Skip to content
View wkentaro's full-sized avatar

Sponsors

@roboflow

Block or report wkentaro

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
wkentaro/README.md

I build tools for computer vision.

Computer vision

  • labelme ★16k+ - label images for segmentation, detection, and classification
  • imgviz ★264+ - visualize images and labels without OpenCV or matplotlib
  • octomap-python ★100+ - Python bindings for the OctoMap 3D mapping library
  • osam - run SAM1/2/3, EfficientSAM, YOLO-World, and other promptable vision models locally
  • sam3-onnx - ONNX export and inference for SAM3
  • yolo-world-onnx - ONNX models for YOLO-World open-vocabulary detection
  • labelme-satellite-image-demo - annotate satellite imagery with labelme and convert to GeoJSON for QGIS

CLIs & utilities

  • gdown ★5.3k+ - download Google Drive files that wget and curl choke on
  • imshow - display images from Python with a customizable viewer
  • moviepy-cli - edit videos from the command line via MoviePy
  • jqk - render JSON with jq patterns
  • git-hunk - non-interactive git hunk staging for AI agents
  • ihq (wip) - externalize git-ignored files to a synced, identity-derived store
  • acron (wip) - schedule unattended coding agents on your own server via cron

Past work

  • pytorch-fcn ★1.8k+ - Fully Convolutional Networks in PyTorch
  • pytorch-for-numpy-users ★705+ - PyTorch reference for NumPy users
  • morefusion ★238+ - 6D pose estimation from volumetric fusion (CVPR 2020)
  • fcn ★216+ - Fully Convolutional Networks in Chainer
  • video-cli ★136+ - command-line tools for quick video editing
  • gshell ★112+ - navigate Google Drive as you do on a shell
  • reorientbot ★58+ - learning object reorientation for posed placement (ICRA 2022)
  • safepicking ★56+ - safe object extraction via object-level mapping (ICRA 2022)

Popular repositories Loading

  1. labelme labelme Public

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

    Python 16k 3.7k

  2. gdown gdown Public

    Google Drive public file downloader when curl/wget fails.

    Python 5.3k 417

  3. pytorch-fcn pytorch-fcn Public archive

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

    Python 1.8k 471

  4. pytorch-for-numpy-users pytorch-for-numpy-users Public

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

    HTML 705 87

  5. imgviz imgviz Public

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

    Python 264 30

  6. morefusion morefusion Public archive

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

    Python 238 46