Katsuya Hyodo's Projects
This is the pretraining code for PeCLR. An equivariant contrastive learning framework for 3D hand pose estimation. The paper is presented at ICCV 2021.
A simple face detect and alignment method, which is easy and stable.
PCL (Point Cloud Library) ROS interface stack
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
The Facial Landmark Preprocessing Toolkit provides efficient preprocessing of facial images and landmarks, supporting image processing, landmark normalization, and data saving for training and testing.
Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild
Sample projects to use MNN. PoseNet, SemanticSegmentation, etc.
Library for loading/unloading plugins in ROS packages during runtime
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
[ECCV 2022] The official repo for the paper "Poseur: Direct Human Pose Regression with Transformers".
ๅ้ฎใPython็ผ็จไธๅฎ่ทตใ่ฏพ็จ่ตๆ
Protocol Buffers - Google's data interchange format
Python library for GPGPU on Raspberry Pi
PyBindGen: a python bindings generator
Python tools for working with KITTI data.
A Python implementation of the bodypix model.
Provide Docker build sequences of PyTorch for various environments.
Cross-compilation of PyTorch armv7l (32bit) for RaspberryPi OS
Qemu kernel for emulating Rpi on QEMU
A cross-platform Qt IDE
GCC 8.1.0 for Raspberry Pi, enabled languages C and C++
OS image repository for RaspberryPi3.
Intel(R) RealSense(TM) ROS Wrapper for D400 series and SR300 Camera
RealSense execution environment built on a Docker container on Ubuntu 20.04. NIVIDA GPU and OpenGL capable. CUADA 11.4.
Package used to retrieve resources of different kinds, e.g. http://, file://, the ROS specific package://, etc.
Implementation of a road damage detector in Chainer