xiangdeyizhang / FaceTrack_ncnn_HyperFT
使用mtcnn和o网络跟踪+光流跟踪进行多目标人脸跟踪，单目标人脸光流跟踪是0.5ms左右
☆119Updated 5 years ago
Alternatives and similar repositories for FaceTrack_ncnn_HyperFT:
Users that are interested in FaceTrack_ncnn_HyperFT are comparing it to the libraries listed below
- A C++ API of the LFFD with ncnn☆99Updated 5 years ago
- 适用于移动端的人脸识别模型，计算量与mobilefacenet相同，但megaface上提升了2%+☆233Updated 5 years ago
- MNN Implementation of the paper of LFFD: A Light and Fast Face Detector for Edge Devices☆128Updated 5 years ago
- Official implementation for paper "A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow for…☆204Updated 2 years ago
- implementation of ncnn's mobileFacenet☆193Updated 6 years ago
- train mtcnn head detector☆90Updated 5 years ago
- MNN MTCNN C++☆50Updated 5 years ago
- 对比ZQCNN-MTCNN与libfacedetection☆149Updated 6 years ago
- ☆141Updated 6 years ago
- 完整版caffe-cpp实现☆55Updated 5 years ago
- Deep Head(face) Pose Estimation☆42Updated 5 years ago
- ☆121Updated 6 years ago
- Support most of operator which convert mxnet to caffe.☆60Updated 5 years ago
- Retinaface caffe with mnetv2 0.25(and many more)☆57Updated 5 years ago
- Intel OpenVINO Implementation of the paper of LFFD: A Light and Fast Face Detector for Edge Devices☆45Updated 5 years ago
- caffe implementation of insightface's combined margin method☆92Updated 5 years ago
- caffe-ssd for face, head and vehicle detection☆73Updated 4 years ago
- Retinaface pytorch face-pose-detect face-key-point-detect☆36Updated 4 years ago
- ☆128Updated 6 years ago
- 开源视频人脸跟踪算法,基于mtcnn人脸检测+onet人脸跟踪,在i7-9700k的cpu检测速度可高达250fps☆220Updated 4 years ago
- This is a TensorFlow implementation of SSH: Single Stage Headless Face Detector☆32Updated 5 years ago
- A re-implementation of PFLD, https://arxiv.org/abs/1902.10859☆45Updated 5 years ago
- train Gender and Age☆39Updated 6 years ago
- a casual work about retraining to optimize mtcnn Pnet and ONet. it can achieve 100+fps on CPU with minSize 60 (1920x1080) on intel i7 67…☆203Updated 6 years ago
- 重新设计的RFBNet300,模型参数量只有0.99MB，AP达到0.78，200FPS☆100Updated 5 years ago
- 基于insightface训练mobilefacenet的相关步骤及ncnn转换流程☆265Updated 6 years ago
- Working on 68/96 landmarks detection with RetinaFace with MobileNet 0.25☆117Updated 2 years ago
- ☆82Updated 7 years ago
- insightface-caffe☆280Updated 5 years ago
- 使用pytorch实现mtcnn的训练及预测，并用pytorch的c++ api实现了前向预测的功能化☆39Updated 4 years ago