.djl.basicmodelzoo.cv.classification.GoogLeNet

Creates a constituent inception block that becomes a part of the whole GoogLeNet model.

initialize(NDManager, DataType, Shape...) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection

L

LeNet - Class in ai.djl.basicmodelzoo.cv.classification

The model was introduced (and named for) Yann Lecun, for the purpose of recognizing handwritten digits in images [LeNet5](http://yann.lecun.com/exdb/lenet/).

leNet(LeNet.Builder) - Static method in class ai.djl.basicmodelzoo.cv.classification.LeNet

Creates a LeNet network block with the help of the LeNet Builder.

LeNet.Builder - Class in ai.djl.basicmodelzoo.cv.classification

The Builder to construct a LeNet object.

loadMetadata(byte, DataInputStream) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection

M

Mlp - Class in ai.djl.basicmodelzoo.basic

Multilayer Perceptron (MLP) NeuralNetworks.

Mlp(int, int, int[]) - Constructor for class ai.djl.basicmodelzoo.basic.Mlp

Create an MLP NeuralNetwork using RELU.

Mlp(int, int, int[], Function<NDList, NDList>) - Constructor for class ai.djl.basicmodelzoo.basic.Mlp

Create an MLP NeuralNetwork.

MLP - Static variable in class ai.djl.basicmodelzoo.BasicModelZoo

MlpModelLoader - Class in ai.djl.basicmodelzoo.cv.classification

Model loader for MLP models.

MlpModelLoader(Repository) - Constructor for class ai.djl.basicmodelzoo.cv.classification.MlpModelLoader

Creates the Model loader from the given repository.

N

NiN - Class in ai.djl.basicmodelzoo.cv.classification

NiN uses convolutional layers with window shapes of 11×11 , 5×5 , and 3×3 , and the corresponding numbers of output channels are the same as in AlexNet.

niN(NiN.Builder) - Static method in class ai.djl.basicmodelzoo.cv.classification.NiN

The NiN block consists of one convolutional layer followed by two 1×1 convolutional layers that act as per-pixel fully-connected layers with ReLU activations.

NiN.Builder - Class in ai.djl.basicmodelzoo.cv.classification

The Builder to construct a NiN object.

niNBlock(int, Shape, Shape, Shape) - Method in class ai.djl.basicmodelzoo.cv.classification.NiN

Creates a constituent NiN block that becomes a part of the whole NiN model.

O

optBatchNormMomentum(float) - Method in class ai.djl.basicmodelzoo.cv.classification.ResNetV1.Builder

Sets the momentum of batchNorm layer.

optFeatures(List<Block>) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection.Builder

Sets the Conv2d blocks to be appended to the network to get multi-output network.

optGlobalPool(boolean) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection.Builder

Sets the boolean whether to attach a global average pooling layer as the last output layer.

R

residualUnit(int, Shape, boolean, boolean, float) - Static method in class ai.djl.basicmodelzoo.cv.classification.ResNetV1

Builds a Block that represents a residual unit used in the implementation of the Resnet model.

RESNET - Static variable in class ai.djl.basicmodelzoo.BasicModelZoo

resnet(ResNetV1.Builder) - Static method in class ai.djl.basicmodelzoo.cv.classification.ResNetV1

Creates a new Block of ResNetV1 with the arguments from the given ResNetV1.Builder.

ResNetModelLoader - Class in ai.djl.basicmodelzoo.cv.classification

Model loader for ResNet_V1.

ResNetModelLoader(Repository) - Constructor for class ai.djl.basicmodelzoo.cv.classification.ResNetModelLoader

Creates the Model loader from the given repository.

ResNetV1 - Class in ai.djl.basicmodelzoo.cv.classification

ResNetV1 contains a generic implementation of ResNet adapted from https://github.com/tornadomeet/ResNet/blob/master/symbol_resnet.py (Original author Wei Wu) by Antti-Pekka Hynninen.

ResNetV1.Builder - Class in ai.djl.basicmodelzoo.cv.classification

The Builder to construct a ResNetV1 object.

S

setBaseNetwork(Block) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection.Builder

Sets the base network for the SSD framework.

setConvArch(int[][]) - Method in class ai.djl.basicmodelzoo.cv.classification.VGG.Builder

Sets the number of blocks according to the user.

setDropOutRate(float) - Method in class ai.djl.basicmodelzoo.cv.classification.AlexNet.Builder

Sets the dropout rate in the network.

setDropOutRate(float) - Method in class ai.djl.basicmodelzoo.cv.classification.NiN.Builder

Sets the dropout rate in the network.

setImageShape(Shape) - Method in class ai.djl.basicmodelzoo.cv.classification.ResNetV1.Builder

Sets the shape of the image.

setNumChannels(int[]) - Method in class ai.djl.basicmodelzoo.cv.classification.AlexNet.Builder

Sets the number of channels for the AlexNet blocks.

setNumChannels(int[]) - Method in class ai.djl.basicmodelzoo.cv.classification.LeNet.Builder

Sets the number of channels for the LeNet blocks.

setNumChannels(int[]) - Method in class ai.djl.basicmodelzoo.cv.classification.NiN.Builder

Sets the number of channels for the niN blocks.

setNumClasses(int) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection.Builder

Sets the number of classes of objects to be detected.

setNumFeatures(int) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection.Builder

Sets the number of down sampling blocks to be applied.

setNumLayers(int) - Method in class ai.djl.basicmodelzoo.cv.classification.ResNetV1.Builder

Sets the number of layers in the network.

setNumLayers(int) - Method in class ai.djl.basicmodelzoo.cv.classification.VGG.Builder

Sets the number of layers.

setOutSize(long) - Method in class ai.djl.basicmodelzoo.cv.classification.ResNetV1.Builder

Sets the size of the output.

setRatios(List<List<Float>>) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection.Builder

Sets the list of aspect ratios of generated anchor boxes.

setSizes(List<List<Float>>) - Method in class ai.djl.basicmodelzoo.cv.object_detection.ssd.SingleShotDetection.Builder

Sets the list of sizes of generated anchor boxes.

SimpleTextDecoder - Class in ai.djl.basicmodelzoo.nlp

SimpleTextDecoder implements a Decoder that employs a RecurrentBlock to decode text input.

SimpleTextDecoder(RecurrentBlock, int) - Constructor for class ai.djl.basicmodelzoo.nlp.SimpleTextDecoder

Contructs a new instance of SimpleTextDecoder with the given RecurrentBlock.

SimpleTextDecoder(TrainableTextEmbedding, RecurrentBlock, long) - Constructor for class ai.djl.basicmodelzoo.nlp.SimpleTextDecoder

Contructs a new instance of SimpleTextDecoder with the given RecurrentBlock.

SimpleTextEncoder - Class in ai.djl.basicmodelzoo.nlp

SimpleTextEncoder implements a Encoder that employs a RecurrentBlock to encode text input.

SimpleTextEncoder(RecurrentBlock) - Constructor for class ai.djl.basicmodelzoo.nlp.SimpleTextEncoder

Contructs a new instance of SimpleTextEncoder with the given RecurrentBlock.

SimpleTextEncoder(TrainableTextEmbedding, RecurrentBlock) - Constructor for class ai.djl.basicmodelzoo.nlp.SimpleTextEncoder

Contructs a new instance of SimpleTextEncoder with the given RecurrentBlock and TrainableTextEmbedding.

SingleShotDetection - Class in ai.djl.basicmodelzoo.cv.object_detection.ssd

SingleShotDetection is an implementation of Block that implements a Single Shot Detection (SSD) model for object detection.

SingleShotDetection.Builder - Class in ai.djl.basicmodelzoo.cv.object_detection.ssd

The Builder to construct a SingleShotDetection.

SqueezeNet - Class in ai.djl.basicmodelzoo.cv.classification

SqueezeNet contains a generic implementation of Squeezenet adapted from [torchvision implmentation](https://github.com/pytorch/vision/blob/master/torchvision/models/squeezenet.py)

squeezenet(int) - Static method in class ai.djl.basicmodelzoo.cv.classification.SqueezeNet

Construct squeezenet v1.1.

SSD - Static variable in class ai.djl.basicmodelzoo.BasicModelZoo

SsdModelLoader - Class in ai.djl.basicmodelzoo.cv.object_detection.ssd

Model loader for SingleShotDetection(SSD).

SsdModelLoader(Repository) - Constructor for class ai.djl.basicmodelzoo.cv.object_detection.ssd.SsdModelLoader

Creates the Model loader from the given repository.

V

VGG - Class in ai.djl.basicmodelzoo.cv.classification

VGG model from the "Very Deep Convolutional Networks for Large-Scale Image Recognition" https://arxiv.org/abs/1409.1556 paper.

vgg(VGG.Builder) - Static method in class ai.djl.basicmodelzoo.cv.classification.VGG

Creates a VGG block with the help of the VGG Builder.

VGG.Builder - Class in ai.djl.basicmodelzoo.cv.classification

The Builder to construct a VGG object.

vggBlock(int, int) - Method in class ai.djl.basicmodelzoo.cv.classification.VGG

Creates a constituent VGG block that becomes a part of the whole VGG model.

A B C F G I L M N O R S V