{"id":13437142,"url":"https://github.com/hailo-ai/tappas","last_synced_at":"2026-01-17T05:34:59.023Z","repository":{"id":44441710,"uuid":"465229726","full_name":"hailo-ai/tappas","owner":"hailo-ai","description":"High-performance, optimized pre-trained template AI application pipelines for systems using Hailo devices","archived":false,"fork":false,"pushed_at":"2025-09-25T15:21:14.000Z","size":455851,"stargazers_count":157,"open_issues_count":2,"forks_count":70,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-09-25T17:30:58.021Z","etag":null,"topics":["deep-learning","edge-ai","gstreamer","hardware-acceleration","machine-learning","neural-networks","video-processing"],"latest_commit_sha":null,"homepage":"http://hailo.ai/","language":"C++","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"lgpl-2.1","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hailo-ai.png","metadata":{"files":{"readme":"README.rst","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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2022-03-02T09:01:15.000Z","updated_at":"2025-09-21T18:05:26.000Z","dependencies_parsed_at":"2025-09-26T02:24:11.160Z","dependency_job_id":null,"html_url":"https://github.com/hailo-ai/tappas","commit_stats":null,"previous_names":[],"tags_count":21,"template":false,"template_full_name":null,"purl":"pkg:github/hailo-ai/tappas","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hailo-ai%2Ftappas","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hailo-ai%2Ftappas/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hailo-ai%2Ftappas/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hailo-ai%2Ftappas/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hailo-ai","download_url":"https://codeload.github.com/hailo-ai/tappas/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hailo-ai%2Ftappas/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28500165,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-17T04:31:57.058Z","status":"ssl_error","status_checked_at":"2026-01-17T04:31:45.816Z","response_time":85,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["deep-learning","edge-ai","gstreamer","hardware-acceleration","machine-learning","neural-networks","video-processing"],"created_at":"2024-07-31T03:00:54.616Z","updated_at":"2026-01-17T05:34:59.018Z","avatar_url":"https://github.com/hailo-ai.png","language":"C++","funding_links":[],"categories":["C++"],"sub_categories":[],"readme":"Hailo TAPPAS - Optimized Execution of Video-Processing Pipelines\n================================================================\n\n.. |gstreamer| image:: https://img.shields.io/badge/gstreamer-1.16%20%7C%201.18%20%7C%201.20-blue\n   :target: https://gstreamer.freedesktop.org/\n   :alt: Gstreamer 1.16 | 1.18 | 1.20\n   :width: 150\n   :height: 20\n\n.. |hailort| image:: https://img.shields.io/badge/HailoRT-4.23.0%20%7C%205.2.0-green\n   :target: https://github.com/hailo-ai/hailort\n   :alt: HailoRT 4.23.0 | 5.2.0\n   :height: 20\n\n\n.. |license| image:: https://img.shields.io/badge/License-LGPLv2.1-green\n   :target: https://github.com/hailo-ai/tappas/blob/master/LICENSE\n   :alt: License: LGPL v2.1\n   :height: 20\n\n.. |check_mark| image:: ./resources/check_mark.png\n  :width: 20\n  :align: middle\n\n.. image:: ./resources/github_Tappas_Mar24.jpg\n  :height: 300\n  :width: 600\n  :align: center\n\n|gstreamer| |hailort| |license|\n\n----\n\nOverview\n--------\n\nTAPPAS is Hailo's infrasturcture for building applications, implementing pipeline elements and\npre-trained AI tasks.\n\nHailo apllications are now maintained at `this repository \u003chttps://github.com/hailo-ai/hailo-apps-infra\u003e`_.\n\nDemonstrating Hailo's system integration scenario of specific use cases on predefined systems\n(software and Hardware platforms). It can be used for evaluations, reference code and demos:\n\n* Accelerating time to market by reducing development time and deployment effort\n* Simplifying integration with Hailo’s runtime SW stack\n* Providing a starting point for customers to fine-tune their applications\n\n\n----\n\nGetting Started with Hailo-8 And Hailo-10H\n-----------------------------------------\n\nPrerequisites\n^^^^^^^^^^^^^\n\n* Hailo-8 or Hailo-10H device\n* HailoRT PCIe driver installed\n* At least 6GB's of free disk space\n\n\n.. note::\n    This version is compatible with HailoRT v4.23.0 for Hailo-8 devices, and with HailoRT v5.2.0 for Hailo-10H devices.\n\n\nInstallation\n^^^^^^^^^^^^\n\n.. list-table::\n   :header-rows: 1\n\n   * - Option\n     - Instructions\n     - Supported OS\n   * - **Hailo SW Suite***\n     - `SW Suite Install guide \u003cdocs/installation/sw-suite-install.rst\u003e`_\n     - Ubuntu x86 24.04, Ubuntu x86 22.04\n   * - Manual install\n     - `Manual install guide \u003cdocs/installation/manual-install.rst\u003e`_\n     - Ubuntu x86 24.04, Ubuntu x86 22.04, Ubuntu aarch64 20.04\n   * - Yocto installation\n     - `Read more about Yocto installation \u003cdocs/installation/yocto.rst\u003e`_\n     - Yocto supported BSP's\n   * - Raspberry Pi 5 installation\n     - `Read more about Raspberry Pi 5 installation \u003chttps://github.com/hailo-ai/hailo-rpi5-examples/blob/main/doc/install-raspberry-pi5.md\u003e`_\n     - Raspberry Pi OS\n\n\n\n``* It is recommended to start your development journey by first installing the Hailo SW Suite``\n\nDocumentation\n^^^^^^^^^^^^^\n\n* `Framework architecture and elements documentation \u003cdocs/TAPPAS_architecture.rst\u003e`_\n* `Guide to writing your own C++ postprocess element \u003cdocs/write_your_own_application/write-your-own-postprocess.rst\u003e`_\n* `Guide to writing your own Python postprocess element \u003cdocs/write_your_own_application/write-your-own-python-postprocess.rst\u003e`_\n* `Debugging and profiling performance \u003cdocs/write_your_own_application/debugging.rst\u003e`_\n* `Cross compile \u003ctools/cross_compiler/README.rst\u003e`_ - A guide for cross-compiling\n\n----\n\nGetting Started with Hailo-15\n-----------------------------\n\nTAPPAS is now released separately for Hailo-8 and Hailo-10H, for Hailo-15 please refer to https://github.com/hailo-ai/hailo-camera-apps.\n\nFor a quick start with Hailo-15, please refer to the Vision Processor Software Package documentation section\nin Hailo's `Developer Zone \u003chttps://hailo.ai/developer-zone/documentation/\u003e`_.\n\n----\n\nExample Applications Built with TAPPAS\n--------------------------------------\n\nTAPPAS includes a `single-stream object detection pipeline \u003capps/detection/README.rst\u003e`_ built on top of GStreamer.\nThese example application is part of the Hailo AI Software Suite.\n\nHailo offers an additional set of\n`Application Code Examples \u003chttps://github.com/hailo-ai/Hailo-Application-Code-Examples\u003e`_.\nFor the Raspberry Pi 5 applications, go to\n`Hailo Raspberry Pi 5 Examples \u003chttps://github.com/hailo-ai/hailo-rpi5-examples\u003e`_.\n\n.. important:: \n    * Example application utilize both the host (for non-neural tasks) and the Neural-Network Core\n      (for neural-networks inference), therefore performance results are affected by the host.\n    * This application example does not include any architecture-specific accelerator usage,\n      and therefore will provide the easiest way to run an application, but with sub-optimal performance.\n\n\n.. note::\n    Running application examples requires a direct connection to a monitor.\n\n\n----\n\nSupport\n-------\n\nIf you need support, please post your question on our `Hailo community Forum \u003chttps://community.hailo.ai/\u003e`_ for assistance.\n\nContact information is available at `hailo.ai \u003chttps://hailo.ai/contact-us/\u003e`_.\n\n----\n\nChangelog\n----------\n\n**v5.2.0 (December 2025)**\n\n* Added ``--static-opencv`` option to ``install.sh`` for static OpenCV linking.\n* Added Python wheel builder for TAPPAS Python binding package\n* Updated pybind11 to support NumPy 2.x\n* Removed Hailo-15 support and related code\n* This release supports both HailoRT v4.23.0 (Hailo-8) and HailoRT v5.2.0 (Hailo-10H)\n\n\n**v5.1.0 (October 2025)**\n\n* Downloader: removed redundant CLI arguments (``--platform``, ``--app-list``);\n* Downloader: HEF files now downloaded from ``model_zoo`` and media files from the TAPPAS bucket; removed the uploader;\n* Detection app: ``detection.sh`` now supports ``--arch`` (Hailo-8/Hailo-10H);\n* Models and resources: migrated model files to ``model_zoo``; TAPPAS bucket is now used only for general MP4 files; updated resources directory structure; changed ``yolov5m_wo_spp_60p.hef`` to ``yolov5m_wo_spp.hef``.\n* Hailo‑10H support: added Hailo-10H HEF downloads.\n* Build and packaging: separated GCC apt installation and removed fixed GCC version; updated related documentation.\n* Dependencies: updated package versions for Python 3.13 compatibility; migrated pandas to support the newer environment.\n* Cleanup: removed Hailo‑8 references where appropriate; removed nested directories under apps; various comment updates.\n* This release supports both HailoRT v4.23.0 (Hailo-8) and HailoRT v5.1.0 (Hailo-10H)\n\n**v5.0.0 (July 2025)**\n\n* All example applications, except the object detection application, are now maintained at `Hailo Applications \u003chttps://github.com/hailo-ai/hailo-apps-infra\u003e`_.\n* Updated manual installation process\n* Added support for Ubuntu 24.04\n* Added support for Python 3.12\n* This release supports both HailoRT v4.22.0 (Hailo-8) and HailoRT v5.0.0 (Hailo-10H)\n* Known issue: When installing via GitHub, only Hailo-8 models are downloaded.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhailo-ai%2Ftappas","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhailo-ai%2Ftappas","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhailo-ai%2Ftappas/lists"}