{"id":13577867,"url":"https://github.com/facebookresearch/pycls","last_synced_at":"2025-02-23T00:31:54.326Z","repository":{"id":35426378,"uuid":"191256013","full_name":"facebookresearch/pycls","owner":"facebookresearch","description":"Codebase for Image Classification Research, written in PyTorch.","archived":true,"fork":false,"pushed_at":"2024-03-20T15:45:40.000Z","size":971,"stargazers_count":2147,"open_issues_count":27,"forks_count":240,"subscribers_count":59,"default_branch":"main","last_synced_at":"2025-02-17T22:17:24.583Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/facebookresearch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"docs/CODE_OF_CONDUCT.md","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":"2019-06-10T22:47:17.000Z","updated_at":"2025-01-18T12:23:57.000Z","dependencies_parsed_at":"2024-06-19T03:50:46.003Z","dependency_job_id":"df90eff2-10d5-42e5-97b4-0720cb934b81","html_url":"https://github.com/facebookresearch/pycls","commit_stats":{"total_commits":106,"total_committers":21,"mean_commits":"5.0476190476190474","dds":0.6415094339622642,"last_synced_commit":"5719de641657c251f807c20a1fcf8ef6f4b60144"},"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2Fpycls","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2Fpycls/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2Fpycls/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2Fpycls/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/facebookresearch","download_url":"https://codeload.github.com/facebookresearch/pycls/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240250386,"owners_count":19771783,"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":[],"created_at":"2024-08-01T15:01:25.032Z","updated_at":"2025-02-23T00:31:53.867Z","avatar_url":"https://github.com/facebookresearch.png","language":"Python","readme":"# pycls\n\n[![Support Ukraine](https://img.shields.io/badge/Support-Ukraine-FFD500?style=flat\u0026labelColor=005BBB)](https://opensource.fb.com/support-ukraine)\n\n**pycls** is an image classification codebase, written in [PyTorch](https://pytorch.org/). It was originally developed for the [On Network Design Spaces for Visual Recognition](https://arxiv.org/abs/1905.13214) project. **pycls** has since matured and been adopted by a number of [projects](#projects) at Facebook AI Research.\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"docs/regnetx_nets.png\" width=\"550px\" /\u003e\n  \u003cp align=\"center\"\u003e\u003cb\u003epycls\u003c/b\u003e provides a large set of baseline models across a wide range of flop regimes.\u003c/p\u003e\n\u003c/div\u003e\n\n## Introduction\n\nThe goal of **pycls** is to provide a simple and flexible codebase for image classification. It is designed to support rapid implementation and evaluation of research ideas. **pycls** also provides a large collection of baseline results ([Model Zoo](MODEL_ZOO.md)).  The codebase supports efficient single-machine multi-gpu training, powered by the PyTorch distributed package, and provides implementations of standard models including [ResNet](https://arxiv.org/abs/1512.03385), [ResNeXt](https://arxiv.org/abs/1611.05431), [EfficientNet](https://arxiv.org/abs/1905.11946), and [RegNet](https://arxiv.org/abs/2003.13678).\n\n## Using pycls\n\nPlease see [`GETTING_STARTED`](docs/GETTING_STARTED.md) for brief installation instructions and basic usage examples.\n\n## Model Zoo\n\nWe provide a large set of baseline results and pretrained models available for download in the **pycls** [Model Zoo](MODEL_ZOO.md); including the simple, fast, and effective [RegNet](https://arxiv.org/abs/2003.13678) models that we hope can serve as solid baselines across a wide range of flop regimes.\n\n## Sweep Code\n\nThe pycls codebase now provides powerful support for studying *design spaces* and more generally *population statistics* of models as introduced in [On Network Design Spaces for Visual Recognition](https://arxiv.org/abs/1905.13214) and [Designing Network Design Spaces](https://arxiv.org/abs/2003.13678). This idea is that instead of planning a single pycls job (e.g., testing a specific model configuration), one can study the behavior of an entire population of models. This allows for quite powerful and succinct experimental design, and elevates the study of individual model behavior to the study of the behavior of model populations. Please see [`SWEEP_INFO`](docs/SWEEP_INFO.md) for details.\n\n## Projects\n\nA number of projects at FAIR have been built on top of **pycls**:\n\n- [On Network Design Spaces for Visual Recognition](https://arxiv.org/abs/1905.13214)\n- [Exploring Randomly Wired Neural Networks for Image Recognition](https://arxiv.org/abs/1904.01569)\n- [Designing Network Design Spaces](https://arxiv.org/abs/2003.13678)\n- [Fast and Accurate Model Scaling](https://arxiv.org/abs/2103.06877)\n- [Are Labels Necessary for Neural Architecture Search?](https://arxiv.org/abs/2003.12056)\n- [PySlowFast Video Understanding Codebase](https://github.com/facebookresearch/SlowFast)\n\nIf you are using **pycls** in your research and would like to include your project here, please let us know or send a PR.\n\n## Citing pycls\n\nIf you find **pycls** helpful in your research or refer to the baseline results in the [Model Zoo](MODEL_ZOO.md), please consider citing an appropriate subset of the following papers:\n\n```\n@InProceedings{Radosavovic2019,\n  title = {On Network Design Spaces for Visual Recognition},\n  author = {Ilija Radosavovic and Justin Johnson and Saining Xie Wan-Yen Lo and Piotr Doll{\\'a}r},\n  booktitle = {ICCV},\n  year = {2019}\n}\n\n@InProceedings{Radosavovic2020,\n  title = {Designing Network Design Spaces},\n  author = {Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Doll{\\'a}r},\n  booktitle = {CVPR},\n  year = {2020}\n}\n\n@InProceedings{Dollar2021,\n  title = {Fast and Accurate Model Scaling},\n  author = {Piotr Doll{\\'a}r and Mannat Singh and Ross Girshick},\n  booktitle = {CVPR},\n  year = {2021}\n}\n```\n\n## License\n\n**pycls** is released under the MIT license. Please see the [`LICENSE`](LICENSE) file for more information.\n\n## Contributing\n\nWe actively welcome your pull requests! Please see [`CONTRIBUTING.md`](docs/CONTRIBUTING.md) and [`CODE_OF_CONDUCT.md`](docs/CODE_OF_CONDUCT.md) for more info.\n","funding_links":[],"categories":["Python","图像数据与CV","DLA","Computer Vision"],"sub_categories":["RegNet","Classification \u0026 Detection \u0026 Tracking"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2Fpycls","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffacebookresearch%2Fpycls","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2Fpycls/lists"}