{"id":15565376,"url":"https://github.com/dkurt/qupath-extension-openvino","last_synced_at":"2025-09-15T14:30:51.909Z","repository":{"id":42572452,"uuid":"406890785","full_name":"dkurt/qupath-extension-openvino","owner":"dkurt","description":"Intel OpenVINO extension for QuPath, a digital pathology platform","archived":false,"fork":false,"pushed_at":"2022-12-07T11:11:14.000Z","size":92,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-04T19:03:22.107Z","etag":null,"topics":["deep-learning","digital-pathology","intel","java","openvino","qupath","stardist"],"latest_commit_sha":null,"homepage":"","language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dkurt.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null},"funding":{"github":null,"patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"lfx_crowdfunding":null,"custom":"https://www.buymeacoffee.com/dkurt"}},"created_at":"2021-09-15T18:53:19.000Z","updated_at":"2024-11-24T19:16:58.000Z","dependencies_parsed_at":"2023-01-24T16:46:07.070Z","dependency_job_id":null,"html_url":"https://github.com/dkurt/qupath-extension-openvino","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/dkurt/qupath-extension-openvino","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fqupath-extension-openvino","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fqupath-extension-openvino/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fqupath-extension-openvino/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fqupath-extension-openvino/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dkurt","download_url":"https://codeload.github.com/dkurt/qupath-extension-openvino/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fqupath-extension-openvino/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":275269385,"owners_count":25435058,"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":"2025-09-15T02:00:09.272Z","response_time":75,"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":["deep-learning","digital-pathology","intel","java","openvino","qupath","stardist"],"created_at":"2024-10-02T16:55:19.915Z","updated_at":"2025-09-15T14:30:51.498Z","avatar_url":"https://github.com/dkurt.png","language":"Java","funding_links":["https://www.buymeacoffee.com/dkurt"],"categories":[],"sub_categories":[],"readme":"# QuPath OpenVINO extension\n\n[![GitHub all releases](https://img.shields.io/github/downloads/dkurt/qupath-extension-openvino/total?color=blue)](https://github.com/dkurt/qupath-extension-openvino/releases) [![Image.sc forum](https://img.shields.io/badge/ask-question-brightgreen/json.svg?\u0026logo=data:image/png;base64,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)](https://forum.image.sc/u/dkurt) [![Awesome OpenVINO](https://img.shields.io/badge/Awesome-OpenVINO-FC60A8?logo=awesomelists)](https://github.com/dkurt/awesome-openvino)\n\nWelcome to the Intel OpenVINO extension for [QuPath](http://qupath.github.io)!\n\nThis adds support for inference optimization using [Intel OpenVINO for Java](https://github.com/openvinotoolkit/openvino_contrib/tree/master/modules/java_api) into QuPath.\n\n| Intel(R) Core(TM) i7-6700K | **Test image**: [OS-3.ndpi](https://cytomine.com/collection/os-3/os-3-ndpi)\u003cbr\u003e**Model**: he_heavy_augment\u003cbr\u003e**Tile size**: 1024x1024 |\n|---|---|\n| TensorFlow 2.4.1 with platform=mkl | 22:31 minutes |\n| OpenVINO 2022.1 | 15:02 minutes (x1.48) |\n| OpenVINO 2022.1 INT8 | 9:54 minutes (x2.33) |\n\n\u003cimg src=\"https://user-images.githubusercontent.com/25801568/159727338-6284edae-5cd2-4536-80af-a26e67efe85b.png\" width=\"256\"\u003e\n\n## Building\n\nYou can always build this extension from source but you can also download pre-built package from [releases](https://github.com/dkurt/qupath-extension-openvino/releases) page. Choose one for your operating system.\n\n### Extension + dependencies separately\n\nYou can build the extension with\n\n```bash\ngradlew clean build copyDependencies\n```\n\nThe output will be under `build/libs`.\n\n* `clean` removes anything old\n* `build` builds the QuPath extension as a *.jar* file and adds it to `libs`\n* `copyDependencies` copies the TensorFlow dependencies to the `libs` folder\n\n### Extension + dependencies together\n\nAlternatively, you can create a single *.jar* file that contains both the\nextension and all its dependencies with\n\n```bash\ngradlew clean shadowjar\n```\n\n## Installing\n\nThe extension + its dependencies will all need to be available to QuPath inside\nQuPath's extensions folder.\n\nThe easiest way to install the jars is to simply drag them on top of QuPath\nwhen it's running.\nYou will then be prompted to ask whether you want to copy them to the\nappropriate folder.\n\n\n## Usage\n\n### OpenVINO IR format\n\nOpenVINO uses own format for the deep learning networks representation (IR). It is a pair of `.xml` and `.bin` files which generated from original model. Download ready to use models from [models](./models) directory. There are FP32 and INT8 (quantized) version of the models. INT8 is faster for most of CPUs.\n\nAlternatively, you can convert model locally. For model conversion you can install `openvino-dev` Python package and use Model Optimizer by `mo` command.\n\nExample conversion for [StarDist](https://github.com/qupath/qupath-extension-stardist) model (we recommend to use Python virtual environment to install required packages):\n\n```bash\npython3 -m venv venv3\nsource venv3/bin/activate\npip install --upgrade pip\npip install openvino-dev tensorflow\n\nmo --input input --data_type FP16 --input_shape \"[1,1024,1024,3]\" --saved_model_dir=he_heavy_augment\n```\n\nNote that extension is able to reshape model to any input size in runtime so `\"[1,1024,1024,3]\"` is just a default input resolution. For `dsb2018_heavy_augment` number of channels equals `1` so use `--input_shape \"[1,1024,1024,1]\"`\n\n:thinking: For questions and feature requests use [issues](https://github.com/dkurt/qupath-extension-openvino/issues) or [forum](https://forum.image.sc/u/dkurt).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdkurt%2Fqupath-extension-openvino","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdkurt%2Fqupath-extension-openvino","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdkurt%2Fqupath-extension-openvino/lists"}