Muhyun Kim Claim this profile

Image Captioning Project of Udacity Computer Vision Nanodegree

Lab materials of Deep Learning on AWS Workshop

AWS re:Invent 2017 MCL310 - Building Deep Learning Applications with Apache MXNet and Gluon

AWS DeepRacer Tools - Unofficial

EN2KR on D2L - English-Korean paragraph by paragraph

This shows how to visualize the stack ensemble model trained by AutoGluon.

OTEL traces reveal how AI agents reason and plan — with Strands Agent SDK and Claude

This is a Jupyter notebook based viewer of AutoGluon training job on SageMaker.

Udacity's Deep Reinforcement Learning Nanodegree Project - Collaboration and Competition using MADDPG

Video streaming server with detected labels displayed using Amazon Rekognition

Example notebooks that show how to apply machine learning, deep learning and reinforcement learning in Amazon SageMaker

No description.

AWS re:Invent 2018 AIM350

A benchmark and generation framework for malicious agent skills.

An independent Python feature port of Claude Code, entirely rewritting from scratch using oh-my-codex. Educational Purpose only.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

The OpenClaw Marketplace — buy and sell trained AI claw configurations

No description.

ACL2023 - AlignScore, a metric for factual consistency evaluation.

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

No description.

Self Driving Car Nanodegree Project 3 - Behavioral Cloning

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

DeepRacer workshop content

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

No description.

Python package built to ease deep learning on graph, on top of existing DL frameworks.

Korean GPT-2 pretrained cased (KoGPT2)

No description.

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

explainerdashboard is a python package for generating analytical dashboards that explain the inner workings of so-called "blackbox" machine learning models.

Deep Learning Examples

AutoGluon: AutoML for Text, Image, and Tabular Data

Materials for DGL Instructor-led training at GTC 2019

Streamlit — The fastest way to build data apps in Python

No description.

Tutorial for pretraining Korean GPT-2 model

working example of a contextual multi-armed bandit

Pedestrian monitor that provides visual feedback to help ensure proper social distancing guidelines are being observed

Materials for DGL hands-on tutorial in WWW 2020

High-performance implementation of SLIM-based approaches for Top-N recommendation

Hands-on Tutorial on Automated Deep Learning

The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate

example of distributed multi-node/multi-device training of MXNet model

GPU IO optimizations for Deep Learning - Illustrated with Caltech 256 dataset on SageMaker. Here, we will be focusing on optimizations for improving I/O for GPU performance tuning. You can typically obtain 10X improvements in overall GPU training performance by just optimizing IO processing routines

Docker container for running PyTorch scripts to train and host PyTorch models on SageMaker

No description.

Learn OpenCV : C++ and Python Examples

Implements the unsupervised pre-training of convolutional neural networks

Deep Clustering for Unsupervised Learning of Visual Features

Serve machine learning models within a 🐳 Docker container using 🧠 Amazon SageMaker.

딥러닝을 활용한 한글문장 OCR 연구

Model Serving on PyTorch

Neural model for converting Image-to-Markup (by Yuntian Deng github.com/da03)

This project builds a very simple implementation of SageMaker Training's internal IO subsystem that is able to pipe channel data files to an algorithm. It is meant to be used as a local-testing tool in order to test a PIPE mode algorithm locally before attempting to run it for real with SageMaker Training.

Code for Defending Against Neural Fake News, https://rowanzellers.com/grover/

Background Matting: The World is Your Green Screen

SimCLR - A Simple Framework for Contrastive Learning of Visual Representations

AI and Machine Learning with Kubeflow, Amazon EKS, and SageMaker

POC In a box guide material for Amazon Personalize

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

Rapid satellite imagery object detection

You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery

Dive into Deep Learning, Berkeley STAT 157 (Spring 2019) textbook. With code, math, and discussions.

Korean translation in progress of https://github.com/aws-samples/aws-deepracer-workshops/tree/master/Workshops/2019-AWSSummits-AWSDeepRacerService/Lab1

Udacity's Deep Reinforcement Learning Nanodegree Project - Continuous Control using DDPG

Udacity's Deep Reinforcement Learning Nanodegree Project - Navigation

No description.

Facial Keypoint Detection Project of Udacity Computer Vision Nanodegree

Amazon SageMaker tutorial - Bring You Own Script

Udacity's Self Driving Car Nanodegree Term1, Project 4 - Advanced Lane Finding

Udacity's Self Driving Car Nanodegree Term1, Project 5 - Vehicle Detection and Tracking

Udacity Self Driving Car Nanodegree Term 1 - 2nd Project

Caffe: a fast open framework for deep learning.

Self-Driving Car Engineer Nanodegree Term 1 - Project 1 Finding Lane Lines on the Road

No description.

Assignments of Udacity Deep Learning Foundataion Nanodegree

labs to learn how to implement end-to-end deep learning environment on aws with famous sample models