Caffe: a fast open framework for deep learning.

A library for efficient similarity search and clustering of dense vectors.

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Productive, portable, and performant GPU programming in Python.

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

Seamless operability between C++11 and Python

Open-source simulator for autonomous driving research.

Open3D: A Modern Library for 3D Data Processing

RenderDoc is a stand-alone graphics debugging tool.

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

OpenCV Bindings for node.js

A large scale non-linear optimization library

Configure Caffe in one hour for Windows users.

Caffe on both Linux and Windows

a Realistic and Rich 3D Environment

Human Pose estimation with TensorFlow framework

Matterport3D is a pretty awesome dataset for RGB-D machine learning tasks :)

3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.

A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes

tensorrt5 , centernet , centerface, deform conv, int8

Code for CVPR19 paper "Monocular Total Capture: Posing Face, Body and Hands in the Wild"

CUDA Voxelizer to convert polygon meshes into annotated voxel grids

A fork of Caffe with OpenMPI-based Multi-GPU (mainly data parallel) support for action recognition and more. More documentation please see the original readme.

TensorRT ONNX Plugin、Inference、Compile

Full version (training+testing) of implementation of Shizhan Zhu et al.'s ICCV-17 work Be Your Own Prada: Fashion Synthesis with Structural Coherence

Realtime C++ code for multi-person pose estimation

Graphs and Graph Algorithms in C++, including Minimum Cost (Lifted) Multicuts

CNN architecture for articulated human pose estimation

Provides the source code for the deep learning components mentioned in "Depth-based hand pose estimation: methods, data, and challenges"