Jerry.D's repositories
3d-pose-baseline
A simple baseline for 3d human pose estimation in tensorflow.
activityrecognition
Information about activity recognition
awesome-github
A curated list of awesome GitHub guides, articles, sites, tools, projects and resources. 收集这个列表,只是为了更好地使用亲爱的GitHub,欢迎提交pr和issue。
awesome-machine-learning-cn
机器学习资源大全中文版,包括机器学习领域的框架、库以及软件
caffe
Caffe: a fast open framework for deep learning.
caffe2
This is currently an experimental refactoring of Caffe.
convnet-benchmarks
Easy benchmarking of all publicly accessible implementations of convnets
cpm
Convolutional Pose Machines in TensorFlow
cs20si
cs20si learning note
cs231n
cs231n assignments
DeepSkeleton
Code for CVPR2016 and TIP papers about Object Skeleton Detection with Fully Convolutional Neural Networks.
EasyOpenPose
OpenPose的简单实现
fast-rcnn
Fast R-CNN
MachineLearning
一些关于机器学习的学习资料与研究介绍
OCRDemo
使用百度的人工智能-文字识别功能,拍照,将图片中的文字转化为文本,复制进行使用
OpenCV3-Intro-Book-Src
《OpenCV3编程入门》书本配套源码||《Introduction to OpenCV3 Programming》Book Source Code
openpose
OpenPose: A Real-Time Multi-Person Keypoint Detection And Multi-Threading C++ Library
OpenPose-1
OpenPose的简单实现版本,简洁不简单,so easy. 就一个cpp
SRN
Side-output Residual Network for Object Symmetry Detection in the Wild
st-resnet
Code release for "Spatiotemporal Residual Networks for Video Action Recognition", NIPS16 & "Spatiotemporal Multiplier Networks for Video Action Recognition", CVPR17.
Technical_Book_DL
This note presents in a technical though hopefully pedagogical way the three most common forms of neural network architectures: Feedforward, Convolutional and Recurrent.
temporal-segment-networks
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016
tensorflow-vgg16-train-and-test
The purpose of this program is for studying. Using tensorflow trains the vgg16 and recognizes only two kinds of picture(cat and dog).
UCF-101_video_classification
Classify UCF101 videos using one frame at a time with a CNN(InceptionV3)
UntrimmedNet
Weakly Supervised Action Recognition and Detection
video-caffe
Video-friendly caffe -- comes with a recent version of Caffe (Sep 2017), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data
Video-Classification-Action-Recognition
some famous works and new content to be added