cmpark0126

pytorch-polynomial-lr-decay

Polynomial Learning Rate Decay Scheduler for PyTorch

CamelyonTask

pytorch-LARS

wicwiu-rust

A WICWIU implementation using rust

MIPS_32bits

Implements 32bits MIPS with verilog. (18.11.25 ~ 18.12.)

ml-serving-system-building

snip-public

SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY

trytune-py

Heterogeneous System ML Pipeline Scheduling Framework with Triton Inference Server as Backend

Awesome-System-for-Machine-Learning

A curated list of research in machine learning systems (MLSys). Paper notes are also provided.

billboard.js

:bar_chart: Re-usable, easy interface JavaScript chart library based on D3.js

client

Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.

cmpark0126.github.io

COMPILER_STUDY

Semester 2019-1, HGU, Compiler and Automata theory

Cortex-M_practice

CPPSTUDY

cs420

KAIST CS420: Compiler Design (2020 Spring)

DBTermProject

distributed_tensorflow_example

Fractal

helpdesk

image

Encoding and decoding images in Rust

infra-public

JAVA_STUDY

kaist-cp

kaist-cp.github.io

Software_Engineering

2019_1

Sudoku

tensorrt-rs

Rust library for running TensorRT accelerated deep learning models

torchgpipe

A GPipe implementation in PyTorch

WICWIU

WICWIU(What I can Create is What I Understand)는 한동대 딥러닝 연구실에서 국내 대학으로는 최초로 공개하는 딥러닝 오픈소스 프레임워크입니다. WICWIU는 모든 API가 C++로 제공되어 메모리 및 성능 최적화에 유리합니다. 또한, 응용시스템의 개발 외에도 프레임워크 자체를 특수한 환경에 맞도록 수정 및 확장이 가능합니다. WICWIU는 Apache2.0 라이선스를 적용해 연구 목적 및 상용 목적으로 제약 없이 활용 가능합니다.