Katsuya Hyodo's Projects
URDF parser
Headers for URDF parsers
A ROS Driver for V4L USB Cameras
Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces. IJCV 2012
OpenCL implementation running on the VideoCore IV GPU of the Raspberry Pi models
A package to open video streams and publish them in ROS using the opencv videocapture mechanism
A Robust and Versatile Monocular Visual-Inertial State Estimator
The official repo for CVPR2021——ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search.
Let's train vision transformers (ViT) for cifar 10!
Tutorials related to using and extending RViz and interactive_markers.
Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos.
ONNX implementation of Whisper. PyTorch free.
Exports OpenAI Whisper speech recognition models to ONNX. Mainly intended for use with Echogarden.
ONNX and TensorRT implementation of Whisper
A repository that provides an environment for generating WASM binaries for onnxruntime-web and a demo environment for running the demo in a browser. Everything is done in Docker. This is a repository for reviewing the work steps required to convert ONNX to WASM and run it in a browser.
Configuration file to build the kernel to access the USB camera connected to the host PC using USBIP from inside the WSL2 Ubuntu 20.04/22.04.
XFeatをONNXに変換し特徴点マッチングを行うサンプル
A YAML parser and emitter in C++
Provides a conversion flow for YOLACT_Edge to models compatible with ONNX, TensorRT, OpenVINO and Myriad (OAK). My own implementation of post-processing allows for e2e inference. Support for Multi-Class NonMaximumSuppression, CombinedNonMaxSuppression.
Procedures and tools for semi-mechanically automatically generating YoloV2 original learning data from video.
Python scripts performing object detection using the YOLOv8 model in ONNX.
Implementation of YOLOv9 QAT optimized for deployment on TensorRT platforms.
An MIT rewrite of YOLOv9
YOLOX is a high-performance anchor-free YOLO. Exceeding yolov3~v5 with ONNX, TensorRT, ncnn, and Openvino supported.
ZED2 SDK Installed Containers
Library to help interface with the on-board hardware of the Pololu Zumo 32U4 robot.
Zumo with odo and 2D lidar for 2D SLAM on ROS