ConvNets-TensorFlow2 is a repository that implements a variety of popular Deep Convolutional Network Architectures using TensorFlow2. The core of this repository is intuitive code and concise architecture. If you are a user of TensorFlow2 and want to study various and popular CNN architectures, this repository will be the best choice to study. ConvNets-TensorFlow2 is continuously updated and managed. This repository has been very much influenced by Cifar100-pytorch.
$ python main.py
--nets={NETS}
--batch_size={BATCH_SIZE}
--lr={LEARNING_RATE}
--epochs={EPOCHS}- VGG
- GoogLeNet
- ResNet
- DenseNet
- InceptionV3
- InceptionV4
- MobileNet
- MobileNetV2
- Squeezenet
- SENet
- ShuffleNet
- CondenseNet
- Xcention
- PreActResNet
- ResAttNet
- ResNeXt
- PolyNet
- PyramidNet
Paper Very Deep Convolutional Networks for Large-Scale Image Recognition
Author Karen Simonyan, Andrew Zissermanr
Code VGG.py
Model Options
--nets {VGG11 or VGG13 or VGG16 or VGG19}Paper Going Deeper with Convolutions
Author Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich
Code GoogLeNet.py
Model Options
--nets {GoogLeNet}Paper Deep Residual Learning for Image Recognition
Author Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
Code ResNet.py
Model Options
--nets {ResNet18 or ResNet34 ResNet50 ResNet101 ResNet 152}Paper Densely Connected Convolutional Networks
Author Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger
Code DenseNet.py
Model Options
--nets {DenseNet121 or DenseNet169 or DenseNet201 or DenseNet161}Paper Rethinking the Inception Architecture for Computer Vision
Author Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna
Code InceptionV3.py
Model Options
--nets {InceptionV3}Paper Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Author Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi
Code InceptionV4.py
Model Options
--nets {InceptionV4}Paper MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Author Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam
Code MobileNet.py
Model Options
--nets {MobileNet}Paper MobileNetV2: Inverted Residuals and Linear Bottlenecks
Author Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen
Code MobileNetV2.py
Model Options
--nets {MobileNetV2}Paper SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Author Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer
Code SqueezeNet.py
Model Options
--nets {SqueezeNet}Paper Squeeze-and-Excitation Networks
Author Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu
Code SEResNet.py
Model Options
--nets {SEResNet18 or SEResNet34 or SEResNet50 or SEResNet101 or SEResNet152}Paper ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Author Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun
Code Coming Soon
Model Options
// Coming SoonPaper CondenseNet: An Efficient DenseNet using Learned Group Convolutions
Author Gao Huang, Shichen Liu, Laurens van der Maaten, Kilian Q. Weinberger
Code Coming Soon
Model Options
// Coming SoonPaper Xception: Deep Learning with Depthwise Separable Convolutions
Author François Chollet
Code Coming Soon
Model Options
// Coming SoonPaper Identity Mappings in Deep Residual Networks
Author Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
Code Coming Soon
Model Options
// Coming SoonPaper Residual Attention Network for Image Classification
Author Fei Wang, Mengqing Jiang, Chen Qian, Shuo Yang, Cheng Li, Honggang Zhang, Xiaogang Wang, Xiaoou Tang
Code Coming Soon
Model Options
// Coming SoonPaper PolyNet: A Pursuit of Structural Diversity in Very Deep Networks
Author Xingcheng Zhang, Zhizhong Li, Chen Change Loy, Dahua Lin
Code Coming Soon
Model Options
// Coming SoonPaper Deep Pyramidal Residual Networks
Author Dongyoon Han, Jiwhan Kim, Junmo Kim
Code Coming Soon
Model Options
// Coming Soon