https://github.com/archsyscall/convnets-tensorflow2

⛵️ Implementation a variety of popular Image Classification Models using TensorFlow2. [ResNet, GoogLeNet, VGG, Inception-v3, Inception-v4, MobileNet, MobileNet-v2, ShuffleNet, ShuffleNet-v2, etc...]
https://github.com/archsyscall/convnets-tensorflow2

deep-learning googlenet inception-v3 inception-v4 machine-learning mobilenet mobilenet-v2 resnet shufflenet shufflenet-v2 tensorflow vgg

Last synced: 5 months ago
JSON representation

⛵️ Implementation a variety of popular Image Classification Models using TensorFlow2. [ResNet, GoogLeNet, VGG, Inception-v3, Inception-v4, MobileNet, MobileNet-v2, ShuffleNet, ShuffleNet-v2, etc...]

• Host: GitHub
• URL: https://github.com/archsyscall/convnets-tensorflow2
• Owner: archsyscall
• License: apache-2.0
• Created: 2020-04-22T11:22:01.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2020-05-05T13:49:57.000Z (over 5 years ago)
• Last Synced: 2025-03-30T22:32:21.090Z (6 months ago)
• Topics: deep-learning, googlenet, inception-v3, inception-v4, machine-learning, mobilenet, mobilenet-v2, resnet, shufflenet, shufflenet-v2, tensorflow, vgg
• Language: Python
• Homepage:
• Size: 145 KB
• Stars: 105
• Watchers: 5
• Forks: 31
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
![TF Depend](https://img.shields.io/badge/TensorFlow-2.1-orange) ![License Badge](https://img.shields.io/badge/license-Apache%202-green)




  



Convolutional Nets in TensorFlow2


[ConvNets-TensorFlow2](https://github.com/marload/ConvNetsRL-TensorFlow2) is a repository that implements a variety of popular Deep Convolutional Network Architectures using [TensorFlow2](https://tensorflow.org). 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](https://github.com/weiaicunzai/pytorch-cifar100).

## Usage

```bash

$ python main.py 

    --nets={NETS} 

    --batch_size={BATCH_SIZE} 

    --lr={LEARNING_RATE} 

    --epochs={EPOCHS}

```

## Models

- [VGG](#vgg)

- [GoogLeNet](#googlenet)

- [ResNet](#resnet)

- [DenseNet](#densenet)

- [InceptionV3](#inceptionv3)

- [InceptionV4](#inceptionv4)

- [MobileNet](#mobilenet)

- [MobileNetV2](#mobilenetv2)

- [Squeezenet](#squeezenet)

- [SENet](#senet)

- [ShuffleNet](#shufflenet)

- [CondenseNet](#condenseNet)

- [Xcention](#xception)

- [PreActResNet](#preactresnet)

- [ResAttNet](#resattnet)

- [ResNeXt](#resnext)

- [PolyNet](#polynet)

- [PyramidNet](#pyramidnet)





### VGG

**Paper** [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://arxiv.org/abs/1409.1556)


**Author** Karen Simonyan, Andrew Zissermanr


**Code** [VGG.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/VGG.py)





**Model Options**

```bash

--nets {VGG11 or VGG13 or VGG16 or VGG19}

```





### GoogLeNet

**Paper** [Going Deeper with Convolutions](https://arxiv.org/abs/1409.4842)


**Author** Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich


**Code** [GoogLeNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/GoogLeNet.py)





**Model Options**

```bash

--nets {GoogLeNet}

```





### ResNet

**Paper** [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)


**Author** Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun


**Code** [ResNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/ResNet.py)





**Model Options**

```bash

--nets {ResNet18 or ResNet34 ResNet50 ResNet101 ResNet 152}

```





### DenseNet

**Paper** [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993)


**Author** Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger




**Code** [DenseNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/DenseNet.py)





**Model Options**

```bash

--nets {DenseNet121 or DenseNet169 or DenseNet201 or DenseNet161}

```





### InceptionV3

**Paper** [Rethinking the Inception Architecture for Computer Vision](https://arxiv.org/abs/1512.00567)


**Author** Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna




**Code** [InceptionV3.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/InceptionV3.py)





**Model Options**

```bash

--nets {InceptionV3}

```





### InceptionV4

**Paper** [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://arxiv.org/abs/1602.07261)


**Author** Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi




**Code** [InceptionV4.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/InceptionV4.py)





**Model Options**

```bash

--nets {InceptionV4}

```





### MobileNet

**Paper** [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://arxiv.org/abs/1704.04861)


**Author** Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam




**Code** [MobileNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/MobileNet.py)





**Model Options**

```bash

--nets {MobileNet}

```





### MobileNetV2

**Paper** [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381)


**Author** Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen




**Code** [MobileNetV2.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/MobileNetV2.py)





**Model Options**

```bash

--nets {MobileNetV2}

```





### SqueezeNet

**Paper** [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://arxiv.org/abs/1602.07360)


**Author** Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer




**Code** [SqueezeNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/SqueezeNet.py)





**Model Options**

```bash

--nets {SqueezeNet}

```





### SENet

**Paper** [Squeeze-and-Excitation Networks](https://arxiv.org/abs/1709.01507)


**Author** Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu




**Code** [SEResNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/SEResNet.py)





**Model Options**

```bash

--nets {SEResNet18 or SEResNet34 or SEResNet50 or SEResNet101 or SEResNet152}

```





### ShuffleNet

**Paper** [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://arxiv.org/abs/1707.01083)


**Author** Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun




**Code** Coming Soon





**Model Options**

```bash

// Coming Soon

```





### CondenseNet

**Paper** [CondenseNet: An Efficient DenseNet using Learned Group Convolutions](https://arxiv.org/abs/1711.09224)


**Author** Gao Huang, Shichen Liu, Laurens van der Maaten, Kilian Q. Weinberger




**Code** Coming Soon





**Model Options**

```bash

// Coming Soon

```





### Xception

**Paper** [Xception: Deep Learning with Depthwise Separable Convolutions](https://arxiv.org/abs/1610.02357)


**Author** François Chollet




**Code** Coming Soon





**Model Options**

```bash

// Coming Soon

```





### PreActResNet

**Paper** [Identity Mappings in Deep Residual Networks](https://arxiv.org/abs/1603.05027)


**Author** Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun




**Code** Coming Soon





**Model Options**

```bash

// Coming Soon

```





### ResAttNet

**Paper** [Residual Attention Network for Image Classification](https://arxiv.org/abs/1704.06904)


**Author** Fei Wang, Mengqing Jiang, Chen Qian, Shuo Yang, Cheng Li, Honggang Zhang, Xiaogang Wang, Xiaoou Tang




**Code** Coming Soon





**Model Options**

```bash

// Coming Soon

```





### PolyNet

**Paper** [PolyNet: A Pursuit of Structural Diversity in Very Deep Networks](https://arxiv.org/abs/1611.05725)


**Author** Xingcheng Zhang, Zhizhong Li, Chen Change Loy, Dahua Lin




**Code** Coming Soon





**Model Options**

```bash

// Coming Soon

```





### PyramidNet

**Paper** [Deep Pyramidal Residual Networks](https://arxiv.org/abs/1610.02915)


**Author** Dongyoon Han, Jiwhan Kim, Junmo Kim




**Code** Coming Soon





**Model Options**

```bash

// Coming Soon

```



## Reference

- https://github.com/weiaicunzai/pytorch-cifar100

- https://github.com/tensorflow/tensorflow