Gager-Git-life / Face-alignment
Face key point alignment based on Ultraface and Pfld by MNN
☆9Updated 3 years ago
Related projects: ⓘ
- Caffe++: assemble new features to enhance Caffe☕️☆11Updated 5 years ago
- ☆34Updated 5 years 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☆21Updated 4 years ago
- Position sensitive PreciseRoIPooling without roi coordinates gradient backward☆16Updated 6 years ago
- SSD-MobileNet with Tencent ncnn framework☆11Updated 6 years ago
- convert pytorch trained yolo model to ncnn for Flexible deployment☆10Updated 6 years ago
- ☆30Updated 5 years ago
- Rethinking Bottleneck Structure for Efficient Mobile Network Design☆13Updated 4 years ago
- This is an official enhanced PyTorch implementation of FSD based on the idea of LFFD.☆11Updated 4 years ago
- Custom Centernet for face detection and other detection tasks☆20Updated 4 years ago
- face recognize based on tvm☆19Updated 5 years ago
- A light and fast one class detection framework for edge devices.☆18Updated 4 years ago
- InsightFace_Tensorrtx aims to implement InsightFace_Pytorch with tensorrt network definition APIs.☆9Updated 4 years ago
- ☆10Updated this week
- ☆11Updated this week
- GHM_Detection☆16Updated 5 years ago
- train Snet(by thundernet) in imagenet☆18Updated 4 years ago
- MobileNet-SSD Face Detection by ncnn☆21Updated 5 years ago
- pytorch face_landmark☆26Updated last year
- TensorRT half precision inference routine on a API-based TensorRT model☆13Updated 6 years ago
- ICME 2017 "Learning a Multi-Center Convolutional Network for Unconstrained Face Alignment"☆16Updated 4 years ago
- ☆15Updated this week
- siamise networks☆14Updated 7 years ago
- face landmark detection based on tvm☆10Updated 5 years ago
- 用mtcnn检测人脸，使用kcf进行人脸跟踪☆19Updated 5 years ago
- A re-implementation of PFLD, https://arxiv.org/abs/1902.10859☆45Updated 5 years ago
- ☆15Updated 4 years ago
- DenseShuffleNet for Semantic Segmentation using Caffe for Cityscapes and Mapillary Vistas Dataset☆10Updated 6 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 4 years ago
- Code for detection-based head tracking.☆14Updated 7 years ago