The winning method in Track 1 and Track 3 at the 2nd AI City Challenge Workshop in CVPR 2018 - Official Implementation

人脸检测服务， 用于输出适合人脸识别的 人脸数据集，通过 mtcnn cnn检测人脸，通过 hopenet 开源项目确定人脸是姿态，拿到头部姿态欧拉角，通过 拉普拉斯算子 拿到人脸模糊度，通过对mtcnn 三级网络和置信度，欧拉角阈值，模糊度设置阈值筛选合适人脸

Real time streaming digital human based on nerf

通过 AdaFace 提取人脸特征向量服务

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

给飞书准备的 ChatGPT 机器人

A multi-voice TTS system trained with an emphasis on quality

Sample code for the Microsoft Cognitive Services Speech SDK

deep learning for image processing including classification and object-detection etc.

http://www.facegood.cc

The lazier way to manage everything docker

Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.

A UE5 plugin for improving the Metahuman ARKit face tracking.

Lecture notes, projects and other materials for Course 'CS205 C/C++ Program Design' at Southern University of Science and Technology.

Blendshape and kinematics solver for Mediapipe/Tensorflow.js face, eyes, pose, and hand tracking models.

A free, multiplatform SDK for real-time facial motion capture using blendshapes, and rigid head pose in 3D space from any RGB camera, photo, or video.

记录我一些关于三维模型常用的工具代码，会不断更新

A C++ header-only implementation of "Deformation Transfer for Triangle Meshes"

自己的学习历程，重点包括各种好玩的图像处理算法、运动捕捉、机器学习

集成了Tensorflow 2版本的端到端语音识别模型，并且RTF(实时率)在0.1左右/Mandarin State-of-the-art Automatic Speech Recognition in Tensorflow 2

DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

A series of python scripts to modify the metahuman rig into a new one for Maya.

基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。

pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。