If you deploy ML to production in your group/team/company – what does production mean for you?
Examples: - "We run a model once a week that predicts some stuff and stores it in a table, then the customer queries it" - "We create an inference endpoint on some cloud resource, which our product/users use to predict poses in videos" - "I wish I knew, we're still figuring it out" - "We deploy a model as part of a larger pipeline in a system of microservices (and other buzzwords)"
Also, if you are in an extra-sharing mood – in your version of production, were there any counter-intuitive things you learned when you first set up the pipeline?
Cheers! Enjoy the picture Dall-E2 made for you of a cat asking for upvotes in return. https://labs.openai.com/s/2enTplV9c9OxU7lyqhyIjXlN