All Projects → yeziyang1992 → Python Tensorflow Face V2.0

yeziyang1992 / Python Tensorflow Face V2.0

Licence: apache-2.0
基于tensorflow的人脸识别

Programming Languages

python
139335 projects - #7 most used programming language
python3
1442 projects

Projects that are alternatives of or similar to Python Tensorflow Face V2.0

Facial Expression Recognition.pytorch
A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset
Stars: ✭ 1,013 (+1105.95%)
Mutual labels:  face-recognition
Face Recognition
A framework for creating and using a Face Recognition system.
Stars: ✭ 60 (-28.57%)
Mutual labels:  face-recognition
Deepface
A Lightweight Deep Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Framework for Python
Stars: ✭ 1,150 (+1269.05%)
Mutual labels:  face-recognition
Opencv Face Filters
Snapchat-like Face Filters in OpenCV
Stars: ✭ 51 (-39.29%)
Mutual labels:  face-recognition
Facenet Face Recognition
This is the research product of the thesis manifold Learning of Latent Space Vectors in GAN for Image Synthesis. This has an application to the research, name a facial recognition system. The application was developed by consulting the FaceNet model.
Stars: ✭ 54 (-35.71%)
Mutual labels:  face-recognition
Awesome machine learning solutions
A curated list of repositories for my book Machine Learning Solutions.
Stars: ✭ 65 (-22.62%)
Mutual labels:  face-recognition
Smart Surveillance System Using Raspberry Pi
This is my Third Year Project for face recognition using OpenCV
Stars: ✭ 41 (-51.19%)
Mutual labels:  face-recognition
Ai Reading Materials
Some of the ML and DL related reading materials, research papers that I've read
Stars: ✭ 79 (-5.95%)
Mutual labels:  face-recognition
Linux face unlock
A face authentication system for Ubuntu that works while logging in and running "sudo" commands with a friendly CLI to operate it.
Stars: ✭ 55 (-34.52%)
Mutual labels:  face-recognition
Celebamask Hq
A large-scale face dataset for face parsing, recognition, generation and editing.
Stars: ✭ 1,156 (+1276.19%)
Mutual labels:  face-recognition
Facerecognition Gui App
A very Simple GUI APP for Face Detection and Recognition
Stars: ✭ 50 (-40.48%)
Mutual labels:  face-recognition
Image recognition
Packages for image recognition - Robocup TU/e Robotics
Stars: ✭ 53 (-36.9%)
Mutual labels:  face-recognition
Face Api
JavaScript module for face detection and face recognition Using Tensorflow/JS
Stars: ✭ 67 (-20.24%)
Mutual labels:  face-recognition
Face Identification With Cnn Triplet Loss
Face identification with cnn+triplet-loss written by Keras.
Stars: ✭ 45 (-46.43%)
Mutual labels:  face-recognition
Tensorflow Implementation Of Lcnn
A Tensorflow implementation of "A Light CNN for Deep Face Representation with Noisy Labels"
Stars: ✭ 74 (-11.9%)
Mutual labels:  face-recognition
Facedataset
制作亚洲人脸数据集
Stars: ✭ 42 (-50%)
Mutual labels:  face-recognition
Boss Detector
Change monitor screen when your boss is coming towards you!
Stars: ✭ 63 (-25%)
Mutual labels:  face-recognition
Insightface
State-of-the-art 2D and 3D Face Analysis Project
Stars: ✭ 10,886 (+12859.52%)
Mutual labels:  face-recognition
Low Face Mode
Dim and brighten the screen based on whether or not you are present! OpenCV detects face with webcam and dims screen if not present.
Stars: ✭ 75 (-10.71%)
Mutual labels:  face-recognition
Face Recognition Cpp
Real Time Face Recognition Detector. Over 30FPS on CPU!
Stars: ✭ 68 (-19.05%)
Mutual labels:  face-recognition

Python-Tensorflow-Face-v2.0

  1. 本文以Triplet网络为基础,改进了原有的通过训练分类器来检测人脸的方法,大大提高了识别的准确度。
  2. 本人使用训练数据集为微软MS-Celeb-1M数据集,[下载地址].(https://www.msceleb.org/download/aligned)
  3. 下载的数据集为.tsv格式,需要还原成jpg格式图片。需要把extracted.py拷贝到tsv文件同目录下,然后运行:
    $ python extracted.py --outputDir=data FaceImageCroppedWithAlignment.tsv
    尽量留有足够大的硬盘空间。
  4. 还需要对数据集进行清理,可到这链接 (密码:9ykp)下载干净的列表,并把下载的txt文件、faceshutil.py和data文件夹放在同一目录下,运行py文件即可
  5. 把get_align_face.py放到out同目录下,进行最后的人脸对齐。得到的train_faces文件夹放在项目同级文件夹下。
  6. 程序运行流程:
    1. 首先运行makefile.py文件,生成一些目录。
    1. 链接( 密码:8tgk)下载LFW数据集,放在 ./temp/lfw/文件夹下,最后的目录是./tmp/lfw/lfw。这是为了测试准确率。
    1. 运行run.py文件,如果想要继续接着训练,需要把new改为True.这样做的目的是可以间断训练,每次训练完一段时间退出,可以接着训练。
    1. 训练完成后,可以运行lfw_test.py文件查看准确率。
  1. 训练好的模型可以放到这个项目中https://github.com/yeziyang1992/Face_Recognition_Client 检验。
  2. 如有问题探讨,邮箱联系:[email protected]
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].