Name: Satoshi Gachi Fujimoto
Type: User
Company: Knowledge Communication Co.,Ltd.
Bio: co-founder #KumaMCN / KnowComInc R&D / #Azure #HoloLens #MRPP / #AWS #ML / #CV #SLAM #Python / #WHILL #自動運転 / #メタバース #XR / #Databricks / #くまもとDX / 高専卒
Twitter: sotongshi
Location: Kumamoto, JAPAN
Blog: https://www.gachimoto.com/
Satoshi Gachi Fujimoto's Projects
WHILL Model CR SDK for Arduino
Protocol Specification for WHILL Model CR
Official tensorflow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations”
The repository for this book is published by Packt
Windows Machine Learning
Samples for Windows Remote Arduino
API samples for the Universal Windows Platform.
A client library that wraps the Windows Device Portal REST APIs.
This Repository is WindowsML demo(ObjectDetection) with Unity in HoloLens
This Repository is WindowsML demo in HoloLens
サンワダイレクトの360度Webカメラ(400-CAM084)のウィンドウをOpenCVで分割するプログラム
The tool that will help you install Windows ARM64 with ease!
A Hololens application, inspired by MapzenGo, to render 3D worlds as hologram.
Primary repository for the x360ce library, front-end and tools.
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Flink and DataFlow
Unified All-in-one Monero miner
Monero CPU miner
An XR-Focused line renderer that mimics rendering with 3d capsules while only using two quads worth of geometry.
Instance segmentation for anime characters based on CondInst
Model to classify yoga pose type and estimate joint positions of a person from an image
This is a Yoga Pose Estimation App which can be able to detect the yoga pose in real time by using posenet and KNN Classifier. Here the dataset used is custom data set which consists of 3 videos for representing 3 different postures. It is deployed in heroku. One Thing to be noted i.e this will work correctly for all mobile and edge devices.
A simple, fully convolutional model for real-time instance segmentation.
The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
A Python wrapper on Darknet. Compatible with YOLO V3.
YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud (ECCV 2018)
YOLOPv2: Better, Faster, Stronger for Panoptic driving Perception
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)