Skip to main content

Package for Face Recognition API

Project description





  1. 基礎: 機器學習/深度學習/圖形處理器技術

  2. "DeepFace: Closing the Gap to Human-Level Performance in Face Verification"


最早的深度學習人臉辨識, 已有 metric learning 的觀念 (使用 siamese network)

但, 無權值共享的 CNN 帶來過多的參數, 3D alignment 也顯得過度複雜

  1. "Deep Face Recognition"


著名的 VGG Face, 整套流程包含 face dataset 的建立

  1. "FaceNet: A Unified Embedding for Face Recognition and Clustering"


用 triplet loss 產生 128 維的 FaceNet embeddings (此向量空間內的距離代表人臉的相似程度), LFW 準確度超過 99%


  1. (A) "Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations"


經典的 VGG Network, 包含 VGG16, VGG19

  1. "Going Deeper With Convolutions"

GoogLeNet, 使用 3x3, 1x1 convolution 構成 inception 網路模組

  1. "Deep residual learning for image recognition"

residual network, 解決梯度消失問題, 讓訓練 100 (甚至1000) 層以上的深度學習變得容易

  1. "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications"

mobile net, 小而快的網路, 但犧牲準確度,

A. "Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments"

*著名的 lfw 人臉辨識準確率測試資料集


99% * LFW precision-recall * LFW ROC

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

frapi-0.1.6.tar.gz (7.3 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page