🍎 My own face recognition with deep neural networks.
Alternatives To Face_recognition
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
Pytorch64,43414617 hours ago23August 10, 202211,492otherC++
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Tensorflow Examples42,312
5 months ago218otherJupyter Notebook
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
Pytorch Tutorial25,860
17 days ago88mitPython
PyTorch Tutorial for Deep Learning Researchers
Data Science Ipython Notebooks23,924
6 months ago26otherPython
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
Ml From Scratch21,618
5 months ago4June 17, 201748mitPython
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
Awesome Deep Learning20,409
20 days ago25
A curated list of awesome Deep Learning tutorials, projects and communities.
Jina17,8962a day ago2,019July 06, 202239apache-2.0Python
🔮 Build multimodal AI services via cloud native technologies · Neural Search · Generative AI · Cloud Native
Awesome Tensorflow16,809
3 months ago30cc0-1.0
TensorFlow - A curated list of dedicated resources http://tensorflow.org
6 years ago10
Oxford Deep NLP 2017 course
5 months ago13apache-2.0Lua
Face recognition with deep neural networks.
Alternatives To Face_recognition
Select To Compare

Alternative Project Comparisons


这个仓库是使用TensorFlow 2.0框架,并基于 cvpr2019-arcface 论文上完成的,其中主要分为四大块:人脸检测、人脸矫正、提取特征和特征比对。各个模块的大小和在我的 17 款 macbook-pro 的 CPU 上跑耗时如下:

  • 人脸检测:使用的是 mtcnn 网络,模型大小约 1.9MB,耗时约 30ms;
  • 人脸矫正:OpenCV 的仿射变换,耗时约 0.83ms;
  • 提取特征:使用 MobileFaceNet(或IResNet)网络,耗时约30ms;
  • 特征比对:使用曼哈顿距离,单次搜索和完成比对耗时约 0.011 ms;



  1. 打开相机注册:
$ python register_face.py -person Sam -camera

s 键保存图片,需要在不同距离和角度拍摄 10 张图片或者按 q 退出。

  1. 导入人脸图片:

保证文件的名字与注册人名相同,并且每张图片只能出现一张这个 ID 的人脸。

$ python register_face.py -person Jay


Method LFW(%) CFP-FP(%) AgeDB-30(%) MegaFace(%) cpu-time weights
MobileFaceNet 99.50 88.94 95.91 --- 35ms 下载链接
IResNet 99.77 98.27 98.28 98.47 435ms 提取码: xgmo

识别模型用的是 MobileFaceNet 网络,这里直接使用了 insightface 在 ms1m-refine-v1 三百万多万张人脸数据集上训练的模型。这部分工作在 mxnet 分支上,你可以通过 git checkout mxnet 进行切换。

由于该模型是 mxnet 格式,因此使用了 mmdnn 导出了其模型权重 mobilefacenet.npy。接着使用了 TF2 自己手写了一个 MobileFaceNet 网络并导入权重,预测精度没有任何损失。这部分工作在 master 分支上。


$ python main.py
Popular Neural Projects
Popular Deep Learning Projects
Popular Machine Learning Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Deep Learning
Neural Network
Image Processing
Object Detection
Face Recognition
Image Classification
Face Detection