{"id":13443217,"url":"https://github.com/NobuoTsukamoto/tflite-cv-example","last_synced_at":"2025-03-20T16:30:54.103Z","repository":{"id":52789938,"uuid":"175419754","full_name":"NobuoTsukamoto/tflite-cv-example","owner":"NobuoTsukamoto","description":"TensorFlow Lite, Coral Edge TPU samples (Python/C++, Raspberry Pi/Windows/Linux).","archived":false,"fork":false,"pushed_at":"2024-08-24T23:22:58.000Z","size":58920,"stargazers_count":120,"open_issues_count":1,"forks_count":15,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-12T19:42:36.751Z","etag":null,"topics":["coral","deeplab","detection","edge-tpu","edgetpu","segmentation","tensorflow-lite"],"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/NobuoTsukamoto.png","metadata":{"files":{"readme":"README.md","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}},"created_at":"2019-03-13T12:48:44.000Z","updated_at":"2024-10-26T01:25:27.000Z","dependencies_parsed_at":"2023-01-21T11:16:10.803Z","dependency_job_id":"977657b4-8f17-425b-85f0-a5501e073ae7","html_url":"https://github.com/NobuoTsukamoto/tflite-cv-example","commit_stats":{"total_commits":174,"total_committers":4,"mean_commits":43.5,"dds":0.03448275862068961,"last_synced_commit":"bf95954a41a1d84ce8789099dbf418a3086f6d4c"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NobuoTsukamoto%2Ftflite-cv-example","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NobuoTsukamoto%2Ftflite-cv-example/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NobuoTsukamoto%2Ftflite-cv-example/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NobuoTsukamoto%2Ftflite-cv-example/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NobuoTsukamoto","download_url":"https://codeload.github.com/NobuoTsukamoto/tflite-cv-example/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244649736,"owners_count":20487480,"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":["coral","deeplab","detection","edge-tpu","edgetpu","segmentation","tensorflow-lite"],"created_at":"2024-07-31T03:01:57.675Z","updated_at":"2025-03-20T16:30:54.096Z","avatar_url":"https://github.com/NobuoTsukamoto.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# TensorFlow Lite samples.\n\n## About\nTensorFlow Lite samples (Python/C++, Raspberry Pi/VisionFive 2/Windows/Linux).\n - CPU(XNNPACK) inference\n - Coral Edge TPU Delegate\n - GPU Delegate \n\n## List of samples.\n\n| Name | Language | Description | API | OS |\n|:---|:---|:---|:---|:---|\n|[Camouflage](camouflage)| Python | Object detection and camouflage objects by PiCamera. | PyCoral | Linux\u003cbr\u003eWindows |\n|[Classify](classify) | Python | Image classifilcation by PiCamera or Video Capture.| TF-Lite\u003cbr\u003ePyCoral | Linux\u003cbr\u003eWindows |\n|[CenterNet](centernet)|Python\u003cbr\u003eC++|CenterNet on-device with TensorFlow Lite.|TF-Lite|Liux\u003cbr\u003eWindows|\n| [DeepLab](deeplab) | Python\u003cbr\u003eC++ | Semantic Segmentation using DeepLab v3. | TF-Lite\u003cBR\u003eEdgeTPU API | Linux\u003cbr\u003eWindows |\n| [Object detection](detection) | Python\u003cbr\u003eC++\u003cbr\u003eVC++ | Object detection by PiCamera or Video Capture. | TF-Lite\u003cbr\u003ePyCoral | Linux\u003cbr\u003eWindows |\n| [U-Net MobileNet v2](segmentation) | Python | Image segmentation model U-Net MobileNet v2. | TF-Lite | Linux\u003cbr\u003eWindows \n| [Super resolution](super_resolution) | Python | Super resolution using ESRGAN. | TF-Lite | Linux\u003cbr\u003eWindows |\n| [YOLOX](yolox/python) | Python | YOLOX with TensorFlow Lite. | TF-Lite | Linux\u003cbr\u003eWindows |\n| [DeepLab V3+ EdgeTPUV2 and AutoSeg EdgeTPU](deeplab_edgetpu2) | Python | DeepLab V3+ EdgeTPUV2 and AutoSeg EdgeTPU with TensorFlow Lite. | TF-Lite\u003cbr\u003eEdgeTPU | Linux\u003cbr\u003eWindows |\n| [FFNet ](ffnet) | C++ | VisionFive 2 TensorFlow Lite GPU Delegate FFNet | TF-Lite\u003cbr\u003eGPU delegate | Linux |\n\n\n## Images\n\n|Object detection|Camouflage|DeepLab|\n|:--:|:--:|:--:|\n|![detection](detection/g3doc/img/output.gif)|![camouflage](camouflage/g3doc/img/output.gif)|![deeplab](deeplab/g3doc/img/output.gif)|\n\n\n|Segmentation|CenterNet|YOLOX|\n|:--:|:--:|:--:|\n|![segmentation](segmentation/g3doc/segmentation.gif)|![centernet](centernet/g3doc/img/centernet.gif)|![yolox](yolox/g3doc/yolox.gif)|\n\n\n|DeepLab V3+ EdgeTPUV2 and AutoSeg EdgeTPU| VisionFive 2 TensorFlow Lite GPU Delegate\u003cbr\u003eFFNet46NS CCC Mobile Pre-Down Fused-Argmax | VisionFive 2 TensorFlow Lite GPU Delegate\u003cbr\u003eEfficientDet-Lite0 |\n|:--:|:--:|:--:|\n|YouTube Link\u003cbr\u003e[![](https://img.youtube.com/vi/-F9R51vFOS8/mqdefault.jpg)](https://www.youtube.com/watch?v=-F9R51vFOS8)|YouTube Link\u003cbr\u003e[![](https://img.youtube.com/vi/QDNdEaW8Z8U/mqdefault.jpg)](https://www.youtube.com/watch?v=QDNdEaW8Z8U)|YouTube Link\u003cbr\u003e[![](https://img.youtube.com/vi/1SAccRvKuFM/mqdefault.jpg)](https://www.youtube.com/watch?v=1SAccRvKuFM)|\n\n## Environment\n- Coral Edge TPU USB Accelerator\n- Raspberry Pi (3 B+ / 4) + PiCamera or UVC Camera\n- Dev Board\n- VisionFive 2\n- x64 PC(Windows or Linux) + Video file or UVC Camera\n- Python3\n\n## Installation\n- OpenCV with OpenCV's extra modules(3.4.5 or higher)\n- TensorFlow Lite Runtime [(Python quickstart)](https://www.tensorflow.org/lite/guide/python).\n- Edge TPU Python library [(Get started with the USB Accelerator)](https://coral.withgoogle.com/tutorials/accelerator/).\n\n## Reference\n- [Get started with the USB Accelerator](https://coral.withgoogle.com/tutorials/accelerator/)\n- [TensorFlow models on the Edge TPU](https://coral.withgoogle.com/tutorials/edgetpu-models-intro/#model-requirements)\n- [Models Built for the Edge TPU](https://coral.withgoogle.com/models/)\n- [Megvii-BaseDetection/YOLOX](https://github.com/Megvii-BaseDetection/YOLOX)\n- [PINTO0309/PINTO_model_zoo](https://github.com/PINTO0309/PINTO_model_zoo)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNobuoTsukamoto%2Ftflite-cv-example","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FNobuoTsukamoto%2Ftflite-cv-example","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNobuoTsukamoto%2Ftflite-cv-example/lists"}