{"id":27897162,"url":"https://github.com/archsyscall/convnets-tensorflow2","last_synced_at":"2025-05-05T17:05:15.879Z","repository":{"id":119376382,"uuid":"257879535","full_name":"archsyscall/ConvNets-TensorFlow2","owner":"archsyscall","description":"⛵️ Implementation a variety of popular Image Classification Models using TensorFlow2. [ResNet, GoogLeNet, VGG, Inception-v3, Inception-v4, MobileNet, MobileNet-v2, ShuffleNet, ShuffleNet-v2, etc...]","archived":false,"fork":false,"pushed_at":"2020-05-05T13:49:57.000Z","size":148,"stargazers_count":105,"open_issues_count":3,"forks_count":31,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-03-30T22:32:21.090Z","etag":null,"topics":["deep-learning","googlenet","inception-v3","inception-v4","machine-learning","mobilenet","mobilenet-v2","resnet","shufflenet","shufflenet-v2","tensorflow","vgg"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/archsyscall.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-04-22T11:22:01.000Z","updated_at":"2025-01-12T11:14:55.000Z","dependencies_parsed_at":null,"dependency_job_id":"d62c14b3-599e-4ca0-9fef-8b1b5fa58346","html_url":"https://github.com/archsyscall/ConvNets-TensorFlow2","commit_stats":null,"previous_names":["archsyscall/convnets-tensorflow2"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archsyscall%2FConvNets-TensorFlow2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archsyscall%2FConvNets-TensorFlow2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archsyscall%2FConvNets-TensorFlow2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/archsyscall%2FConvNets-TensorFlow2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/archsyscall","download_url":"https://codeload.github.com/archsyscall/ConvNets-TensorFlow2/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252542062,"owners_count":21764907,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","googlenet","inception-v3","inception-v4","machine-learning","mobilenet","mobilenet-v2","resnet","shufflenet","shufflenet-v2","tensorflow","vgg"],"created_at":"2025-05-05T17:05:12.184Z","updated_at":"2025-05-05T17:05:15.871Z","avatar_url":"https://github.com/archsyscall.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![TF Depend](https://img.shields.io/badge/TensorFlow-2.1-orange) ![License Badge](https://img.shields.io/badge/license-Apache%202-green)\u003cbr\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"150\" src=\"./assets/logo.png\"\u003e\n\u003c/p\u003e\n\n\u003ch2 align=center\u003eConvolutional Nets in TensorFlow2\u003c/h2\u003e\n\n[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).\n\n## Usage\n```bash\n$ python main.py \n    --nets={NETS} \n    --batch_size={BATCH_SIZE} \n    --lr={LEARNING_RATE} \n    --epochs={EPOCHS}\n```\n\n## Models\n\n- [VGG](#vgg)\n- [GoogLeNet](#googlenet)\n- [ResNet](#resnet)\n- [DenseNet](#densenet)\n- [InceptionV3](#inceptionv3)\n- [InceptionV4](#inceptionv4)\n- [MobileNet](#mobilenet)\n- [MobileNetV2](#mobilenetv2)\n- [Squeezenet](#squeezenet)\n- [SENet](#senet)\n- [ShuffleNet](#shufflenet)\n- [CondenseNet](#condenseNet)\n- [Xcention](#xception)\n- [PreActResNet](#preactresnet)\n- [ResAttNet](#resattnet)\n- [ResNeXt](#resnext)\n- [PolyNet](#polynet)\n- [PyramidNet](#pyramidnet)\n\n\n\u003chr\u003e\n\n\u003ca name='vgg'\u003e\u003c/a\u003e\n\n### VGG\n\n**Paper** [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://arxiv.org/abs/1409.1556)\u003cbr\u003e\n**Author** Karen Simonyan, Andrew Zissermanr\u003cbr\u003e\n**Code** [VGG.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/VGG.py)\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n--nets {VGG11 or VGG13 or VGG16 or VGG19}\n```\n\n\u003chr\u003e\n\n\u003ca name='googlenet'\u003e\u003c/a\u003e\n\n### GoogLeNet\n\n**Paper** [Going Deeper with Convolutions](https://arxiv.org/abs/1409.4842)\u003cbr\u003e\n**Author** Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich\u003cbr\u003e\n**Code** [GoogLeNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/GoogLeNet.py)\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n--nets {GoogLeNet}\n```\n\n\u003chr\u003e\n\n\u003ca name='resnet'\u003e\u003c/a\u003e\n\n### ResNet\n\n**Paper** [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)\u003cbr\u003e\n**Author** Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun\u003cbr\u003e\n**Code** [ResNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/ResNet.py)\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n--nets {ResNet18 or ResNet34 ResNet50 ResNet101 ResNet 152}\n```\n\n\u003chr\u003e\n\u003ca name='densenet'\u003e\u003c/a\u003e\n\n### DenseNet\n\n**Paper** [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993)\u003cbr\u003e\n**Author** Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger\n\u003cbr\u003e\n**Code** [DenseNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/DenseNet.py)\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n--nets {DenseNet121 or DenseNet169 or DenseNet201 or DenseNet161}\n```\n\n\u003chr\u003e\n\n\n\u003ca name='inceptionv3'\u003e\u003c/a\u003e\n\n### InceptionV3\n\n**Paper** [Rethinking the Inception Architecture for Computer Vision](https://arxiv.org/abs/1512.00567)\u003cbr\u003e\n**Author** Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna\n\u003cbr\u003e\n**Code** [InceptionV3.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/InceptionV3.py)\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n--nets {InceptionV3}\n```\n\n\u003chr\u003e\n\n\u003ca name='inceptionv4'\u003e\u003c/a\u003e\n\n### InceptionV4\n\n**Paper** [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://arxiv.org/abs/1602.07261)\u003cbr\u003e\n**Author** Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi\n\u003cbr\u003e\n**Code** [InceptionV4.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/InceptionV4.py)\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n--nets {InceptionV4}\n```\n\n\u003chr\u003e\n\n\u003ca name='mobilenet'\u003e\u003c/a\u003e\n\n### MobileNet\n\n**Paper** [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://arxiv.org/abs/1704.04861)\u003cbr\u003e\n**Author** Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam\n\u003cbr\u003e\n**Code** [MobileNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/MobileNet.py)\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n--nets {MobileNet}\n```\n\n\u003chr\u003e\n\n\u003ca name='mobilenetv2'\u003e\u003c/a\u003e\n\n### MobileNetV2\n\n**Paper** [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381)\u003cbr\u003e\n**Author** Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen\n\u003cbr\u003e\n**Code** [MobileNetV2.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/MobileNetV2.py)\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n--nets {MobileNetV2}\n```\n\n\u003chr\u003e\n\n\u003ca name='squeezenet'\u003e\u003c/a\u003e\n\n### SqueezeNet\n\n**Paper** [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \u003c0.5MB model size](https://arxiv.org/abs/1602.07360)\u003cbr\u003e\n**Author** Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer\n\u003cbr\u003e\n**Code** [SqueezeNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/SqueezeNet.py)\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n--nets {SqueezeNet}\n```\n\n\u003chr\u003e\n\n\u003ca name='SENet'\u003e\u003c/a\u003e\n\n### SENet\n\n**Paper** [Squeeze-and-Excitation Networks](https://arxiv.org/abs/1709.01507)\u003cbr\u003e\n**Author** Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu\n\u003cbr\u003e\n**Code** [SEResNet.py](https://github.com/marload/ConvNets-TensorFlow2/blob/master/models/SEResNet.py)\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n--nets {SEResNet18 or SEResNet34 or SEResNet50 or SEResNet101 or SEResNet152}\n```\n\n\u003chr\u003e\n\n\u003ca name='shufflenet'\u003e\u003c/a\u003e\n\n### ShuffleNet\n\n**Paper** [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://arxiv.org/abs/1707.01083)\u003cbr\u003e\n**Author** Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun\n\u003cbr\u003e\n**Code** Coming Soon\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n// Coming Soon\n```\n\n\u003chr\u003e\n\n\u003ca name='condensenet'\u003e\u003c/a\u003e\n\n### CondenseNet\n\n**Paper** [CondenseNet: An Efficient DenseNet using Learned Group Convolutions](https://arxiv.org/abs/1711.09224)\u003cbr\u003e\n**Author** Gao Huang, Shichen Liu, Laurens van der Maaten, Kilian Q. Weinberger\n\u003cbr\u003e\n**Code** Coming Soon\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n// Coming Soon\n```\n\n\u003chr\u003e\n\n\u003ca name='xception'\u003e\u003c/a\u003e\n\n### Xception\n\n**Paper** [Xception: Deep Learning with Depthwise Separable Convolutions](https://arxiv.org/abs/1610.02357)\u003cbr\u003e\n**Author** François Chollet\n\u003cbr\u003e\n**Code** Coming Soon\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n// Coming Soon\n```\n\n\u003chr\u003e\n\n\u003ca name='preactresnet'\u003e\u003c/a\u003e\n\n### PreActResNet\n\n**Paper** [Identity Mappings in Deep Residual Networks](https://arxiv.org/abs/1603.05027)\u003cbr\u003e\n**Author** Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun\n\u003cbr\u003e\n**Code** Coming Soon\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n// Coming Soon\n```\n\n\u003chr\u003e\n\n\u003ca name='resattnet'\u003e\u003c/a\u003e\n\n### ResAttNet\n\n**Paper** [Residual Attention Network for Image Classification](https://arxiv.org/abs/1704.06904)\u003cbr\u003e\n**Author** Fei Wang, Mengqing Jiang, Chen Qian, Shuo Yang, Cheng Li, Honggang Zhang, Xiaogang Wang, Xiaoou Tang\n\u003cbr\u003e\n**Code** Coming Soon\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n// Coming Soon\n```\n\n\u003chr\u003e\n\n\u003ca name='polynet'\u003e\u003c/a\u003e\n\n### PolyNet\n\n**Paper** [PolyNet: A Pursuit of Structural Diversity in Very Deep Networks](https://arxiv.org/abs/1611.05725)\u003cbr\u003e\n**Author** Xingcheng Zhang, Zhizhong Li, Chen Change Loy, Dahua Lin\n\u003cbr\u003e\n**Code** Coming Soon\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n// Coming Soon\n```\n\n\u003chr\u003e\n\n\u003ca name='pyramidnet'\u003e\u003c/a\u003e\n\n### PyramidNet\n\n**Paper** [Deep Pyramidal Residual Networks](https://arxiv.org/abs/1610.02915)\u003cbr\u003e\n**Author** Dongyoon Han, Jiwhan Kim, Junmo Kim\n\u003cbr\u003e\n**Code** Coming Soon\n\u003cbr\u003e\u003cbr\u003e\n**Model Options**\n\n```bash\n// Coming Soon\n```\n\n\u003chr\u003e\n\n## Reference\n\n- https://github.com/weiaicunzai/pytorch-cifar100\n- https://github.com/tensorflow/tensorflow\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farchsyscall%2Fconvnets-tensorflow2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farchsyscall%2Fconvnets-tensorflow2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farchsyscall%2Fconvnets-tensorflow2/lists"}