{"id":15565377,"url":"https://github.com/dkurt/openvino_ngraph_api","last_synced_at":"2025-04-03T06:45:58.372Z","repository":{"id":129100598,"uuid":"239442562","full_name":"dkurt/openvino_ngraph_api","owner":"dkurt","description":null,"archived":false,"fork":false,"pushed_at":"2023-05-10T11:54:44.000Z","size":12,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-08T20:32:34.433Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","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":null,"license":null,"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}},"created_at":"2020-02-10T06:24:06.000Z","updated_at":"2023-02-17T13:03:46.000Z","dependencies_parsed_at":"2024-10-28T19:54:49.358Z","dependency_job_id":null,"html_url":"https://github.com/dkurt/openvino_ngraph_api","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fopenvino_ngraph_api","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fopenvino_ngraph_api/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fopenvino_ngraph_api/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkurt%2Fopenvino_ngraph_api/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dkurt","download_url":"https://codeload.github.com/dkurt/openvino_ngraph_api/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246952273,"owners_count":20859811,"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":"2024-10-02T16:55:21.614Z","updated_at":"2025-04-03T06:45:58.346Z","avatar_url":"https://github.com/dkurt.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# OpenVINO nGraph API tutorial project\n\nThis project demonstrates basic usage of OpenVINO API to build\nIntermediate Representation networks in runtime and then infer it. To load\nnative networks topologies OpenCV is used. It also provides reference outputs to\ncompare accuracy.\n\n**NOTE** By default, OpenCV already uses OpenVINO as computational backend (read more [here](https://github.com/opencv/opencv/wiki/Intel%27s-Deep-Learning-Inference-Engine-backend)). So this project might be useful only if you want to emit OpenCV dependency or you have a format of deep learning networks\nwhich is not supported by OpenCV readers yet.\n\n## Getting started\n\n1. Download OpenVINO 2020.1: https://software.seek.intel.com/openvino-toolkit\n\n2. Clone this repository\n\n    ```sh\n    git clone https://github.com/dkurt/openvino_ngraph_api\n    cd openvino_ngraph_api\n    git lfs pull\n    ```\n\n3. Setup environment variables\n\n    ```sh\n    source /opt/intel/openvino/bin/setupvars.sh\n    export ngraph_DIR=/opt/intel/openvino/deployment_tools/ngraph/cmake\n    ```\n\n4. Build using CMake\n\n    ```sh\n    mkdir build \u0026\u0026 cd build\n    cmake .. -DCMAKE_BUILD_TYPE=Release \u0026\u0026 make -j8\n    ```\n\n5. Test one of the topologies (model files can be downloaded by URLs from https://github.com/opencv/opencv_extra/blob/4.x/testdata/dnn/download_models.py)\n\n    ```sh\n    $ ./ngraph_demo alexnet\n\n    Reference range: [1.05861e-07, 0.655111]\n    l1 diff: 4.21329e-10\n    lInf diff: 8.9407e-08\n    inference time: 17.4656ms\n    ```\n\n    ```sh\n    $ ./ngraph_demo squeezenet\n\n    Reference range: [2.68397e-08, 0.258784]\n    l1 diff: 1.21957e-09\n    lInf diff: 2.38419e-07\n    inference time: 6.62212ms\n    ```\n\n    ```sh\n    $ ./ngraph_demo ssd\n\n    [ OK ] matched class 3 with confidence 0.46\n    [ OK ] matched class 7 with confidence 0.99\n    [ OK ] matched class 12 with confidence 0.68\n    [ OK ] matched class 13 with confidence 1.00\n    [ OK ] matched class 15 with confidence 0.96\n    [ OK ] matched class 15 with confidence 0.36\n    inference time: 20.7912ms\n    ```\n\n    ```sh\n    $ ./ngraph_demo alexnet_quant\n\n    Reference range: [1.26981e-07, 0.625701]\n    l1 diff: 6.70524e-05\n    lInf diff: 0.0294101\n    inference time: 11.1459ms\n    ```\n\nTested on `Intel(R) Core(TM) i5-4460  CPU @ 3.20GHz x4` with Intel OpenVINO 2020.2\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdkurt%2Fopenvino_ngraph_api","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdkurt%2Fopenvino_ngraph_api","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdkurt%2Fopenvino_ngraph_api/lists"}