[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-401":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":21,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":25,"readmeContent":26,"aiSummary":27,"trendingCount":16,"starSnapshotCount":16,"syncStatus":28,"lastSyncTime":29,"discoverSource":30},401,"models","tensorflow\u002Fmodels","tensorflow","Models and examples built with TensorFlow","",null,"Python",77663,45027,2639,1083,0,1,26,73.1,"Other",false,"master",true,[],"2026-06-17 04:00:03","\u003Cdiv align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Ftf_model_garden\u002Ftf_model_garden_logo.png\">\n\u003C\u002Fdiv>\n\n[![Python](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Ftensorflow.svg?style=plastic)](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Ftensorflow)\n[![tf-models-official PyPI](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Ftf-models-official.svg)](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Ftf-models-official)\n\n\n# Welcome to the Model Garden for TensorFlow\n\nThe TensorFlow Model Garden is a repository with a number of different\nimplementations of state-of-the-art (SOTA) models and modeling solutions for\nTensorFlow users. We aim to demonstrate the best practices for modeling so that\nTensorFlow users can take full advantage of TensorFlow for their research and\nproduct development.\n\nTo improve the transparency and reproducibility of our models, training logs on\n[TensorBoard.dev](https:\u002F\u002Ftensorboard.dev) are also provided for models to the\nextent possible though not all models are suitable.\n\n| Directory | Description |\n|-----------|-------------|\n| [official](official) | • A collection of example implementations for SOTA models using the latest TensorFlow 2's high-level APIs\u003Cbr \u002F>• Officially maintained, supported, and kept up to date with the latest TensorFlow 2 APIs by TensorFlow\u003Cbr \u002F>• Reasonably optimized for fast performance while still being easy to read\u003Cbr \u002F> For more details on the capabilities, check the guide on the [Model-garden](https:\u002F\u002Fwww.tensorflow.org\u002Ftfmodels)|\n| [research](research) | • A collection of research model implementations in TensorFlow 1 or 2 by researchers\u003Cbr \u002F>• Maintained and supported by researchers |\n| [community](community) | • A curated list of the GitHub repositories with machine learning models and implementations powered by TensorFlow 2 |\n| [orbit](orbit) | • A flexible and lightweight library that users can easily use or fork when writing customized training loop code in TensorFlow 2.x. It seamlessly integrates with `tf.distribute` and supports running on different device types (CPU, GPU, and TPU). |\n\n## Installation\n\nTo install the current release of tensorflow-models, please follow any one of the methods described below.\n\n#### Method 1: Install the TensorFlow Model Garden pip package\n\n\u003Cdetails>\n\n**tf-models-official** is the stable Model Garden package. Please check out the [releases](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels\u002Freleases) to see what are available modules.\n\npip3 will install all models and dependencies automatically.\n\n```shell\npip3 install tf-models-official\n```\n\nPlease check out our examples:\n  - [basic library import](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels\u002Fblob\u002Fmaster\u002Ftensorflow_models\u002Ftensorflow_models_pypi.ipynb)\n  - [nlp model building](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels\u002Fblob\u002Fmaster\u002Fdocs\u002Fnlp\u002Findex.ipynb)\nto learn how to use a PIP package.\n\nNote that **tf-models-official** may not include the latest changes in the master branch of this\ngithub repo. To include latest changes, you may install **tf-models-nightly**,\nwhich is the nightly Model Garden package created daily automatically.\n\n```shell\npip3 install tf-models-nightly\n```\n\n\u003C\u002Fdetails>\n\n\n#### Method 2: Clone the source\n\n\u003Cdetails>\n\n1. Clone the GitHub repository:\n\n```shell\ngit clone https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels.git\n```\n\n2. Add the top-level ***\u002Fmodels*** folder to the Python path.\n\n```shell\nexport PYTHONPATH=$PYTHONPATH:\u002Fpath\u002Fto\u002Fmodels\n```\n\nIf you are using in a Windows environment, you may need to use the following command with PowerShell:\n```shell\n$env:PYTHONPATH += \":\\path\\to\\models\"\n```\n\nIf you are using a Colab notebook, please set the Python path with os.environ.\n\n```python\nimport os\nos.environ['PYTHONPATH'] += \":\u002Fpath\u002Fto\u002Fmodels\"\n```\n\n3. Install other dependencies\n\n```shell\npip3 install --user -r models\u002Fofficial\u002Frequirements.txt\n```\n\nFinally, if you are using nlp packages, please also install\n**tensorflow-text-nightly**:\n\n```shell\npip3 install tensorflow-text-nightly\n```\n\n\u003C\u002Fdetails>\n\n\n## Announcements\n\nPlease check [this page](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels\u002Fwiki\u002FAnnouncements) for recent announcements.\n\n## Contributions\n\n[![help wanted:paper implementation](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Ftensorflow\u002Fmodels\u002Fhelp%20wanted%3Apaper%20implementation)](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels\u002Flabels\u002Fhelp%20wanted%3Apaper%20implementation)\n\nIf you want to contribute, please review the [contribution guidelines](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels\u002Fwiki\u002FHow-to-contribute).\n\n## License\n\n[Apache License 2.0](LICENSE)\n\n## Citing TensorFlow Model Garden\n\nIf you use TensorFlow Model Garden in your research, please cite this repository.\n\n```\n@misc{tensorflowmodelgarden2020,\n  author = {Hongkun Yu and Chen Chen and Xianzhi Du and Yeqing Li and Abdullah Rashwan and Le Hou and Pengchong Jin and Fan Yang\n            and Frederick Liu and Jaeyoun Kim and Jing Li},\n  title = {{TensorFlow Model Garden}},\n  howpublished = {\\url{https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels}},\n  year = {2020}\n}\n```\n","tensorflow\u002Fmodels 是一个包含多种基于 TensorFlow 构建的模型和示例的仓库。项目核心功能包括提供一系列使用最新 TensorFlow 2 高级 API 实现的最先进（SOTA）模型，以及研究模型的实现，并且通过 tf-models-official 包进行官方维护和支持。这些模型经过合理优化，在保持代码可读性的同时追求高性能。此外，项目还提供了灵活轻量级的 Orbit 库，用于简化自定义训练循环代码的编写，并支持多设备类型运行。此项目适用于希望利用 TensorFlow 进行科学研究或产品开发的用户，特别是那些需要参考最佳实践并确保其模型透明度和可复现性的开发者。",2,"2026-06-17 02:35:22","top_all"]