基于Pytorch实现的实时头部姿态估计+情绪检测-附项目源码-优质项目实战.zip

# FacePose_pytorch The pytorch implement of the head pose estimation(yaw,roll,pitch) and emotion detection with SOTA performance in real time.Easy to deploy, easy to use, and high accuracy.Solve all problems of face detection at one time.(极简，极快，高效是我们的宗旨)  ## Demo # install requirements First install Anaconda3, python 3.7,and then: pip install numpy opencv-python pip install torch==1.4.0 pip install torchvision==0.5.0 Download the emoticon model (the angle model is already in the code):[https://pan.baidu.com/s/1oxznkRcP5w8lzYMAjj87-w],accesscode:WIKI # run the simple inference script(angel) Take a video of face rotation with a computer camera,and put it into video file CUDA_VISIBLE_DEVICE=0 python video.py --video_name ./video/your_video_name.mp4 (tips:You can modify video.py file to infer pictures) # run the simple inference script(emotion) Download the emoticon model into checkpoint file,and(If you use your own photo, you need to cut out the face from the picture or use Retinaface to detection the face first. You can look at it in video.py) CUDA_VISIBLE_DEVICE=0 python emotion.py --img ./img/surprise.jpg At present, only one face is supported. You can try to modify the code to support the angle and expression recognition of multiple faces. It may be a bit complicated. ## Training There is no need to model train(Using my model is enough) ## Introduction 1. Firstly, the Retinaface is used to extract the face frame, and then PFLD is used to identify the key points of the face. Finally, the key points are followed up to estimate the face pose. It is very easy to deploy and use, with high precision and fast speed. 2. We collected our own facial angle conversion data from hundreds of people and fit a simple linear model through the rotation key points of hundreds of people's faces.Experiments show that the simple mathematical linear point model is more efficient and accurate(You can also use GBDT or other algorithms to regression). 3. At the same time, referring to several papers published in the United States summit in 2020, we developed a highly accurate emotion recognition model. Results show that the methods with 95% on raf-db, 80% on affectnet, and 98% on ferplus.At present, we predict seven kinds of expressions: "surprise", "fear", "strange", "happiness", "Sadness", "anger" and "neutral". ## Performance GPU type | fps/s | Angle error(yaw,roll,pitch)| emotion Nvidia-V100 | 90 | -3°~+3° | 95% on average ## Example