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
Code accompanying the book "Machine Learning for Hackers"
Fast multilayer perceptron neural network library for iOS and Mac OS X
Python implementation of ML-PnP
Implementation of the moving least squares algorithm for 3D deformation by Yuanchen Zhu and Steven Gortler of Harvard University
Official Tensorflow implementation of "M-LSD: Towards Light-weight and Real-time Line Segment Detection"
M-LSD line segment detection model for Unity Barracuda
OpenMMLab Image and Video Editing Toolbox
A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.
MNIST on Unity Barracuda
MNIST on Unity Barracuda (GPU version)
Deep Learning(PoseNet) Application in SLAM
We present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
Models and examples built with TensorFlow
A collection of pre-trained, state-of-the-art models in the ONNX format
Pre-trained and Reproduced Deep Learning Models (『飞桨』官方模型库,包含多种学术前沿和工业场景验证的深度学习模型)
Code repository for the book Modern Python Cookbook, published by Packt
Modern Robotics: Mechanics, Planning, and Control Code Library --- The primary purpose of the provided software is to be easy to read and educational, reinforcing the concepts in the book. The code is optimized neither for efficiency nor robustness.
A Trimap-Free Solution for Portrait Matting in Real Time
Modular-Programming-with-Python Code
WebRTC Native Client Momo
A one-stop repository for low-code easily-installable object detection pipelines.
Official PyTorch Implementation for "Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud", ICCVW 2019
単眼デプス推定で推定した相対距離をシンプルなキャリブレーションで絶対距離へ変換するプログラム
Unsupervised single image depth prediction with CNNs
Single Image Depth Estimation with Feature Pyramid Network
Unofficial implementation of Unsupervised Monocular Depth Estimation neural network MonoDepth in PyTorch