Kentaro Wada

Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.

A graphical tool for drawing labels on images, draw shapes around objects to create training data for AI vision models, with AI-assisted annotation to speed up the process.

Google Drive public file downloader when curl/wget fails.

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

PyTorch for Numpy users. https://pytorch-for-numpy-users.wkentaro.com

Rich Image Visualization with Minimum Dependency (no OpenCV, Matplotlib)

MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion, CVPR 2020

Chainer Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

Command line tools for quick video editing.

Navigate in Google Drive as you do on shell (gshell = Google Drive + Shell).

Python binding of the OctoMap library.

Get up and running with SAM1,2,3, EfficientSAM, YOLO-World, and other promptable vision models locally.

ONNX export and inference for SAM3.

Example Code of Calling Python from C++ with PyBind11.

ReorientBot: Learning Object Reorientation for Specific-Posed Placement, ICRA 2022

Chainer Implementation of Mask R-CNN. (Training code to reproduce the original result is available.)

SafePicking: Learning Safe Object Extraction via Object-Level Mapping, ICRA 2022

My dotfiles.

Toolkit for PASCAL3D dataset.

Command line interface for MoviePy.

ONNX models of YOLO-World (an open-vocabulary object detection).

Annotate satellite imagery with LabelMe and convert the annotations to GeoJSON for use in GIS tools like QGIS.

logboard: Monitor and Compare Logs on Browser/Terminal.

Render a JSON with jq patterns.

Volumetric Fusion of Multiple Semantic Labels and Masks

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

Imshow - Flexible and Customizable Image Display with Python

Image Visualization Tools for C++

Release tools from GitHub to PyPi.

3D Object Segmentation for Shelf Bin Picking by Humanoid with Deep Learning and Occupancy Voxel Grid Map (Humanoids2016)

Fork to export to ONNX for Labelme.

Fork to export to ONNX for Labelme.

Zero to (https://)Myapp. Using Flask, Gunicorn, Nginx, and Certbot.

Chainer implementation of "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Network".

Organize screenshot/screencast in a uniform manner.

No description.

Chainer implementation of "Toward Multimodal Image-to-Image Translation".

A Flexible Framework for Robot Control in Python

Non-interactive git hunk staging for AI agents.

Python library for loading and using triangular meshes.

Transgender of real persons to achieve real harem, with mixed reality on Hololens.

Probabilistic 3D Multilabel Real-time Mapping for Multi-object Manipulation (IROS2017)

Experimental packages for Fanuc manipulators within ROS-Industrial

Simple example of Catkin + Cython.

See Gotenshita(御殿下) court open status.

StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

Homebrew installation of labelme.

Render a JSON with jq patterns. Faster version in Rust -> https://github.com/wkentaro/jqk

A flexible framework of neural networks for deep learning

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

Contains basic Python drivers for accessing an Axis camera's MJPG stream. Also provides control for PTZ cameras.

Code for Polygon-RNN++ (CVPR 2018)

ChainerCV: a Library for Computer Vision in Deep Learning

My personal page.

supereight: a high performance template octree library and a dense volumetric SLAM pipeline implementation

Image augmentation for machine learning experiments.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

:metal: LabelImg is a graphical image annotation tool and label object bounding boxes in images

Convolutional Neural Networks

Chainer folk of Fast R-CNN (Object Detection Method)

`cd` to repos in workspace managed by wstool.

Open ROS Components for Robots from Fetch Robotics

Gazebo simulator for Fetch

Unofficial Python API client for Notion.so

Fast K-Nearest Neighbor search with GPU

Easy-to-use glTF 2.0-compliant OpenGL renderer for visualization of 3D scenes.

Segmentation models with pretrained backbones. PyTorch.

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

an abstraction to train neural networks

Demos of ROS(-Industrial) functionality specifically for (simulated) Fanuc robots

Fixes the crash described in: https://x.com/wkentaro_/status/1825042400563396988

MoveIt! ROS

MoveIt! configurations for different robots

The MoveIt! motion planning framework

ROS messages used by MoveIt

Yet Another Robotics and Reinforcement (YARR) learning framework for PyTorch.

A toolkit for robot learning research.

NumPy-like API accelerated with CUDA

MIT-Princeton Vision Toolbox for Robotic Pick-and-Place at the Amazon Robotics Challenge 2017 - Grasp Detection and Image Matching for Novel Objects with Deep Learning

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

Object Detection with Faster R-CNN in Chainer

Package which provides conversions from PCL data types to ROS data types.

Simple utility to show nVidia GPU memory usage wrt. CUDA device IDs.

Vim plugin for ROS development

c++ port of the python code from https://github.com/gnebehay/CMT

Packages for common geometric calculations including the ROS transform library, "tf". Also includes ROS bindings for "bullet" physics engine and "kdl" kinematics/dynamics package.

Generates index page like mod_autoindex.

The image_common of http://www.ros.org/wiki/image_common has moved to github

RViz display plugins for visualizing octomap messages in ROS

An Efficient Probabilistic 3D Mapping Framework Based on Octrees. Contains the main OctoMap library, the viewer octovis, and dynamicEDT3D.

The turtlebot stack provides all the basic drivers for running and using a TurtleBot.

Contains packages for modeling various aspects of robot information, specified in the Xml Robot Description Format (URDF). The core package of this stack is urdf, which parses URDF files, and constructs an object model (C++) of the robot.

Code used in tutorials found on ROS wiki

ROS stack for mapping with OctoMap, contains octomap_server package

No description.

awesome topics for jsk

Open Robotics Automation Virtual Environment: An environment for testing, developing, and deploying robotics motion planning algorithms.

ROS wrapper for openni 2.0

Launchfiles for use with depth cameras.

Launch files to open an OpenNI2 device and load all nodelets to convert raw depth/RGB/IR streams to depth images, disparity images, and (registered) point clouds.

PCL pcd fileformat i/o in Python

:zap: Dark powered Vim/Neovim plugin manager

Caffe models in TensorFlow

Models built with TensorFlow

Simple Image Annotation Tool

A fast, extensible progress bar for Python

Computation using data flow graphs for scalable machine learning

Guided Policy Search

ROS Messages and robot description files for the Baxter Research Robot

ROS package containing PCL-related messages

ROS 3D Robot Visualizer

A release automation tool which makes releasing catkin (http://ros.org/wiki/catkin) packages easier.

Image Processing SciKit (Toolbox for SciPy)

OpenRTM - ROS interoperability packages

Python bindings to the pointcloud library (pcl)

Lint macros for ROS packages

No description.

No description.

Check catkin packages for common errors

Wrappers, tools and additional API's for using ROS with Gazebo. Formally simulator_gazebo stack

Allows one to create "nodelets" -- ROS node-like entities that run within the same process so as to avoid IPC and serialization overhead

No description.

Fast R-CNN

A Machine Learning library based on Theano

Use a text editor. Make a PDF.

Deep neural networks without the learning cliff! A wrapper library compatible with scikit-learn.

The ROS Cheatsheet source

This package is a ROS service that supports generic machine learning algorithms for supervised classification.

A CMake-based build system that is used to build all packages in ROS.

Core ROS packages

Tools for using the Kinect One (Kinect v2) in ROS

A server for preview rst document instantly

An informative and fancy bash prompt for Git users

Full-featured Python interface for the Slack API

rosdep multi-package manager system dependency tool

No description.

Messages to slack from command line

A faster and simpler version of antigen written in Go

A light-weight version of rosdoc that does not rely on ROS infrastructure for crawling packages.

Simple text-based Terminal Screensaver

Animated pipes terminal screensaver

Additional completion definitions for Zsh.

Pythonic command line arguments parser, that will make you smile

Git for Humans, Inspired by GitHub for Mac™.

Python Command-line Application Tools

Command line tools for working with catkin

A delightful community-driven framework for managing your zsh configuration. Includes 180+ optional plugins (rails, git, OSX, hub, capistrano, brew, ant, php, python, etc), over 120 themes to spice up your morning, and an auto-update tool so that makes it easy to keep up with the latest updates from the community.

Python library for interacting with various VCS systems

ROS communications-related packages, including core client libraries (roscpp, rospy, roslisp) and graph introspection tools (rostopic, rosnode, rosservice, rosparam).

EusLisp is an integrated programming system for the research on intelligent robots based on Common Lisp and Object-Oriented programming

Informative git prompt for zsh

catkin env hooks providing bash completion and setting ROS_WORKSPACE in devel space

PR2-specific components that are used in bringing up a robot.

JSK model utilities

No description.

JSK Lab OpenNI ROS packages

No description.

No description.

JSK ros packages for smartphones

jsk control ros packages

JSK planning packages

script to create live cd/usb

JSK euslisp packages

JSK demo programs

Tutorials for rtmros packages

PR2 euslisp packages

Commonly used messages in ROS. Includes messages for actions (actionlib_msgs), diagnostics (diagnostic_msgs), geometric primitives (geometry_msgs), robot navigation (nav_msgs), and common sensors (sensor_msgs), such as laser range finders, cameras, point clouds.

This repo maintains a lists of repositories for each ROS distribution

The standard snippets repository for neosnippet

Numpy main repository

No description.

No description.

Externalize git-ignored files and directories to a synced, identity-derived store, kept out of git.

agent multiplexer that lives in your terminal.

A lightweight alternative to Clawdbot / OpenClaw that runs in containers for security. Connects to WhatsApp, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

No description.

Apply black reformatting to Python files only in regions changed since a given commit. For a practical usage example, see the blog post at https://dev.to/akaihola/improving-python-code-incrementally-3f7a

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

A flexible, high-performance 3D simulator for Embodied AI research.

Minimal examples of data structures and algorithms in Python

ROS integration for Franka Emika research robots

Reinforcement Learning in PyTorch

A large-scale benchmark and learning environment.

"DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion" code repository

This is an implementation sketch of the KinectFusion system described by Newcombe et al.

An object-oriented GUI library for pyglet.

No description.

Build wheels for wkentaro/octomap-python.

Pytorch implementation of "A simple neural network module for relational reasoning" (Relational Networks)

Code for the paper "Neural 3D Mesh Renderer" (CVPR 2018) by H. Kato, Y. Ushiku, and T. Harada.

ROS C++ message definition and serialization generators

Standalone Python library for generating ROS message and service data structures for various languages

Bundle python requirements in a catkin package via virtualenv

The uncompromising Python code formatter

awesome-semantic-segmentation

Maintains a bond (i.e. heart beat ) between ROS nodes and provides feedback when the bond is broken

Common code for working with audio in ROS

No description.

Easy continuous integration repository for ROS repositories