News for hackers. Stuff that matters.

A comment on Deploying ML/Deep Learning Models to Production.

Re:Deploying ML/Deep Learning Models to Production by lawlorino on Monday January 28, 2019 @06:04PM (#19021956)
It depends on your use case and the type of model e.g. is it from TensorFlow or scikit-learn or just a simple lookup table. Could you expand a little? Like someone else has said already, it also depends on how comfortable you are or how necessary it is to own the whole pipeline.
[ Parent | on HN ]
Re:Deploying ML/Deep Learning Models to Production by prasann16 on Monday January 28, 2019 @06:23PM (#19022103)
It's not necessary for me to own the pipeline. I am just looking for a scalable service where I can upload my model and it will provide me with API for inference which I can use on my website. Have you used any managed services like Algorithmia or Microsoft Azure ML? Do you know any other services I can look into?
[ Parent | on HN ]