본문 바로가기
Developing../MLOps:k8s

MLOps 학습기

by bents 2022. 7. 13.

구조
https://neptune.ai/blog/best-mlops-tools

1. 로깅
https://velog.io/@ifelifelse/Logging

Logging

이제부터는 노강의 온리pdf 자료로 정리한다. 강의영상 제공이 끝났기 때문... 모르는건 검색해보면서 정리한다. 그래도 복사 붙혀넣기는 아니고 타이핑으로 음미하면서 공부하겠습니다.네이버

velog.io

2. MLflow
https://velog.io/@ifelifelse/MLflow

MLflow

이번에도 마찬가지로 강의영상은 없이 강의자료를 통해 정리를 하려고 한다. 저번 Logging 강의자료에서 느꼈지만 강의자료만으로 인터넷 검색이 거의 불필요했다. 몹시 쉽게 잘 정리된 강의자료

velog.io


3. kubeflow / kfserve vs seldon
https://getindata.com/blog/machine-learning-model-serving-tools-comaprison-kserve-seldon-core-bentoml/

4. mlflow, kubeflow, seldon core
https://ubuntu.com/blog/mlops-pipeline-with-mlflow-seldon-core-and-kubeflow-pipelines

MLOps Pipeline with MLFlow, Seldon Core and Kubeflow | Ubuntu

MLOps pipelines are a set of steps that automate the process of creating and maintaining AI/ML models. In other words, Data Scientists create multiple notebooks while building their experiments, and naturally the next step is a transition from experiments

ubuntu.com


5. dvc + mlflow
https://databricks.com/kr/session_eu20/data-versioning-and-reproducible-ml-with-dvc-and-mlflow

Data Versioning and Reproducible ML with DVC and MLflow - Databricks

Machine Learning development involves comparing models and storing the artifacts they produced. We often compare several algorithms to select the most efficient ones. We assess different hyper-parameters to fine-tune the model. Git helps us store multiple

databricks.com


https://blog.alkisnar.io/2021/06/14/data-versioning/

Data Versioning – Alkisnar's Blog

Recently I was tasked to build a system that would automatically deploy pipelines using Kubeflow and Pachyderm. This system needed data versioning to make sure that results were reproducible in the future. Data versioning, or DVC can be summed up in these

blog.alkisnar.io


# 구축사례 / MLOps 분류가 4가지로 심플함
https://ambiata.com/blog/2020-12-07-mlops-tools/

MLOps: How to choose the best ML model tools | Blogs

MLOps is a rapidly growing field aimed at standardising and streamlining the lifecycle of ML models, from development and deployment through to ongoing maintenance. In this post we discuss some key considerations when selecting the right set of MLOps tools

ambiata.com



'Developing.. > MLOps:k8s' 카테고리의 다른 글

docker command  (0) 2022.07.14
cka 공부 자료  (0) 2022.07.07
kubeflow sdk  (0) 2022.07.02
[1] 나만의 MLOps - kubeflow  (0) 2022.06.16
[5] 컨테이너 인프라 환경 구축을 위한 쿠버네티스/도커  (0) 2022.06.15