ctgushiwei

Face-Anti-Spoofing-by-RGB-IR-image

Trained model and part data of face anti-spoofing with a single RGB frame,the model is trained by caffe.

HyperLPR-1

基于keras-tensorflow的车牌识别

AlignedReID

Alignedreid＋+: Dynamically Matching Local Information for Person Re-Identification.

AMSoftmax

A simple yet effective loss function for face verification.

caffe-mobilenet

A caffe implementation of mobilenet's depthwise convolution layer.

caffe-mobilenet_v2

caffe based mobilenet v2 deploy

Caffe-MobileNetV2-ReLU6

Caffe implementation of ReLU6 Layer

DeepDeblur

DeepDeblur: Text Image Recovery from Blur to Sharp

deeplearning_ai_books

deeplearning.ai（吴恩达老师的深度学习课程笔记及资源）

DREAM

This is the public repository for our accepted CVPR 2018 paper "Pose-Robust Face Recognition via Deep Residual Equivariant Mapping"

Face-alignment-mobilenet-v2

Face Alignment by Mobilenetv2

Face_Alignment_Two_Stage_Re-initialization

Test code of the CVPR 2017 paper "A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection"

Focal-Loss

loss layer of implementation

go_elife

AI make life easier

HyperLPR

基于深度学习的实时车牌识别项目 A license plate recognition(LPR) project base on deep learning.

IMDb-Face

A new large-scale noise-controlled face recognition dataset.

Incremental-Network-Quantization

Caffe Implementation for Incremental network quantization

insightface

Face Recognition Project on MXNet

interviews

Everything you need to know to get the job.

Joint-Face-Detection-and-Alignment

Caffe and Python implementation of Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks

LAB

[CVPR 2018] Look at Boundary: A Boundary-Aware Face Alignment Algorithm

License-Plate-Detect-Recognition-via-Deep-Neural-Networks-accuracy-up-to-99.9

works in real-time with detection and recognition accuracy up to 99.8% for Chinese license plates: 100 ms/plate

mace

Mobile AI Compute Engine

MobileNet-SSD

Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

ncnn-vs2013

基于ncnn的face-landmark

SeqFace

SFD

S³FD: Single Shot Scale-invariant Face Detector

sphereface

Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.

tensorflowbook

tensorflow教程每个章节的源码

wattman_sw

wattman