xiaoyong

C3D

C3D is a modified version of BVLC caffe to support 3D ConvNets.

LightGBM

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

3D-embryo

caffe_rtpose

Realtime C++ code for multi-person pose estimation

convolutional-pose-machines-release

Code repository for Convolutional Pose Machines, CVPR'16

Realtime_Multi-Person_Pose_Estimation

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

visual_genome_python_driver

A python wrapper for the Visual Genome API

universe

Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.

TorchCraft

Connecting Torch to StarCraft

dataset

The Open Images dataset

GOTURN

Source code for paper: Learning to Track at 100 FPS with Deep Regression Networks, Held, et al. ECCV 2016

tiny

Tiny Face Detector, CVPR 2017

kmcuda

Large scale K-means and K-nn implementation on NVIDIA GPU / CUDA

caffe-mt

This is a fork of caffe added some useful layers, the original caffe site is https://github.com/BVLC/caffe.

conv_arithmetic

A technical report on convolution arithmetic in the context of deep learning

pva-faster-rcnn

Demo code for PVANet

pix2pix

Image-to-image translation with conditional adversarial nets

context-encoder

[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs

dcgan_code

Deep Convolutional Generative Adversarial Networks

neovim

Vim-fork focused on extensibility and usability

mpv

🎥 Command line video player

cnn-benchmarks

Benchmarks for popular CNN models

CNNdroid

Open Source Library for GPU-Accelerated Execution of Trained Deep Convolutional Neural Networks on Android

DeepLearningFlappyBird

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

craftGBD

code for CUImage and CUVideo

FCNT

vdetlib

Video detection library

T-CNN

ImageNet 2015 Object Detection from Video (VID)

caffe-rfcn

Caffe branch for R-FCN

jekyll-bootstrap

The quickest way to start and publish your Jekyll powered blog. 100% compatible with GitHub pages.