Shunta Saito Claim this profile

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

LLM inference in C/C++

Run LLMs with MLX

DeepPose implementation in Chainer

Object Detection with Faster R-CNN in Chainer

Semantic Segmentation for Aerial / Satellite Images with Convolutional Neural Networks including an unofficial implementation of Volodymyr Mnih's methods

Download Caltech Pedestrian Dataset and convert them for Python users without using MATLAB

Various CNN models for CIFAR10 with Chainer

A Python wrapper of NVIDIA Video Loader (NVVL) with CuPy for fast video loading with Python

CAUTION: This is not maintained anymore. Visit https://github.com/chainer-community/chainer-colab-notebook/

PSPNet in Chainer

Chainer folk of Fast R-CNN (Object Detection Method)

Siamese Network implementation using Chainer

Reproduction work of "Neural Relational Inference for Interacting Systems" in Chainer

No description.

Semantic Segmentation for Aerial Imagery using Convolutional Neural Network

Support Vector Machine (SVM) implementation using Chainer

Jupyter notebooks for Chainer hands-on

Run a static part of the computational graph written in Chainer with Tensorflow

SOINN implementation with C++

Convolution filter visualization tool for VGG-net using Chainer

A Python wrapper of OpenCV implementation of BING Objectness

Python wrapper of selective search like algorithm in dlib

[THIS PROJECT HAS BEEN DEPRECATED. BECAUSE NOW CUDA SUPPORTS libc++] Caffe (Convolutional Architecture for Fast Feature Embedding) related formulae for OSX 10.9

No description.

Burn captions (.srt) into videos

Command Line Tools for Chainer

Reinforcement Learning - TicTacToe

An example of generating text with PLaMo-13b using MLX

No description.

Use 2 Kinects with OpenNI, Capture IR images from both kinects.

No description.

No description.

This is fork of https://bitbucket.org/aquariusjay/deeplab-public-ver2

Deep Residual Network implementation by Chainer

No description.

No description.

No description.

No description.

Mixture Density Network with Chainer

Examples in the MLX framework

No description.

Pre-built binaries of OpenMPI w/ CUDA & verbs options

NeuralNetwork sample (back propagation)

Use CuPy ndarray with cuDF/cuML functions

OpenSoundControl Library Test on Qt 4.8.0

Save Color, Depth, IR images from Kinect for Windows V2 into different movie files

ChainerRL is a deep reinforcement learning library built on top of Chainer.

Caffe: a fast framework for deep learning. For the most recent version checkout the dev branch. For the latest stable release checkout the master branch.

No description.

Easy benchmarking of all publicly accessible implementations of convnets

Densely Connected Convolutional Network implementation by Chainer

No description.

PCLのOpenNIGrabberを使ってKinectからテクスチャ付き点群データを取得して表示するサンプル

No description.

No description.

OpenNI2 & NiTE2 with openFrameworks (OSX Mountain Lion)

Advanced mathematical types and functions for Swift

Swift API for MLX

The most powerful local music generation model that outperforms most commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.

Inochi2D SDK - Bring your characters to life

2.24x decode TPS increase On Qwen 3.6 27B @ temp 0.6 | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

[SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

"Single-image Layer Decomposition for Anime Characters" (SIGGRAPH 2026, Conditionally Accepted)

MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

No description.

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

OpenVINO Intel NPU Compiler

MLX-VLM is a package for running Vision LLMs locally on your Mac using MLX.

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

OpenVINO Tokenizers extension

A high-throughput and memory-efficient inference and serving engine for LLMs

A lightweight yet powerful audio-to-MIDI converter with pitch bend detection

No description.

GGUF Q4 (dequantize) -> PyTorch fp16 -> OpenVINO int4

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

🙌 OpenHands: Code Less, Make More

No description.

An Open-Source Asynchronous Coding Agent

広聴AI (デジタル民主主義2030ブロードリスニング)

Unsupervised text tokenizer for Neural Network-based text generation.

Lightweight coding agent that runs in your terminal

Suna - Open Source Generalist AI Agent

Preferred Generation Benchmark

Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)

Universal LLM Deployment Engine with ML Compilation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

High-performance In-browser LLM Inference Engine

No description.

Python tool for converting files and office documents to Markdown.

A simple UI / Web / Frontend for MLX mlx-lm using Streamlit.

Swift Package to implement a transformers-like API in Swift

No description.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

No description.

Demo of running NNs across different frameworks

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

S3 Filesystem

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Official repo for consistency models.

No description.

No description.

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

OpenMMLab Detection Toolbox and Benchmark

Object detection. EfficientDet-D5 level COCO AP in 20 epochs. SOTA single-stage detector on Waymo Open Dataset.

TFRecord Viewer for browsing contents of TFRecords with object detection/classification annotations.

IO library to access various filesystems with unified API

Repo for publishing code Samples and CLI samples for BatchAI service

Open Source Differentiable Computer Vision Library for PyTorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

TCP tunnel that works like VPN

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

No description.

The Material Darker theme for JupyterLab

JupyterLab computational environment.

Effective and Efficient Sports Play Retrieval with Deep Representation Learning

Object detection, 3D detection, and pose estimation using center point detection:

Datasets, Transforms and Models specific to Computer Vision

Code for Neural Motifs: Scene Graph Parsing with Global Context (CVPR 2018)

Pytorch reimplementation of LinkNet for Scene Graph Generation

ChainerCV: a Library for Computer Vision in Deep Learning

Tutorials for using ONNX

cuDF - GPU DataFrame Library

Caffe2 is a lightweight, modular, and scalable deep learning framework.

Chainer on Google Colaboratory

No description.

Add-on package for ONNX format support in Chainer

Squeeze-and-Excitation Networks

A domain specific language to express machine learning workloads.

A library that uses hardware acceleration to load sequences of video frames to facilitate machine learning training

No description.

MoCoGAN: Decomposing Motion and Content for Video Generation

ChainerUI: User Interface for Chainer

NumPy-like API accelerated with CUDA

No description.

scikit-learn: machine learning in Python

PRML algorithms implemented in Python

The Fastest DNN Running Framework on Web Browser

ONNX model format support for Apache MXNet

The implementation of Temporal Generative Adversarial Nets with Singular Value Clipping

Python bindings to the pointcloud library (pcl)

A python interface for libfreenect2 for python 2.7 and 3.x.

PARTY OR DIE

No description.

ChainerMN: Scalable distributed deep learning with Chainer

The official website of Chainer (chainer/chainer)

No description.

No description.

A flexible framework of neural networks

Docker - the open-source application container engine

Dash repo of user contributed docsets

keyboard controller firmware for Atmel AVR USB family

KinectSDK1.5のFaceTrackingLibを使うための基本的なコードを模索中

OpenNIを使ってKinectからDepth,RGBを取得し，OpenCVで表示する最小限のサンプル

ヒッピー部 Vol.3「Happy Map」で使用したシステムです。

Show point clouds captured by Kinect using OpenNI from PCL ( MacOSX Lion + Qt4.7 )

Ogre3DをMacOSX Lion + Qtで動かす．

cv modules for printeps

use caffe ( https://github.com/BVLC/caffe ) from python and update weights also from python

Open source drivers for the Kinect for Windows v2 device

cublasDgemm v.s. eigen3

No description.

ヒッピー部Vol.4『あたまのうしろ』で使用したシステムのコード

Show Wavefront OBJ file with PCLVisualizer