{"id":20256589,"url":"https://github.com/interdigitalinc/compressai-vision","last_synced_at":"2025-10-10T00:46:29.494Z","repository":{"id":61740796,"uuid":"536772007","full_name":"InterDigitalInc/CompressAI-Vision","owner":"InterDigitalInc","description":"CompressAI-Vision helps you design, test and compare Video Compression for Machines pipelines. Compression methods can be either pulled from custom AI-based modules from CompressAI or traditional codecs such as H.266/VVC.","archived":false,"fork":false,"pushed_at":"2025-08-19T17:51:56.000Z","size":67777,"stargazers_count":93,"open_issues_count":0,"forks_count":9,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-08-19T19:40:48.911Z","etag":null,"topics":["compression","computer-vision","deep-learning","machine-to-machine-communication","pytorch","video-compression"],"latest_commit_sha":null,"homepage":"https://interdigitalinc.github.io/CompressAI-Vision/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause-clear","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/InterDigitalInc.png","metadata":{"files":{"readme":"README.md","changelog":"NEWS.md","contributing":"CONTRIBUTING.md","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,"zenodo":null}},"created_at":"2022-09-14T21:56:37.000Z","updated_at":"2025-08-19T17:52:01.000Z","dependencies_parsed_at":"2022-10-20T16:15:37.395Z","dependency_job_id":"da3a2053-fec0-4654-b5be-c43f99c819f5","html_url":"https://github.com/InterDigitalInc/CompressAI-Vision","commit_stats":null,"previous_names":[],"tags_count":23,"template":false,"template_full_name":null,"purl":"pkg:github/InterDigitalInc/CompressAI-Vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InterDigitalInc%2FCompressAI-Vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InterDigitalInc%2FCompressAI-Vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InterDigitalInc%2FCompressAI-Vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InterDigitalInc%2FCompressAI-Vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/InterDigitalInc","download_url":"https://codeload.github.com/InterDigitalInc/CompressAI-Vision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InterDigitalInc%2FCompressAI-Vision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279002344,"owners_count":26083357,"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","status":"online","status_checked_at":"2025-10-09T02:00:07.460Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["compression","computer-vision","deep-learning","machine-to-machine-communication","pytorch","video-compression"],"created_at":"2024-11-14T10:47:18.291Z","updated_at":"2025-10-10T00:46:29.488Z","avatar_url":"https://github.com/InterDigitalInc.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/source/_static/logo.svg\" alt=\"CompressAI-Vision-logo\"\u003e\n\u003c/p\u003e\n\nCompressAI-Vision helps you to develop, test and evaluate compression models with standardized tests in the context of compression methods optimized for machine tasks algorithms such as Neural-Network (NN)-based detectors.\n\nIt currently focuses on two types of pipeline:\n\n- Video compression for remote inference (`compressai-remote-inference`), which corresponds to the MPEG \"Video Coding for Machines\" (VCM) activity.\n\n- Split inference (`compressai-split-inference`), which  includes an evaluation framework for compressing intermediate features produced in the context of split models. The software supports all thepipelines considered in the related MPEG  activity: \"Feature Compression for Machines\" (FCM).\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/source/media/images/compressai-vision-pipelines.png\" alt=\"CompressAI-Vision supported pipelines\"\u003e\n\u003c/p\u003e\n\n## Features\n\n- [Detectron2](https://detectron2.readthedocs.io/en/latest/index.html) for Object Detection (Faster-RCNN) and Instance Segmentation (Mask-RCNN)\n\n- [JDE](https://github.com/Zhongdao/Towards-Realtime-MOT) for Object Tracking\n\n- [YOLOX-Darknet53](https://github.com/Megvii-BaseDetection/YOLOX) for Object Detection\n\n- [MMPOSE RTMO](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmo) for Pose Estimation (Bottom Up)\n\n- [Segment Anything](https://github.com/facebookresearch/segment-anything/tree/main)\n\n## Documentation\n\nA complete documentation is provided [here](https://interdigitalinc.github.io/CompressAI-Vision/index.html), including [installation](https://interdigitalinc.github.io/CompressAI-Vision/installation), [CLI usage](https://interdigitalinc.github.io/CompressAI-Vision/cli_usage.html), as well as [tutorials](https://interdigitalinc.github.io/CompressAI-Vision/tutorials).\n\n## installation\n\nThe CompressAI library providing learned compresion modules is available as a submodule. It can be initilized by running:\n```\ngit submodule update --init --recursive\n```\nNote: the installation scripts documented below installs compressai from source expects the submodule to be populated. \n\nCompressAI-Vision can be installed using a virtual environment and pip or using uv. \n\n### 1. Using a virtual environment:\n\n#### Initialization of the environment\nTo get started locally and install the development version of CompressAI-Vision, first create a [virtual environment](https://docs.python.org/3.8/library/venv.html) with python==3.8:\n\n```\npython3.8 -m venv venv\nsource ./venv/bin/activate\npip install -U pip\n```\n\n#### Installation of compressai-vision and supported vision models:\n\nFirst, if you want to manually export CUDA related paths, please source (e.g. for CUDA 11.8):\n```\nbash scripts/env_cuda.sh 11.8\n```\nThen, please run:\n```\nbash scripts/install.sh\n```\n\nFor more otions, check:\n```\nbash scripts/install.sh --help\n```\n\nNOTE 1: install.sh gives you the possibility to install vision models' source and weights at specified locations so that mutliple versions of compressai-vision can point to the same installed vision models\n\nNOTE 2: the downlading of JDE pretrained weights might fail. Check that the size of following file is ~558MB.\npath/to/weights/jde/jde.1088x608.uncertainty.pt\nThe file can be downloaded at the following link (in place of the above file path):\n\"https://docs.google.com/uc?export=download\u0026id=1nlnuYfGNuHWZztQHXwVZSL_FvfE551pA\"\n\n### 2. Using uv:\nWithin the root folder of compressai-vision:\n```\nbash scripts/install_uv.sh\n```\n\nNote: Make sure you pin the desired installed python version before, e.g., \n```\nuv python pin 3.8\n```\n\n## Usage\n\n### Split inference pipelines\n\nTo run split-inference pipelines, please use the following command:\n```\ncompressai-split-inference --help\n```\n\nNote that the following entry point is kept for backward compability. It runs split inference as well. \n```\ncompressai-vision-eval --help\n```\n\n\nFor example for testing a full split inference pipelines without any compression, run\n\n```\ncompressai-vision-eval --config-name=eval_split_inference_example\n```\n\n### Remote inference pipelines\n\nFor remote inference (MPEG VCM-like) pipelines, please run:\n```\ncompressai-remote-inference --help\n```\n\n### Configurations\n\nPlease check other configuration examples provided in ./cfgs as well as examplary scripts in ./scripts\n\nTest data related to the MPEG FCM activity can be found in ./data/mpeg-fcm/\n\n## For developers\n\nAfter your dev, you can run (and adapt) test scripts from the scripts/tests directory. Please check [scripts/tests/README.md] for more details\n\n### Contributing\n\nCode is formatted using black and isort. To format code, type:\n```\nmake code-format\n```\nStatic checks with those same code formatters can be run manually with:\n```\nmake static-analysis\n```\n\n### Compiling documentation\n\nTo produce the html documentation, from [docs/](docs/), run:\n```\nmake html\n```\nTo check the pages locally, open [docs/_build/html/index.html](docs/index.html)\n\n## License\n\nCompressAI-Vision is licensed under the BSD 3-Clause Clear License\n\n## Authors\n\nFabien Racapé, Hyomin Choi, Eimran Eimon, Sampsa Riikonen, Jacky Yat-Hong Lam\n\n## Related links\n * [HEVC HM reference software](https://hevc.hhi.fraunhofer.de)\n * [VVC VTM reference software](https://vcgit.hhi.fraunhofer.de/jvet/VVCSoftware_VTM)\n * [Detectron2](https://detectron2.readthedocs.io/en/latest/index.html)\n * [JDE](https://github.com/Zhongdao/Towards-Realtime-MOT.git)\n * [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX)\n * [MMPOSE RTMO](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmo)\n * [Segment Anything](https://github.com/facebookresearch/segment-anything/tree/main)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finterdigitalinc%2Fcompressai-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finterdigitalinc%2Fcompressai-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finterdigitalinc%2Fcompressai-vision/lists"}