guoyuantao/Classification_model

The mainstream model of image classification is realized in this work. LeNet、VGG、Inception v1、v2、v3、v4、ResNet、SENet、ShuffleNet、MobileNet、GhostNet...

CNN_Model

Implement all convolutional neural networks

CNN Origin：

• Neocognitron: A Self-organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position (Kunihiko Fukushima -1980)

LeNet5：

• Backpropagation Applied to Handwritten Zip Code Recognition (Y. LeCun -1989)
• Gradient-Based Learning Applied to Document Recognition (Y. LeCun -1998)

AlexNet：

• ImageNet Classification with Deep Convolutional Neural Networks (Alex Krizhevsky -2012)

ZFNet：

• Visualizing and Understanding Convolutional Networks (Matthew D. Zeiler -2013)

NIN：

• Network In Network (Min Lin -2014)

GoogleLeNet(Inception v1)：

• Going deeper with convolutions (Christian Szegedy -2014)

VGGNet：

• Very Deep Convolutional Network For Large-Scale Image Recognition (Karen Simonyan -2014)

Inception v2：

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (Sergey Ioffe -2015)

Inception v3：

• Rethinking the Inception Architecture for Computer Vision (Christian Szegedy -2015)

ResNet v1：

• Deep Residual Learning for Image Recognition (Kaiming He -2015)

ResNet v2：

• Identity Mappings in Deep Residual Networks(Kaiming He -2016)

Stochastic Depth：

• Deep Networks with Stochastic Depth (Huang Gao 2016)

WideResNet：

• Wide Residual Networks (Sergey Zagoruyko 2016)

RiR：

• Resnet in Resnet: Generalizing Residual Architectures (Sasha Targ 2016)

Inception v4、Inception-ResNet v1 and Inception-ResNet v2：

• Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (Christian Szegedy 2016)

FractalNet：

• FractalNet: Ultra-Deep Neural Networks without Residuals (Gustav Larsson 2016)

ResNeXt：

• Aggregated Residual Transformations for Deep Neural Networks (Saining Xie 2016)

DenseNet：

• Densely Connected Convolutional Networks (wang Gao 2017)

DPN：

• Dual Path Networks (Yunpeng Chen, 颜水成（360） 2017)

PyramidNet：

• Deep Pyramidal Residual Networks (Dongyoon Han, Jiwhan Kim 2017)

SENet：

• Squeeze-and-Excitation Networks (Hu jie 2017)

SqueezeNet：

• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size (Berkeley and Stanford 2017)

MobileNets V1：

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (Google 2017)

MobileNets V2：

• MobileNetV2: Inverted Residuals and Linear Bottlenecks (Google 2018)

ShuffleNet V1：

• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices (Xiangyu Zhang,Jian Sun 2017)

ShuffleNet V2：

• ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design (Ningning Ma, Xiangyu Zhang 2018)

MobileNet V3：

• Searching for MobileNetV3 (Google 2019)

EfficientNet：

• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (Google 2019)

GhostNet：

• GhostNet: More Features from Cheap Operations (Kai Han, Yunhe Wang 2020)

RegNet：

• Designing Network Design Spaces (Ilija Radosavovic Kaiming He 2020)