All Classes and Interfaces
Class
Description
AlexNet
contains a generic implementation of AlexNet adapted from [torchvision
implmentation](https://github.com/pytorch/vision/blob/master/torchvision/models/alexnet.py)The Builder to construct a
AlexNet
object.Model Zoo is a repository that contains all models for DJL.
An imperative model zoo provider implements the
ZooProvider
interface.GoogLeNet uses a stack of a total of 9 inception blocks and global average pooling to generate
its estimates.
The Builder to construct a
GoogLeNet
object.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/).
The Builder to construct a
LeNet
object.Multilayer Perceptron (MLP) NeuralNetworks.
A
BlockFactory
class that creates MLP block.MobileNetV1
contains a generic implementation of Mobilenet adapted from
https://github.com/weiaicunzai/pytorch-cifar100/blob/master/models/mobilenet.py (Original author
weiaicunzai).The Builder to construct a
MobileNetV1
object.MobileNetV2
contains a generic implementation of MobilenetV2 adapted from
https://github.com/weiaicunzai/pytorch-cifar100/blob/master/models/mobilenetv2.py (Original
author weiaicunzai).The Builder to construct a
MobileNetV2
object.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.
The Builder to construct a
NiN
object.A
BlockFactory
class that creates ResNetV1
block.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.The Builder to construct a
ResNetV1
object.SimpleTextDecoder
implements a Decoder
that employs a RecurrentBlock
to
decode text input.SimpleTextEncoder
implements a Encoder
that employs a RecurrentBlock
to
encode text input.SingleShotDetection
is an implementation of Block
that implements a Single Shot
Detection (SSD) model for object detection.The Builder to construct a
SingleShotDetection
.SqueezeNet
contains a generic implementation of Squeezenet adapted from [torchvision
implmentation](https://github.com/pytorch/vision/blob/master/torchvision/models/squeezenet.py)A
BlockFactory
class that creates SingleShotDetection
block.TabNet
contains a generic implementation of TabNet adapted from
https://towardsdatascience.com/implementing-tabnet-in-pytorch-fc977c383279 (Original author
Samrat Thapa)AttentionTransformer is where the tabNet models learn the relationship between relevant
features, and decides which features to pass on to the feature transformer of the current
decision step.
The Builder to construct a
TabNet
object.DecisionStep is just combining featureTransformer and attentionTransformer together.
VGG model from the "Very Deep Convolutional Networks for Large-Scale Image Recognition"
https://arxiv.org/abs/1409.1556 paper.
The Builder to construct a
VGG
object.YOLOV3
contains a generic implementation of yolov3 (Original author bubbliiiing).The Builder to construct a
YOLOV3
object.