Package ai.djl.basicmodelzoo.cv.classification
package ai.djl.basicmodelzoo.cv.classification
Contains classes for the
Application.CV.IMAGE_CLASSIFICATION models in the BasicModelZoo.-
ClassesClassDescription
AlexNetcontains a generic implementation of AlexNet adapted from [torchvision implmentation](https://github.com/pytorch/vision/blob/master/torchvision/models/alexnet.py)The Builder to construct aAlexNetobject.GoogLeNet uses a stack of a total of 9 inception blocks and global average pooling to generate its estimates.The Builder to construct aGoogLeNetobject.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 aLeNetobject.MobileNetV1contains 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 aMobileNetV1object.MobileNetV2contains 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 aMobileNetV2object.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 aNiNobject.ABlockFactoryclass that createsResNetV1block.ResNetV1contains 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 aResNetV1object.SqueezeNetcontains a generic implementation of Squeezenet adapted from [torchvision implmentation](https://github.com/pytorch/vision/blob/master/torchvision/models/squeezenet.py)VGG model from the "Very Deep Convolutional Networks for Large-Scale Image Recognition" https://arxiv.org/abs/1409.1556 paper.The Builder to construct aVGGobject.