liyang53719

FCRN-DepthPrediction

Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)

hdrcnn

HDR image reconstruction from a single exposure using deep CNNs

monodepth

Unsupervised single image depth prediction with CNNs

TX2

what TX2 need

2016_person_re-ID

TOMM2017 A Discriminatively Learned CNN Embedding for Person Re-identification

cogwerx-jetson-tx2

Deep learning builds for NVIDIA Jetson TX2

ORB_SLAM

A Versatile and Accurate Monocular SLAM

ZCU102_YOLO

We porting YOLO on ZCU102 based on Zynq UltraScale MPSoC Base TRD 2017.1.

Face-Pose-Net

Estimate 3D face pose by a Convolutional Neural Network

PipeCNN

An OpenCL-based FPGA Accelerator for Convolutional Neural Networks

hourglasstensorlfow

Tensorflow implementation of Stacked Hourglass Networks for Human Pose Estimation

DeepLabV3-Tensorflow

Reimplementation of DeepLabV3

MobileNet-Caffe

Caffe Implementation of Google's MobileNets (v1 and v2)

AlphaPose

caffe2

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

bnn-fpga

Binarized Convolutional Neural Networks on Software-Programmable FPGAs

TrainAConvolutionalNeuralNetworkForRegressionExample

This project is build for retrain openpose network

vivado-library

Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

cocoapi

COCO API - Dataset @ http://cocodataset.org/

Joint-Demosaic-and-Denoising-with-ADMM

Code for ICIP 2017 paper JOINT DEMOSAICING AND DENOISING OF NOISY BAYER IMAGES WITH ADMM

Realtime_Multi-Person_Pose_Estimation

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

pose-tensorflow

Human Pose estimation with TensorFlow framework

GNet-pose

Source code release of the paper: Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation.

PoseTrack-CVPR2017

face_specific_augm

Face Renderer to perform Domain (Face) Specific Data Augmentation

binary-human-pose-estimation

This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian Bulat and Georgios Tzimiropoulos.

deep-photo-styletransfer

Code and data for paper "Deep Photo Style Transfer": https://arxiv.org/abs/1703.07511

caffe

Ristretto: Caffe-based approximation of convolutional neural networks.

CMT-CNN

Learning Cross-Modal Deep Representations for Robust Pedestrian Detection