guozhongluo

Realtime_Multi-Person_Pose_Estimation

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

mobile-deep-learning

This research aims at simply deploying CNN(Convolutional Neural Network) on mobile devices, with low complexity and high speed.

seglink

An Implementation of the seglink alogrithm in paper Detecting Oriented Text in Natural Images by Linking Segments

CCDL

深度学习应用框架，专注于深度学习的工程应用

ncnn-vs2013

基于ncnn的face-landmark

ncnn-vs2015-examples-demo

ncnn vs2015 examples demo

DeepCompression-caffe

Caffe for Deep Compression

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

SynthText_Chinese_version

Modify from https://github.com/ankush-me/SynthText.git to generate chinese character

openpose

OpenPose: A Real-Time Multi-Person Keypoint Detection And Multi-Threading C++ Library

sceneReco

ctpn+crnn Scene character recognition

YOLO

YOLO VS2015 c++ code， Only need opencv, do not rely on the Caffe Library

caffe2

Caffe2 is a cross-platform framework made with expression, speed, and modularity in mind.

mini-caffe

Minimal runtime core of Caffe, Forward only, GPU support and Memory efficiency.

convolutional-pose-machines-release

Code repository for Convolutional Pose Machines, CVPR'16

deconvfaces

Generating faces with deconvolution networks

4dface

Real-time 3D face tracking and reconstruction from 2D video

caffe-ssd

SSD Caffe: a fast open framework for deep learning.

dataset

The Open Images dataset

EasyCNN

easy convolution neural network

DeepFace

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

image-style-transfor

ImageColorTheme

Extract Color Themes from Images

2dMorphing

2D Image Morphing Algorithms based on mesh warping. C++ project, which is transplanted from the c codes given by Yurong Sun and George Wolberg. Details: http://davis.wpi.edu/~matt/courses/morph/2d.htm