{"id":14977665,"url":"https://github.com/opencv/opencv_zoo","last_synced_at":"2025-05-14T23:03:34.804Z","repository":{"id":36981307,"uuid":"390637491","full_name":"opencv/opencv_zoo","owner":"opencv","description":"Model Zoo For OpenCV DNN and Benchmarks.","archived":false,"fork":false,"pushed_at":"2025-05-07T06:01:04.000Z","size":1026,"stargazers_count":758,"open_issues_count":16,"forks_count":232,"subscribers_count":26,"default_branch":"main","last_synced_at":"2025-05-07T07:20:04.551Z","etag":null,"topics":["benchmark","deep-learning","model-zoo","opencv"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/opencv.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":"2021-07-29T07:22:20.000Z","updated_at":"2025-05-07T06:01:04.000Z","dependencies_parsed_at":"2023-01-17T11:00:27.668Z","dependency_job_id":"d230719b-1f86-4265-ad96-61024eccc85e","html_url":"https://github.com/opencv/opencv_zoo","commit_stats":{"total_commits":156,"total_committers":29,"mean_commits":5.379310344827586,"dds":0.5192307692307692,"last_synced_commit":"a988f337936a624cb62fd58958116ba8b0a98afa"},"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opencv%2Fopencv_zoo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opencv%2Fopencv_zoo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opencv%2Fopencv_zoo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opencv%2Fopencv_zoo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/opencv","download_url":"https://codeload.github.com/opencv/opencv_zoo/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254243355,"owners_count":22038045,"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":["benchmark","deep-learning","model-zoo","opencv"],"created_at":"2024-09-24T13:56:06.179Z","updated_at":"2025-05-14T23:03:29.783Z","avatar_url":"https://github.com/opencv.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# OpenCV Zoo and Benchmark\n\nA zoo for models tuned for OpenCV DNN with benchmarks on different platforms.\n\nGuidelines:\n\n- Install latest `opencv-python`:\n  ```shell\n  python3 -m pip install opencv-python\n  # Or upgrade to latest version\n  python3 -m pip install --upgrade opencv-python\n  ```\n- Clone this repo to download all models and demo scripts:\n  ```shell\n  # Install git-lfs from https://git-lfs.github.com/\n  git clone https://github.com/opencv/opencv_zoo \u0026\u0026 cd opencv_zoo\n  git lfs install\n  git lfs pull\n  ```\n- To run benchmarks on your hardware settings, please refer to [benchmark/README](./benchmark/README.md).\n\n## Models \u0026 Benchmark Results\n\n![](benchmark/color_table.svg?raw=true)\n\nHardware Setup:\n\nx86-64:\n- [Intel Core i7-12700K](https://www.intel.com/content/www/us/en/products/sku/134594/intel-core-i712700k-processor-25m-cache-up-to-5-00-ghz/specifications.html): 8 Performance-cores (3.60 GHz, turbo up to 4.90 GHz), 4 Efficient-cores (2.70 GHz, turbo up to 3.80 GHz), 20 threads.\n\nARM:\n- [Khadas VIM3](https://www.khadas.com/vim3): Amlogic A311D SoC with a 2.2GHz Quad core ARM Cortex-A73 + 1.8GHz dual core Cortex-A53 ARM CPU, and a 5 TOPS NPU. Benchmarks are done using **per-tensor quantized** models. Follow [this guide](https://github.com/opencv/opencv/wiki/TIM-VX-Backend-For-Running-OpenCV-On-NPU) to build OpenCV with TIM-VX backend enabled.\n- [Khadas VIM4](https://www.khadas.com/vim4): Amlogic A311D2 SoC with 2.2GHz Quad core ARM Cortex-A73 and 2.0GHz Quad core Cortex-A53 CPU, and 3.2 TOPS Build-in NPU.\n- [Khadas Edge 2](https://www.khadas.com/edge2): Rockchip RK3588S SoC with a CPU of 2.25 GHz Quad Core ARM Cortex-A76 + 1.8 GHz Quad Core Cortex-A55, and a 6 TOPS NPU.\n- [Atlas 200 DK](https://e.huawei.com/en/products/computing/ascend/atlas-200): Ascend 310 NPU with 22 TOPS @ INT8. Follow [this guide](https://github.com/opencv/opencv/wiki/Huawei-CANN-Backend) to build OpenCV with CANN backend enabled.\n- [Atlas 200I DK A2](https://www.hiascend.com/hardware/developer-kit-a2): SoC with 1.0GHz Quad-core CPU and Ascend 310B NPU with 8 TOPS @ INT8.\n- [NVIDIA Jetson Nano B01](https://developer.nvidia.com/embedded/jetson-nano-developer-kit): a Quad-core ARM A57 @ 1.43 GHz CPU, and a 128-core NVIDIA Maxwell GPU.\n- [NVIDIA Jetson Nano Orin](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/): a 6-core Arm® Cortex®-A78AE v8.2 64-bit CPU, and a 1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores (max freq 625MHz).\n- [Raspberry Pi 4B](https://www.raspberrypi.com/products/raspberry-pi-4-model-b/specifications/): Broadcom BCM2711 SoC with a Quad core Cortex-A72 (ARM v8) 64-bit @ 1.5 GHz.\n- [Horizon Sunrise X3](https://developer.horizon.ai/sunrise): an SoC from Horizon Robotics with a quad-core ARM Cortex-A53 1.2 GHz CPU and a 5 TOPS BPU (a.k.a NPU).\n- [MAIX-III AXera-Pi](https://wiki.sipeed.com/hardware/en/maixIII/ax-pi/axpi.html#Hardware): Axera AX620A SoC with a quad-core ARM Cortex-A7 CPU and a 3.6 TOPS @ int8 NPU.\n- [Toybrick RV1126](https://t.rock-chips.com/en/portal.php?mod=view\u0026aid=26): Rockchip RV1126 SoC with a quard-core ARM Cortex-A7 CPU and a 2.0 TOPs NPU.\n\nRISC-V:\n- [StarFive VisionFive 2](https://doc-en.rvspace.org/VisionFive2/Product_Brief/VisionFive_2/specification_pb.html): `StarFive JH7110` SoC with a RISC-V quad-core CPU, which can turbo up to 1.5GHz, and an GPU of model `IMG BXE-4-32 MC1` from Imagination, which has a work freq up to 600MHz.\n- [Allwinner Nezha D1](https://d1.docs.aw-ol.com/en): Allwinner D1 SoC with a 1.0 GHz single-core RISC-V [Xuantie C906 CPU](https://www.t-head.cn/product/C906?spm=a2ouz.12986968.0.0.7bfc1384auGNPZ) with RVV 0.7.1 support. YuNet is tested for now. Visit [here](https://github.com/fengyuentau/opencv_zoo_cpp) for more details.\n\n***Important Notes***:\n\n- The data under each column of hardware setups on the above table represents the elapsed time of an inference (preprocess, forward and postprocess).\n- The time data is the mean of 10 runs after some warmup runs. Different metrics may be applied to some specific models.\n- Batch size is 1 for all benchmark results.\n- `---` represents the model is not availble to run on the device.\n- View [benchmark/config](./benchmark/config) for more details on benchmarking different models.\n\n## Some Examples\n\nSome examples are listed below. You can find more in the directory of each model!\n\n### Face Detection with [YuNet](./models/face_detection_yunet/)\n\n![largest selfie](./models/face_detection_yunet/example_outputs/largest_selfie.jpg)\n\n### Face Recognition with [SFace](./models/face_recognition_sface/)\n\n![sface demo](./models/face_recognition_sface/example_outputs/demo.jpg)\n\n### Facial Expression Recognition with [Progressive Teacher](./models/facial_expression_recognition/)\n\n![fer demo](./models/facial_expression_recognition/example_outputs/selfie.jpg)\n\n### Human Segmentation with [PP-HumanSeg](./models/human_segmentation_pphumanseg/)\n\n![messi](./models/human_segmentation_pphumanseg/example_outputs/messi.jpg)\n\n### Image Segmentation with [EfficientSAM](./models/image_segmentation_efficientsam/)\n\n![sam_present](./models/image_segmentation_efficientsam/example_outputs/sam_present.gif)\n\n### License Plate Detection with [LPD_YuNet](./models/license_plate_detection_yunet/)\n\n![license plate detection](./models/license_plate_detection_yunet/example_outputs/lpd_yunet_demo.gif)\n\n### Object Detection with [NanoDet](./models/object_detection_nanodet/) \u0026 [YOLOX](./models/object_detection_yolox/)\n\n![nanodet demo](./models/object_detection_nanodet/example_outputs/1_res.jpg)\n\n![yolox demo](./models/object_detection_yolox/example_outputs/3_res.jpg)\n\n### Object Tracking with [VitTrack](./models/object_tracking_vittrack/)\n\n![webcam demo](./models/object_tracking_vittrack/example_outputs/vittrack_demo.gif)\n\n### Palm Detection with [MP-PalmDet](./models/palm_detection_mediapipe/)\n\n![palm det](./models/palm_detection_mediapipe/example_outputs/mppalmdet_demo.gif)\n\n### Hand Pose Estimation with [MP-HandPose](models/handpose_estimation_mediapipe/)\n\n![handpose estimation](models/handpose_estimation_mediapipe/example_outputs/mphandpose_demo.webp)\n\n### Person Detection with [MP-PersonDet](./models/person_detection_mediapipe)\n\n![person det](./models/person_detection_mediapipe/example_outputs/mppersondet_demo.webp)\n\n### Pose Estimation with [MP-Pose](models/pose_estimation_mediapipe)\n\n![pose_estimation](models/pose_estimation_mediapipe/example_outputs/mpposeest_demo.webp)\n\n### QR Code Detection and Parsing with [WeChatQRCode](./models/qrcode_wechatqrcode/)\n\n![qrcode](./models/qrcode_wechatqrcode/example_outputs/wechat_qrcode_demo.gif)\n\n### Chinese Text detection [PPOCR-Det](./models/text_detection_ppocr/)\n\n![mask](./models/text_detection_ppocr/example_outputs/mask.jpg)\n\n### English Text detection [PPOCR-Det](./models/text_detection_ppocr/)\n\n![gsoc](./models/text_detection_ppocr/example_outputs/gsoc.jpg)\n\n### Text Detection with [CRNN](./models/text_recognition_crnn/)\n\n![crnn_demo](./models/text_recognition_crnn/example_outputs/CRNNCTC.gif)\n\n## License\n\nOpenCV Zoo is licensed under the [Apache 2.0 license](./LICENSE). Please refer to licenses of different models.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopencv%2Fopencv_zoo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopencv%2Fopencv_zoo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopencv%2Fopencv_zoo/lists"}