{"id":18009271,"url":"https://github.com/xlite-dev/yolov5face-toolkit","last_synced_at":"2025-10-19T09:27:09.840Z","repository":{"id":37328771,"uuid":"449748566","full_name":"xlite-dev/yolov5face-toolkit","owner":"xlite-dev","description":"🍅 YOLO5Face 2021 with MNN/NCNN/TNN/ONNXRuntime ","archived":false,"fork":false,"pushed_at":"2023-04-21T15:11:17.000Z","size":40668,"stargazers_count":56,"open_issues_count":6,"forks_count":8,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-24T15:01:55.905Z","etag":null,"topics":["cpp","yolo5-face","yolo5face","yolov5-face","yolov5-face-landmark","yolov5face","yolov7-face","yolov8-face"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/xlite-dev.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":"2022-01-19T15:31:29.000Z","updated_at":"2025-03-23T06:31:36.000Z","dependencies_parsed_at":"2024-10-30T03:54:54.461Z","dependency_job_id":null,"html_url":"https://github.com/xlite-dev/yolov5face-toolkit","commit_stats":null,"previous_names":["deftruth/yolov5face-toolkit","xlite-dev/yolov5face-toolkit"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xlite-dev%2Fyolov5face-toolkit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xlite-dev%2Fyolov5face-toolkit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xlite-dev%2Fyolov5face-toolkit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xlite-dev%2Fyolov5face-toolkit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xlite-dev","download_url":"https://codeload.github.com/xlite-dev/yolov5face-toolkit/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245670531,"owners_count":20653383,"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":["cpp","yolo5-face","yolo5face","yolov5-face","yolov5-face-landmark","yolov5face","yolov7-face","yolov8-face"],"created_at":"2024-10-30T02:08:58.318Z","updated_at":"2025-10-19T09:27:09.835Z","avatar_url":"https://github.com/xlite-dev.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# YOLOv5Face ToolKit\n使用 🍅🍅 Lite.AI.ToolKit C++工具箱来跑YOLO5Face人脸检测(带关键点)的一些案例(https://github.com/DefTruth/lite.ai.toolkit) , 包含ONNXRuntime C++、MNN、TNN和NCNN版本。\n\n![](resources/YOLO5Face.png)\n\n如果觉得有用，不妨给个Star⭐️🌟支持一下吧~ 🙃🤪🍀\n\n## 2. C++版本源码\n\nYOLO5Face C++ 版本的源码包含ONNXRuntime、MNN、TNN和NCNN四个版本，源码可以在 [lite.ai.toolkit](https://github.com/DefTruth/lite.ai.toolkit) 工具箱中找到。本项目主要介绍如何基于 [lite.ai.toolkit](https://github.com/DefTruth/lite.ai.toolkit) 工具箱，直接使用YOLO5Face来跑人脸检测。需要说明的是，本项目是基于MacOS下编译的 [liblite.ai.toolkit.v0.1.0.dylib](https://github.com/DefTruth/yolox.lite.ai.toolkit/blob/main/lite.ai.toolkit/lib) 来实现的，对于使用MacOS的用户，可以直接下载本项目包含的*liblite.ai.toolkit.v0.1.0*动态库和其他依赖库进行使用。而非MacOS用户，则需要从[lite.ai.toolkit](https://github.com/DefTruth/lite.ai.toolkit) 中下载源码进行编译。[lite.ai.toolkit](https://github.com/DefTruth/lite.ai.toolkit) c++工具箱目前包含70+流行的开源模型，就不多介绍了，只是平时顺手捏的，整合了自己学习过程中接触到的一些模型，感兴趣的同学可以去看看。\n* [yolo5face.cpp](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/ort/cv/yolo5face.cpp)\n* [yolo5face.h](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/ort/cv/yolo5face.h)\n* [mnn_yolo5face.cpp](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/mnn/cv/mnn_yolo5face.cpp)\n* [mnn_yolo5face.h](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/mnn/cv/mnn_yolo5faceh)\n* [tnn_yolo5face.cpp](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/tnn/cv/tnn_yolo5face.cpp)\n* [tnn_yolo5face.h](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/tnn/cv/tnn_yolo5face.h)\n* [ncnn_yolo5face.cpp](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/ncnn/cv/ncnn_yolo5face.cpp)\n* [ncnn_yolo5face.h](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/ncnn/cv/ncnn_yolo5face.h)  \n\nONNXRuntime C++、MNN、TNN和NCNN版本的推理实现均已测试通过，欢迎白嫖~  \n\n\n## 3. 模型文件\n\n### 3.1 ONNX模型文件\n可以从我提供的链接下载 ([Baidu Drive](https://pan.baidu.com/s/1elUGcx7CZkkjEoYhTMwTRQ) code: 8gin) , 也可以从本仓库下载。\n\n\n|                 Class                 |      Pretrained ONNX Files      |              Rename or Converted From (Repo)              | Size  |\n| :-----------------------------------: | :-----------------------------: | :-------------------------------------------------------: | :---: |  \n| *lite::cv::face::detect::YOLO5Face* | yolov5face-blazeface-640x640.onnx | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 3.4Mb |\n| *lite::cv::face::detect::YOLO5Face* | yolov5face-l-640x640.onnx | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 181Mb |\n| *lite::cv::face::detect::YOLO5Face* | yolov5face-m-640x640.onnx | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 83Mb |\n| *lite::cv::face::detect::YOLO5Face* | yolov5face-n-0.5-320x320.onnx | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 2.5Mb |\n| *lite::cv::face::detect::YOLO5Face* | yolov5face-n-0.5-640x640.onnx | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 4.6Mb |\n| *lite::cv::face::detect::YOLO5Face* | yolov5face-n-640x640.onnx | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 9.5Mb |\n| *lite::cv::face::detect::YOLO5Face* | yolov5face-s-640x640.onnx | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 30Mb |\n\n\n### 3.2 MNN模型文件\nMNN模型文件下载地址，([Baidu Drive](https://pan.baidu.com/s/1KyO-bCYUv6qPq2M8BH_Okg) code: 9v63), 也可以从本仓库下载。\n\n|                 Class                 |      Pretrained MNN Files      |              Rename or Converted From (Repo)              | Size  |\n| :-----------------------------------: | :-----------------------------: | :-------------------------------------------------------: | :---: |\n| *lite::mnn::cv::face::detect::YOLO5Face* | yolov5face-blazeface-640x640.mnn | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 3.4Mb |\n| *lite::mnn::cv::face::detect::YOLO5Face* | yolov5face-l-640x640.mnn | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 181Mb |\n| *lite::mnn::cv::face::detect::YOLO5Face* | yolov5face-m-640x640.mnn | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 83Mb |\n| *lite::mnn::cv::face::detect::YOLO5Face* | yolov5face-n-0.5-320x320.mnn | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 2.5Mb |\n| *lite::mnn::cv::face::detect::YOLO5Face* | yolov5face-n-0.5-640x640.mnn | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 4.6Mb |\n| *lite::mnn::cv::face::detect::YOLO5Face* | yolov5face-n-640x640.mnn | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 9.5Mb |\n| *lite::mnn::cv::face::detect::YOLO5Face* | yolov5face-s-640x640.mnn | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 30Mb |\n\n\n### 3.3 TNN模型文件\nTNN模型文件下载地址，([Baidu Drive](https://pan.baidu.com/s/1lvM2YKyUbEc5HKVtqITpcw) code: 6o6k), 也可以从本仓库下载。\n\n|                 Class                 |      Pretrained TNN Files      |              Rename or Converted From (Repo)              | Size  |\n| :-----------------------------------: | :-----------------------------: | :-------------------------------------------------------: | :---: |\n| *lite::tnn::cv::face::detect::YOLO5Face* | yolov5face-blazeface-640x640.opt.tnnproto\u0026tnnmodel | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 3.4Mb |\n| *lite::tnn::cv::face::detect::YOLO5Face* | yolov5face-l-640x640.opt.tnnproto\u0026tnnmodel | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 181Mb |\n| *lite::tnn::cv::face::detect::YOLO5Face* | yolov5face-m-640x640.opt.tnnproto\u0026tnnmodel | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 83Mb |\n| *lite::tnn::cv::face::detect::YOLO5Face* | yolov5face-n-0.5-320x320.opt.tnnproto\u0026tnnmodel | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 2.5Mb |\n| *lite::tnn::cv::face::detect::YOLO5Face* | yolov5face-n-0.5-640x640.opt.tnnproto\u0026tnnmodel | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 4.6Mb |\n| *lite::tnn::cv::face::detect::YOLO5Face* | yolov5face-n-640x640.opt.tnnproto\u0026tnnmodel | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 9.5Mb |\n| *lite::tnn::cv::face::detect::YOLO5Face* | yolov5face-s-640x640.opt.tnnproto\u0026tnnmodel | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 30Mb |\n\n\n### 3.4 NCNN模型文件\nNCNN模型文件下载地址，([Baidu Drive](https://pan.baidu.com/s/1hlnqyNsFbMseGFWscgVhgQ) code: sc7f), 也可以从本仓库下载。\n\n|                 Class                 |      Pretrained NCNN Files      |              Rename or Converted From (Repo)              | Size  |\n| :-----------------------------------: | :-----------------------------: | :-------------------------------------------------------: | :---: |\n| *lite::ncnn::cv::face::detect::YOLO5Face* | yolov5face-l-640x640.opt.param\u0026bin | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 181Mb |\n| *lite::ncnn::cv::face::detect::YOLO5Face* | yolov5face-m-640x640.opt.param\u0026bin | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 83Mb |\n| *lite::ncnn::cv::face::detect::YOLO5Face* | yolov5face-n-0.5-320x320.opt.param\u0026bin | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 2.5Mb |\n| *lite::ncnn::cv::face::detect::YOLO5Face* | yolov5face-n-0.5-640x640.opt.param\u0026bin | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 4.6Mb |\n| *lite::ncnn::cv::face::detect::YOLO5Face* | yolov5face-n-640x640.opt.param\u0026bin | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 9.5Mb |\n| *lite::ncnn::cv::face::detect::YOLO5Face* | yolov5face-s-640x640.opt.param\u0026bin | [YOLO5Face](https://github.com/deepcam-cn/yolov5-face)  | 30Mb |\n\n\n## 4. 接口文档\n\n在[lite.ai.toolkit](https://github.com/DefTruth/lite.ai.toolkit) 中，YOLO5Face的实现类为：\n\n```c++\nclass LITE_EXPORTS lite::cv::face::detect::YOLO5Face;\nclass LITE_EXPORTS lite::mnn::cv::face::detect::YOLO5Face;\nclass LITE_EXPORTS lite::tnn::cv::face::detect::YOLO5Face;\nclass LITE_EXPORTS lite::ncnn::cv::face::detect::YOLO5Face;\n```  \n\n该类型目前包含1公共接口`detect`用于进行目标检测。\n```c++\npublic:\n    /**\n     * @param mat cv::Mat BGR format\n     * @param detected_boxes_kps vector of BoxfWithLandmarks to catch detected boxes and landmarks.\n     * @param score_threshold default 0.25f, only keep the result which \u003e= score_threshold.\n     * @param iou_threshold default 0.45f, iou threshold for NMS.\n     * @param topk default 400, maximum output boxes after NMS.\n     */\n    void detect(const cv::Mat \u0026mat, std::vector\u003ctypes::BoxfWithLandmarks\u003e \u0026detected_boxes_kps,\n                float score_threshold = 0.25f, float iou_threshold = 0.45f,\n                unsigned int topk = 400);\n```\n`detect`接口的输入参数说明：\n* mat: cv::Mat类型，BGR格式。\n* detected_boxes_kps: BoxfWithLandmarks向量，包含被检测到的框box(Boxf)，box中包含x1,y1,x2,y2,label,score等成员; 以及landmarks(landmarks)人脸关键点(5个)，其中包含了points，代表关键点，是一个cv::point2f向量(vector); \n* score_threshold：分类得分（质量得分）阈值，默认0.25，小于该阈值的框将被丢弃。\n* iou_threshold：NMS中的iou阈值，默认0.3。\n* topk：默认400，只保留前k个检测到的结果。\n\n## 5. 使用案例\n这里测试使用的是yolov5face-n-640x640.onnx(yolov5n-face)nano版本的模型，你可以尝试使用其他版本的模型。\n\n### 5.1 ONNXRuntime版本\n```c++\n#include \"lite/lite.h\"\n\nstatic void test_default()\n{\n    std::string onnx_path = \"../hub/onnx/cv/yolov5face-n-640x640.onnx\"; // yolov5n-face\n    std::string test_img_path = \"../resources/4.jpg\";\n    std::string save_img_path = \"../logs/4.jpg\";\n    \n    auto *yolov5face = new lite::cv::face::detect::YOLO5Face(onnx_path);\n    \n    std::vector\u003clite::types::BoxfWithLandmarks\u003e detected_boxes;\n    cv::Mat img_bgr = cv::imread(test_img_path);\n    yolov5face-\u003edetect(img_bgr, detected_boxes);\n    \n    lite::utils::draw_boxes_with_landmarks_inplace(img_bgr, detected_boxes);\n    \n    cv::imwrite(save_img_path, img_bgr);\n    \n    std::cout \u003c\u003c \"Default Version Done! Detected Face Num: \" \u003c\u003c detected_boxes.size() \u003c\u003c std::endl;\n    \n    delete yolov5face;\n}\n```  \n\n### 5.2 MNN版本\n```c++\n#include \"lite/lite.h\"\n\nstatic void test_mnn()\n{\n#ifdef ENABLE_MNN\n    std::string mnn_path = \"../hub/mnn/cv/yolov5face-n-640x640.mnn\"; // yolov5n-face\n    std::string test_img_path = \"../resources/12.jpg\";\n    std::string save_img_path = \"../logs/12.jpg\";\n    \n    auto *yolov5face = new lite::mnn::cv::face::detect::YOLO5Face(mnn_path);\n    \n    std::vector\u003clite::types::BoxfWithLandmarks\u003e detected_boxes;\n    cv::Mat img_bgr = cv::imread(test_img_path);\n    yolov5face-\u003edetect(img_bgr, detected_boxes);\n    \n    lite::utils::draw_boxes_with_landmarks_inplace(img_bgr, detected_boxes);\n    \n    cv::imwrite(save_img_path, img_bgr);\n    \n    std::cout \u003c\u003c \"MNN Version Done! Detected Face Num: \" \u003c\u003c detected_boxes.size() \u003c\u003c std::endl;\n    \n    delete yolov5face;\n#endif\n}\n```  \n\n### 5.3 TNN版本\n```c++\n#include \"lite/lite.h\"\n\nstatic void test_tnn()\n{\n#ifdef ENABLE_TNN\n    std::string proto_path = \"../hub/tnn/cv/yolov5face-n-640x640.opt.tnnproto\"; // yolov5n-face\n    std::string model_path = \"../hub/tnn/cv/yolov5face-n-640x640.opt.tnnmodel\";\n    std::string test_img_path = \"../resources/9.jpg\";\n    std::string save_img_path = \"../logs/9.jpg\";\n    \n    auto *yolov5face = new lite::tnn::cv::face::detect::YOLO5Face(proto_path, model_path);\n    \n    std::vector\u003clite::types::BoxfWithLandmarks\u003e detected_boxes;\n    cv::Mat img_bgr = cv::imread(test_img_path);\n    yolov5face-\u003edetect(img_bgr, detected_boxes);\n    \n    lite::utils::draw_boxes_with_landmarks_inplace(img_bgr, detected_boxes);\n    \n    cv::imwrite(save_img_path, img_bgr);\n    \n    std::cout \u003c\u003c \"TNN Version Done! Detected Face Num: \" \u003c\u003c detected_boxes.size() \u003c\u003c std::endl;\n    \n    delete yolov5face;\n#endif\n}\n```  \n\n### 5.4 NCNN版本\n```c++\n#include \"lite/lite.h\"\n\nstatic void test_ncnn()\n{\n#ifdef ENABLE_NCNN\n    std::string param_path = \"../hub/ncnn/cv/yolov5face-n-640x640.opt.param\"; // yolov5n-face\n    std::string bin_path = \"../hub/ncnn/cv/yolov5face-n-640x640.opt.bin\";\n    std::string test_img_path = \"../resources/1.jpg\";\n    std::string save_img_path = \"../logs/1.jpg\";\n    \n    auto *yolov5face = new lite::ncnn::cv::face::detect::YOLO5Face(param_path, bin_path, 1, 640, 640);\n    \n    std::vector\u003clite::types::BoxfWithLandmarks\u003e detected_boxes;\n    cv::Mat img_bgr = cv::imread(test_img_path);\n    yolov5face-\u003edetect(img_bgr, detected_boxes);\n    \n    lite::utils::draw_boxes_with_landmarks_inplace(img_bgr, detected_boxes);\n    \n    cv::imwrite(save_img_path, img_bgr);\n    \n    std::cout \u003c\u003c \"NCNN Version Done! Detected Face Num: \" \u003c\u003c detected_boxes.size() \u003c\u003c std::endl;\n    \n    delete yolov5face;\n#endif\n}\n```  \n\n* 输出结果为:\n  \n![](resources/YOLO5Face.png)\n\n\n## 6. 编译运行\n在MacOS下可以直接编译运行本项目，无需下载其他依赖库。其他系统则需要从[lite.ai.toolkit](https://github.com/DefTruth/lite.ai.toolkit) 中下载源码先编译*lite.ai.toolkit.v0.1.0*动态库。\n```shell\ngit clone --depth=1 https://github.com/DefTruth/YOLO5Face.lite.ai.toolkit.git\ncd YOLO5Face.lite.ai.toolkit \nsh ./build.sh\n```  \n\n* CMakeLists.txt设置\n\n```cmake\ncmake_minimum_required(VERSION 3.17)\nproject(YOLO5Face.lite.ai.toolkit)\n\nset(CMAKE_CXX_STANDARD 11)\n\n# setting up lite.ai.toolkit\nset(LITE_AI_DIR ${CMAKE_SOURCE_DIR}/lite.ai.toolkit)\nset(LITE_AI_INCLUDE_DIR ${LITE_AI_DIR}/include)\nset(LITE_AI_LIBRARY_DIR ${LITE_AI_DIR}/lib)\ninclude_directories(${LITE_AI_INCLUDE_DIR})\nlink_directories(${LITE_AI_LIBRARY_DIR})\n\nset(OpenCV_LIBS\n        opencv_highgui\n        opencv_core\n        opencv_imgcodecs\n        opencv_imgproc\n        opencv_video\n        opencv_videoio\n        )\n# add your executable\nset(EXECUTABLE_OUTPUT_PATH ${CMAKE_SOURCE_DIR}/examples/build)\n\nadd_executable(lite_yolo5face examples/test_lite_yolo5face.cpp)\ntarget_link_libraries(lite_yolo5face\n        lite.ai.toolkit\n        onnxruntime\n        MNN  # need, if built lite.ai.toolkit with ENABLE_MNN=ON,  default OFF\n        ncnn # need, if built lite.ai.toolkit with ENABLE_NCNN=ON, default OFF\n        TNN  # need, if built lite.ai.toolkit with ENABLE_TNN=ON,  default OFF\n        ${OpenCV_LIBS})  # link lite.ai.toolkit \u0026 other libs.\n```\n\n* building \u0026\u0026 testing information:\n```shell\n[ 50%] Building CXX object CMakeFiles/lite_yolo5face.dir/examples/test_lite_yolo5face.cpp.o\n[100%] Linking CXX executable lite_yolo5face\n[100%] Built target lite_yolo5face\nTesting Start ...\nLITEORT_DEBUG LogId: ../hub/onnx/cv/yolov5face-n-640x640.onnx\n=============== Input-Dims ==============\ninput_node_dims: 1\ninput_node_dims: 3\ninput_node_dims: 640\ninput_node_dims: 640\n=============== Output-Dims ==============\nOutput: 0 Name: output Dim: 0 :1\nOutput: 0 Name: output Dim: 1 :25200\nOutput: 0 Name: output Dim: 2 :16\n========================================\ngenerate_bboxes_kps num: 2824\nDefault Version Done! Detected Face Num: 326\nLITEORT_DEBUG LogId: ../hub/onnx/cv/yolov5face-n-640x640.onnx\n=============== Input-Dims ==============\ninput_node_dims: 1\ninput_node_dims: 3\ninput_node_dims: 640\ninput_node_dims: 640\n=============== Output-Dims ==============\nOutput: 0 Name: output Dim: 0 :1\nOutput: 0 Name: output Dim: 1 :25200\nOutput: 0 Name: output Dim: 2 :16\n========================================\ngenerate_bboxes_kps num: 253\nONNXRuntime Version Done! Detected Face Num: 16\nLITEMNN_DEBUG LogId: ../hub/mnn/cv/yolov5face-n-640x640.mnn\n=============== Input-Dims ==============\n        **Tensor shape**: 1, 3, 640, 640, \nDimension Type: (CAFFE/PyTorch/ONNX)NCHW\n=============== Output-Dims ==============\ngetSessionOutputAll done!\nOutput: output:         **Tensor shape**: 1, 25200, 16, \n========================================\ngenerate_bboxes_kps num: 71\nMNN Version Done! Detected Face Num: 5\nLITENCNN_DEBUG LogId: ../hub/ncnn/cv/yolov5face-n-640x640.opt.param\ngenerate_bboxes_kps num: 34\nNCNN Version Done! Detected Face Num: 2\nLITETNN_DEBUG LogId: ../hub/tnn/cv/yolov5face-n-640x640.opt.tnnproto\n=============== Input-Dims ==============\ninput: [1 3 640 640 ]\nInput Data Format: NCHW\n=============== Output-Dims ==============\noutput: [1 25200 16 ]\n========================================\ngenerate_bboxes_kps num: 98\nTNN Version Done! Detected Face Num: 7\nTesting Successful !\n```  \n\n![](resources/10.jpg)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxlite-dev%2Fyolov5face-toolkit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxlite-dev%2Fyolov5face-toolkit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxlite-dev%2Fyolov5face-toolkit/lists"}