When talking to people who haven’t deployed ML models, I keep hearing a lot of misperceptions about ML models in production. Here are a few of them.
— Chip Huyen (@chipro) September 29, 2020
(1/6)
When talking to people who haven’t deployed ML models, I keep hearing a lot of misperceptions about ML models in production. Here are a few of them.
— Chip Huyen (@chipro) September 29, 2020
(1/6)
2. You only have a few ML models in production
— Chip Huyen (@chipro) September 29, 2020
Booking, eBay have 100s models in prod. Google has 10000s. An app has multiple features, each might have one or multiple models for different data slices.
You can also serve combos of several models outputs like an ensemble.
(3/6)
Deploying ML systems isn't just about getting ML systems to the end-users.
— Chip Huyen (@chipro) September 29, 2020
It's about building an infrastructure so the team can be quickly alerted when something goes wrong, figure out what went wrong, test in production, roll-out/rollback updates.
It's fun!
(6/6)