News for hackers. Stuff that matters.

A comment on Show HN: Convect – Instant Serverless Deployment of ML Models. Parent comment

Re:Show HN: Convect – Instant Serverless Deployment of ML Mo... by sameerank on Thursday May 27, 2021 @05:58PM (#27309084)
At the moment, Convect only deploys scikit-learn models, but I am planning to support inference with PyTorch and other ML frameworks. Not planning to run on GPUs, as there are other products that already help with this, unless I see interest in this from my users. Convect would support concurrency according to AWS Lambda's quota, which is in the hundreds of thousands.
[ Parent | on HN ]
Re:Show HN: Convect – Instant Serverless Deployment of ML Mo... by mistrial9 on Thursday May 27, 2021 @10:49PM (#27311216)
before the "boo birds" show up, I want to support this move as practical and useful. Real graduate projects using Scikit-Learn plus domain knowledge (gasp) make powerful results regularly. (I have no prior connection to this product)
[ Parent | on HN ]
Re:Show HN: Convect – Instant Serverless Deployment of ML Mo... by sameerank on Friday May 28, 2021 @02:56PM (#27319175)
Yup, this was my thinking too. :)

The variety of data problems you can work on with good old logistic regression (or the other models in scikit-learn) is really quite vast and seemed like a reasonable place to start.

[ Parent | on HN ]