Paper: 131116 Netowork In Network
Implementation: https://github.com/nutszebra/network_in_network
Paper: 131116 Netowork In Network
Implementations: https://github.com/nutszebra/network_in_network_with_bn
Paper: 140904 Very Deep Convolutional Networks for Large-Scale Image Recognition
Implementaion: https://github.com/nutszebra/vgg
Paper: 140917 Going deeper with convolutions
Impelementation: https://github.com/nutszebra/googlenet
Paper: 150211 Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Implementaion: https://github.com/nutszebra/googlenet_v2
Paper: 151202 Rethinking the Inception Architecture for Computer Vision
Implementaion: https://github.com/nutszebra/googlenet_v3
Paper: 150206 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Implementaion: https://github.com/nutszebra/prelu_net
Paper: 150722 Training Very Deep Networks
Implementaion: https://github.com/nutszebra/highway_networks
Paper: 151210 Deep Residual Learning for Image Recognition
Implementaion: https://github.com/nutszebra/original_residual_net
Paper: 160223 Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Implementaion: soon
Paper: 160224 SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Implementaion: https://github.com/nutszebra/squeeze_net
Paper: 160316 Identity Mappings in Deep Residual Networks
Implementaion: https://github.com/nutszebra/residual_net
Paper: 160325 Resnet in Resnet: Generalizing Residual Architectures
Implementation: https://github.com/nutszebra/resnet_in_resnet
Paper: 160330 Deep Networks with Stochastic Depth
Implementaion: https://github.com/nutszebra/stochastic_depth
Paper: 160520 Swapout: Learning an ensemble of deep architectures
Implementaion: https://github.com/nutszebra/swapout
Paper: 160523 Wide Residual Networks
Implementaion: https://github.com/nutszebra/wide_residual_net
Paper: 160524 FractalNet: Ultra-Deep Neural Networks without Residuals
Implementaion: https://github.com/nutszebra/fractal_net
Paper: 160528 Weighted Residuals for Very Deep Networks
Implementaion: https://github.com/nutszebra/weighted_residual_net
Paper: 160809 Residual Networks of Residual Networks: Multilevel Residual Networks
Implementaion: https://github.com/nutszebra/residual_networks_of_residual_networks
Paper: 160825 Densely Connected Convolutional Networks
Implementaion: https://github.com/nutszebra/dense_net
Paper: 161007 Xception: Deep Learning with Depthwise Separable Convolutions
Implementaion: soon
Paper:161010 Deep Pyramidal Residual Networks
Implementaion: https://github.com/nutszebra/pyramidal_residual_networks
Paper: 161105 Neural Architecture Search with Reinforcement Learning
Implementaion: https://github.com/nutszebra/neural_architecture_search_with_reinforcement_learning_appendix_a
Paper: 161116 Aggregated Residual Transformations for Deep Neural Networks
Implementaion: https://github.com/nutszebra/resnext
Paper: 161205 Deep Pyramidal Residual Networks with Separated Stochastic Depth
Implementaion: https://github.com/nutszebra/pyramidal_residual_networks_with_separated_stochastic_depth