guowenzhe Goto Github PK

algorithm-practice

Learning algorithm

algorithm-test

began-tensorflow

侧脸->正脸训练模型：Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"

beginning-javascript

test this book

caffe

Caffe: a fast open framework for deep learning.

caffe-master-20150826-triplet

基于20150826 caffe版本上添加的triplet loss与L2 normalize 层

caffe-squeezenet

caffe_ocr

主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构

code-git-test

code-tortoisegit-test

corewords

get core words

cosface

Tensorflow implementation for paper CosFace: Large Margin Cosine Loss for Deep Face Recognition

data_augment

using cut mirror and elastic Distort to get more input date

deep-learning-coursera

Deep Learning Specialization by Andrew Ng on Coursera.

deepdetect

Deep Learning API and Server in C++11 with Python bindings and support for Caffe, Tensorflow, XGBoost and TSNE

deepface

Face analysis mainly based on Caffe. At this time, face analysis tasks like detection, alignment and recognition have been done.

deepid

deep face recognition algorithm

deepid2

use caffe to training a deepid2 net with softmax and contrastive loss, adding identity2verify_layer to translate a single sample into pairwise, thus mix the softmax and contrastive layer together

deepid2_based_inception

this network is built based on Inception. and optimize it by using identification loss and verification loss which derive from DeepID2+

deeplearning

深度学习相关教程

deeplearning_demo

some demo

dlcv_for_beginners

《深度学习与计算机视觉》配套代码

facerank_modify

this project was modify by this version: https://github.com/fendouai/FaceRank

faceverification

An Experimental Implementation of Face Verification, 96.8% on LFW.

faster_rcnn_logo

Application of py_faster_rcnn for logo detection task: ZF & VGG16

have-fun-with-machine-learning

An absolute beginner's guide to Machine Learning and Image Classification with Neural Networks

javascript

Learning from javascript books

joint_bayesian

mtcnn

mtcnn_caffe

Simple implementation of kpzhang93's paper from Matlab to c++, and don't change models.