Тёмный

MLOps for non-DevOps folks, a.k.a. “I have a model, now what?! - Hannes Hapke - ML4ALL 2019 

ML4ALL
Подписаться 11 тыс.
Просмотров 13 тыс.
50% 1

Опубликовано:

 

28 окт 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 7   
@engkamyabi
@engkamyabi 4 года назад
Thanks for the talk. Just a few notes. TF.js can be potentially used in cases with no network by building browser-based desktop apps using frameworks like Electron. Also while cloud options can be more pricy in terms of infrastucture cost but they are usually more managed and requiring less maintenance cost/overhead.
@ana-mariatofan4408
@ana-mariatofan4408 Год назад
Why Flask and not FastAPI? FastAPI is more suited to POST calls for example (say you want to give an observation as input and get back a prediction for it) because it also provides an input schema validation mechanism with pydantic. Maybe I am missing something but I am curious regarding this choice.
@yaseral-hamzi7687
@yaseral-hamzi7687 4 года назад
Thanks for this interesting topic. Could you please mention some articles for reference.
@ashhere31
@ashhere31 5 лет назад
Nicely explained many complex stuff. well done
@AntonioDellElceUK
@AntonioDellElceUK 3 года назад
Flask is an API framework, right?
@nagarajannethi
@nagarajannethi 3 года назад
Ya
@amjds1341
@amjds1341 3 года назад
Who are those people who dislikes such informative videos?
Далее
An introduction to MLOps on Google Cloud
23:56
Просмотров 43 тыс.
Introduction to MLOps
45:39
Просмотров 40 тыс.
How to deploy machine learning models into production
35:39
Webinar: MLOps automation with Git Based CI/CD for ML
57:52