Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

A toolkit for making real world machine learning and data analysis applications in C++

(CGCSTCD'2017) An easy, flexible, and accurate plate recognition project for Chinese licenses in unconstrained situations. CGCSTCD = China Graduate Contest on Smart-city Technology and Creative Design

Open Source Biometrics, Face Recognition

LSD-SLAM

Multiple Object Tracker, Based on Hungarian algorithm + Kalman filter.

A C++ Background Subtraction Library with wrappers for Python, MATLAB, Java and GUI on QT

A Versatile and Accurate Monocular SLAM

Configure Caffe in one hour for Windows users.

[CVPR 2018] Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks

LINE: Large-scale information network embedding

A common bricks library for building scalable and portable distributed machine learning.

dabnn is an accelerated binary neural networks inference framework for mobile platform

Deep face segmentation in extremely hard conditions

Faster Recurrent Neural Network Language Modeling Toolkit with Noise Contrastive Estimation and Hierarchical Softmax

Facial detection, landmark tracking and expression transfer library for Windows, Linux and Mac

C++11 implementation of the supervised descent optimisation method

A library for k-nearest neighbor search

A lightweight and user friendly C++ library for deep and convolutional neural network with GPU acceleration

An implementation of the largeVis algorithm for visualizing large, high-dimensional datasets, for R

Original open source people tracking library (now deprecated with the release of OPT v2 "Gnocchi").

Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usage

C++ model train&inference framework

mojo cnn: c++ convolutional neural network

C++ implementation of Face Alignment at 3000 FPS via Regressing Local Binary Features

Unsupervised Learning using Videos (ICCV 2015)

Convolutional (Patch) Networks for Semantic Segmentation

Code of my CVPR'16 paper: "Efficient 3D Room Shape Recovery From a Single Panorama."

A large collection of mostly reinforcement learning agents.