Liangfu Chen

End to end Tensor IR/DSL stack for deploying deep learning workloads to hardwares

Reproduction of MobileNetV2 using MXNet

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

An Implementation of the Driving Scene Perception Network (DSPNet)

standalone Brain Extraction Tool (bet2), released by

Stereo Vision -- attempt to build 3D model from multiple view image sets

A light-weight deep learning framework implemented in C++.

Lagacy code that implemented PWP (Pixel-Wise Posterior) algorithm

Multiple View Geometry

Python port of http://www.ics.forth.gr/~lourakis/sba

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

No description.

A schedule language for large model training

Linux kernel module for contiguous memory allocation

A Qt based logic analyzer, oscilloscope and MSO GUI from sigrok.

No description.

Tune BERT model for Tesla T4

A vector processor implemented in Chisel

Mathematical Functions in Verilog

No description.

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

Agent mode for gptel

A simple LLM client for Emacs

JIT compiler and runtime for a toy language, using Cranelift

Linux development repository for socfpga

An auto-scaling cluster of build agents running in your own AWS VPC

MacOS Demo for Claude Computer Use

No description.

Transformer related optimization, including BERT, GPT

JupyterLite demo deployed to GitHub Pages 🚀

Autogluon-cloud aims to provide user tools to train, fine-tune and deploy AutoGluon backed models on the cloud. With just a few lines of codes, users could train a model and perform inference on the cloud without worrying about MLOps details such as resource management

AutoGluon: AutoML for Image, Text, and Tabular Data

No description.

Example notebooks for working with SageMaker Studio Lab. Sign up for an account at the link below!

Convert scikit-learn models and pipelines to ONNX

Demo applications showcasing DJL

AutoGluon Benchmarking Repository

Hummingbird compiles trained ML models into tensor computation for faster inference.

A Python Interpreter written in Rust

Automatically generates Rust FFI bindings to C (and some C++) libraries.

PicoRV32 - A Size-Optimized RISC-V CPU

Slice:Drop is a web-based, interactive viewer for medical imaging data.

No description.

No description.

The AWS Cloud Development Kit is a framework for defining cloud infrastructure in code

Neo-AI-DLR is a common runtime for machine learning models compiled by AWS SageMaker Neo, TVM, or TreeLite.

No description.

Open source text annotation tool for machine learning practitioner.

repo for tvm

Spot Tagging Bot for Digital Assets

No description.

No description.

NLP made easy

Simple RISC-V 3-stage Pipeline in Chisel

A repository to cache VTA bistreams

Portable version of the OpenBSD maintained mg, micro emacs clone

Dive into Deep Learning Compiler

a list of hello world demos

Rocket Chip Generator

No description.

Common RTL blocks used in SiFive's projects

A list of hardware designs written in Chisel3

A Giter8 Template for Chisel Projects

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Implementation of a subset of CBP of h.264 encoder

A self-contained version of the tutorial which can be easily cloned and viewed by others.

A Contour Tree library

Android application to store data from RFduino

User space mappable dma buffer device driver for Linux.

A fork from http://git.edi.lv/rihards.novickis/FPSoC_Linux_drivers

Examples using the Cyclone V SoC chip

Angstrom development environment setup using Android repo tool

Gumstix overo board support (unofficial community BSP)

sparse mlp in mxnet

FPGA Design Suite based on C to Verilog design flow.

The Augmented Block Cimmino Distributed Solver

No description.

RFC for common in-memory tensor structure and operator interface for deep learning system

Bring deep learning to bare metal

Liangfu Chen's Homepage on Github

converted mobilenet models for mxnet

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK and PyTorch.

Library targeting Intel Architecture for small, dense or sparse matrix multiplications, and small convolutions.

Deep neural network framework for multiple GPUs

Caffe fork that supports Fast R-CNN

An extremely light weight tiny-YOLO inference engine targeted towards OpenCL hardware.

Implementation of the Zhang-Suen thinning algorithm using OpenCV

PyQt4 bindings to libqxt QxtGlobalShortcut

The main repository containing Stunt Rally sources and game data. A 3D racing game based on VDrift and OGRE with track editor.

README and scripts for the Cityscapes Dataset

MXNet port of SSD: Single Shot MultiBox Object Detector. Reimplementation of https://github.com/weiliu89/caffe/tree/ssd

Implementation of the SYCL specification.

Source code for the LabelMe annotation tool.

A 2d/3d convolution implementation using PyOpenCL

No description.

Faster R-CNN, an MXNet implementation with distributed implementation and data parallelization.

Yocto layer for InVehicle Infotainment software

A logging library based on the miniglog library found in ceres-solver @ https://code.google.com/p/ceres-solver/

A large scale non-linear optimization library

No description.

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

Pangolin is a lightweight portable rapid development library for managing OpenGL display / interaction and abstracting video input.

LSD-SLAM

g2o: A General Framework for Graph Optimization

Matrix Shadow:Lightweight CPU/GPU Matrix and Tensor Template Library in C++/CUDA for (Deep) Machine Learning

A common bricks library for building scalable and portable distributed machine learning.

dcm2nii DICOM to NIfTI converter

header only deep learning library in C++11/TBB

a software library containing BLAS functions written in OpenCL

a software library containing FFT functions written in OpenCL

A markdown parser for docutils

Series of letters to my daughter, which she would read some day.

C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library

configuration files for create a developing environment in Linux (Debian Distribution)

The emacs major mode for editing files in the YAML data serialization format.

Caffe: a fast open framework for deep learning.

No description.

a flask based wiki, using markdown files as backend. completely file based!

Deep Learning and Unsupervised Feature Learning Tutorial Solutions

Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.

a fork of "Online Template Learning"(OTL) library from https://bitbucket.org/haroldsoh/otl

No description.

No description.

My master thesis - final submit revision

Configure files for amazon ec2

No description.

Neurosynth viewer

Edit and visualize numeric charts, save as XML (academic project)

Automatically exported from code.google.com/p/eeglab

A Shadowsocks client for Android

The set of scripts that preprocess and insert MRI data into the database.

Atamai Image Registration and Segmentation

Automatically exported from code.google.com/p/achartengine

No description.

A fast tunnel proxy that helps you bypass firewalls

An Objective-C category that adds Android-style toast notifications to iOS.

Cross Platform C++ Threading and Networking Library

Cross-platform, Serial Port library written in C++

A bunch of plugins for the pelican blog engine.

Better Gantt Chart for Redmine

GNU Scientific Library with CMake build support

A set of classes for using DICOM in VTK.

A Tutorial for the Blog Post - Your First iOS App: 100% Programmatically

My personal code

Volume Rendering via VTK

Qt-based Brain Browser for interactive neuro imaging

No description.

Cascade Object Detection with Deformable Part Models – Add-on package for voc-release4.01

web.py is a web framework for python that is as simple as it is powerful.

vatic is an online, interactive video annotation tool for computer vision research that crowdsources work to Amazon's Mechanical Turk. Our tool makes it easy to build massive, affordable video data sets. Written in Python + C + Javascript, vatic is free and open-source software.

A project for porting and optimizing OpenCV for Google's Android OS