Deploying ML/Deep Learning Models to Production
What platform do you guys use to deploy your Machine Learning/Deep Learning models to production?
Do you guys prefer building a custom solution (using flask/Docker) or using managed services like Azure, Algorithmia, etc? and Why?
I have never deployed models before so looking at pros/cons of each approach.
10 comments
[ 3.5 ms ] story [ 43.2 ms ] threadIf you use something like flask/Docker you are totally owning the entire pipeline and that might be a good/bad thing. By own, I mean hosting it yourself. Do you really want to own the pipeline, are you getting anything out of it, is this a competitive advantage to you some how? If not, you probably want to just off-load it to something else. Then, someone else can worry about all the production issues, and you can focus on what you're good at.
My understanding is that:
- data scientists create the model
- data engineers do the data wrangling and data warehousing
- devops responsible for more software engineering oriented projects and miss (?) some of the skills that would be required for ML/DL deployment (and debugging).
Am I missing something here or is there a gap?
Offtopic (sorry for hijacking): if anyone has experience in deploying ML/DL projects (freelancer), shoot me an email.