xlite-dev / scrfd-toolkitLinks
Super fast accurate face detector ! SCRFD(CVPR 2021) with MNN/TNN/NCNN/ONNXRuntime C++.
☆17Updated 3 years ago
Alternatives and similar repositories for scrfd-toolkit
Users that are interested in scrfd-toolkit are comparing it to the libraries listed below
Sorting:
- SCRFD face detection based on MNN inference framework☆17Updated 3 years ago
- ☆65Updated 3 years ago
- YOLO5Face 2021 with MNN/NCNN/TNN/ONNXRuntime☆57Updated 2 years ago
- FSANet: 1 Mb!! Head Pose Estimation with MNN、TNN and ONNXRuntime C++.☆17Updated 3 years ago
- 使用ONNXRuntime部署YOLOV7人脸+关键点检测,包含C++和Python两个版本的程序☆51Updated 2 years ago
- Windows 💻 RobustVideoMatting with ONNXRuntime/MNN/TNN C++/Python☆12Updated 3 years ago
- ncnn Android demo of PP-TinyPose☆26Updated 3 years ago
- The rknn2 API uses the secondary encapsulation of the process, which is easy for everyone to call. It is applicable to rk356x rk3588☆45Updated 3 years ago
- ☆24Updated 3 years ago
- Android hand detect and pose estimation by ncnn☆95Updated 3 years ago
- c++实现的clip推理,模型有一点点改动,但是不大,改动和导出模型的代码可以在readme里找到,模型文件都在Releases里,包括AX650的模型。新增支持ChineseCLIP☆30Updated 3 weeks ago
- Retinaface人脸检测网络 MNN、NCNN嵌入式,Linux端推理源码,包含一个卡通人脸检测的模型,脚本一键构建可执行程序☆25Updated 3 years ago
- c++ version of yolov7-mask with ncnn☆59Updated 2 years ago
- ☆10Updated 5 years ago
- ppstructure deploy by ncnn☆33Updated 11 months ago
- 开源视频人脸跟踪算法,MNN基于mtcnn人脸检测+onet人脸跟踪,在i7-9700k的cpu检测速度可高达500fps☆22Updated 5 years ago
- 基于rknn的yolov5的cpp实现,包含各种依赖库,是一个完整工程,可直接编译运行☆20Updated 3 years ago
- ☆16Updated 5 years ago
- Next Gen Face detection based on YOLOv7☆60Updated 2 years ago
- scrfd使用onnxruntime-gpu跟tensorrt加速☆23Updated 3 years ago
- Retinaface pytorch face-pose-detect face-key-point-detect☆36Updated 4 years ago
- Android BlazePose demo by ncnn☆82Updated 3 years ago
- 使用OpenCV部署L2CS-Net人脸朝向估计,包含C++和Python两个版本的程序,只依赖opencv库就可以运行☆19Updated last year
- Optimized pose detector inference for edge devices☆15Updated 2 years ago
- 用pytorch训练ssd,相比原版pytorch-ssd改动了不少☆11Updated 3 years ago
- 移动端快速人脸检测模型是基于RetinaFace的优化去掉stride8以及stride32和stride16的landmark 在CPU位Intel(R) Pentium(R) CPU G2020 @ 2.90GHz(2900 MHz)的设备中人脸检测可达到40ms/帧☆15Updated 5 years ago
- mnn yolo demos.☆76Updated 9 months ago
- YOLOX with NCNN/MNN/TNN/ONNXRuntime C++.☆13Updated 3 years ago
- deep-sdm is appied for face landmark.☆73Updated 4 years ago
- Deploy SCRFD, an efficient high accuracy face detection approach, in your web browser with ncnn and webassembly☆51Updated 2 years ago