zhangmaom Goto Github PK

person_reid_baseline_pytorch

A tiny, friendly, strong pytorch implement of person re-identification baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

pose-ren

Demo code for "Pose Guided Structured Region Ensemble Network for Cascaded Hand Pose Estimation"

pytorch-unet

Pytorch implementation of the U-Net for image semantic segmentation, with dense CRF post-processing

region-ensemble-network

Repository for Region Ensemble Network based Hand Pose Estimation

revisiting_single_depth_estimation

official implementation of "Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries"

semantic-mono-depth

Geometry meets semantics for semi-supervised monocular depth estimation - ACCV 2018

smplify-x

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

so-handnet

Code repository for our paper entilted "SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation with Semi-supervised Learning", ICCV 2019.

spherehand

This project corresponds to __Self-supervised 3D hand pose estimation through training by fitting__, which is accepted in CVPR 2019.

synthetic2realistic

ECCV 2018 "T2Net: Synthetic-to-Realistic Translation for Depth Estimation Tasks"

teachnet_teleoperation

Vision-based Teleoperation of Shadow Dexterous Hand using End-to-End Deep Neural Network

tianchidasai

本项目使用的是商汤科技的mmdetection，链接如下https://github.com/open-mmlab/mmdetection 一、安装 (1)环境配置 Linux (tested on Ubuntu 16.04 and CentOS 7.2) Python 3.4+ PyTorch 1.0 Cython mmcv >= 0.2.2 (2)安装步骤 #上传的模型为已经安装后的版本，应该不需要再次安装，为保险起见，附上安装过程 先编译 cd code cd mmdetection pip install cython ./compile.sh 后安装 python(3) setup.py install # 或者用句号结尾安装 "pip install ." 二、数据准备 (1)解压数据 运行code目录下zip.py文件，解压的数据存放于data/First_round_data/目录下 (2)数据增广 运行code目录下data_augmentation.py，生成增广图集和新的标注.pkl文件，位置于mmdetection/data/coco/annotations (3)测试文件目录 运行code目录下pickle_file_creation.py，读取测试集图片名 三、模型训练 在code/mmdetection/目录下，运行 ./tools/dist_train.sh ./config/retinanet_r101_fpn_1x.py 4 --validate #其中4表示gpu数量 四、测试模型 在code/mmdetection/目录下，运行 python tools/test.py config/retinanet_r101_fpn_1x.py work_dirs/fifi/epoch_20.pth --gpus 4 --final1.pkl 运行code目录下json_to_json.py，submit/目录中将生成最终上传的json文件final.json

tianchiguangdong2019_2th

two-layers-perceptron

Python

unsupervised_depth_estimation

Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue

v2v-posenet_release

Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018

vae-hands-3d

Code to evaluate model of paper "Cross-modal Deep Variational Hand Pose Estimation"

visgel

[CVPR 2019] Connecting Touch and Vision via Cross-Modal Prediction

visualizing-cnns-for-monocular-depth-estimation

official implementation of "Visualization of Convolutional Neural Networks for Monocular Depth Estimation"