Caffe2 is a lightweight, modular, and scalable deep learning framework.

PyTorch implementation for 3D human pose estimation

Code for 3D object detection for autonomous driving

3D ResNets for Action Recognition

PyTorch implementation of the Social LSTM model

This's an implementation of deepmind Visual Interaction Networks paper using pytorch

PyTorch implementation of several SSD based object detection algorithms.

Image Segmentation and Object Detection in Pytorch

PyTorch implementation of GOTURN visual tracker

A faster pytorch implementation of faster r-cnn

Visualizer for Deep Neural Networks

Semantic Segmentation Architectures Implemented in PyTorch

PyTorch for Semantic Segmentation

Pytorch Imprementation of Dual Path Networks

A PyTorch implementation of the paper "Semantic Image Synthesis via Adversarial Learning" in ICCV 2017

Simple, online, and realtime tracking of multiple objects in a video sequence.

A PyTorch toolkit for 2D Human Pose Estimation.

YOLO: You only look once real-time object detector

Object Detection

MXNet port of SSD: Single Shot MultiBox Object Detector. Reimplementation of https://github.com/weiliu89/caffe/tree/ssd

Deformable Convolutional Networks

Faster R-CNN, an MXNet implementation with distributed implementation and data parallelization.

This is a pytorch version of Realtime_Multi-Person_Pose_Estimation, origin code is here https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation

C++ object detection module for mxnet-ssd

LSTM implementation, and multi-layer LSTMs for learning on graph neighborhoods