changooh

AugmentedAutoencoder

Official Code: Implicit 3D Orientation Learning for 6D Object Detection from RGB Images

bpycv

Computer vision utils for Blender (generate instance annoatation, depth and 6D pose in one line code)

cocosynth

COCO Synth provides tools for creating synthetic COCO datasets.

deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

deep-learning-with-python

Deep Learning Practice materials

dl-colab-notebooks

Try out deep learning models online on Google Colab

fastbook

Draft of the fastai book

ggcnn

Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach" (RSS 2018)

grasp_multiObject

Robotic grasp dataset for multi-object multi-grasp evaluation with RGB-D data. This dataset is annotated using the same protocal as Cornell Dataset, and can be used as multi-object extension of Cornell Dataset.

grasp_multiObject_multiGrasp

An implementation of our RA-L work 'Real-world Multi-object, Multi-grasp Detection'

changooh/AugmentedAutoencoder

Official Code: Implicit 3D Orientation Learning for 6D Object Detection from RGB Images

changooh/bpycv

Computer vision utils for Blender (generate instance annoatation, depth and 6D pose in one line code)

changooh/cocosynth

COCO Synth provides tools for creating synthetic COCO datasets.

changooh/deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

changooh/deep-learning-with-python

Deep Learning Practice materials

changooh/dl-colab-notebooks

Try out deep learning models online on Google Colab

changooh/fastbook

Draft of the fastai book

changooh/ggcnn

Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach" (RSS 2018)

changooh/grasp_multiObject

Robotic grasp dataset for multi-object multi-grasp evaluation with RGB-D data. This dataset is annotated using the same protocal as Cornell Dataset, and can be used as multi-object extension of Cornell Dataset.

changooh/grasp_multiObject_multiGrasp

An implementation of our RA-L work 'Real-world Multi-object, Multi-grasp Detection'

changooh/insightbook.opencv_project_python

changooh/monodepth2

Monocular depth estimation from a single image

changooh/MSMLHACK

MS_ML_HACK

changooh/openpifpaf

Official implementation of "PifPaf: Composite Fields for Human Pose Estimation" in PyTorch.

changooh/openpifpafwebdemo

Web browser based demo of OpenPifPaf.

changooh/Python-Data-Analysis-and-Image-Processing-Tutorial

파이썬을 활용한 데이터 분석과 이미지 처리 - 강의 자료 및 소스코드 Repository입니다.

changooh/Revisiting_Single_Depth_Estimation

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

changooh/robotic-grasping

changooh/roLabelImg

Label Rotated Rect On Images for training

changooh/selfDrivingDemo

CNN기반 자율주행모델 시뮬레이션 데모입니다.

changooh/simData

The dataset of our RA-L work 'Learning Affordance Segmentation for Real-world Robotic Manipulation via Synthetic Images'

changooh/TensorFlow

Deep Learning Zero to All - Tensorflow

changooh/todaycode-hands-on

todaycode-hands-on

changooh/uois

changooh/visual-pushing-grasping

Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.

changooh/yolact

customized yolact

changooh/yolact_copy

A simple, fully convolutional model for real-time instance segmentation.