Re:Kubeflow – Machine Learning Toolkit for Kubernetes
by mountainerd on Thursday December 07, 2017 @05:11PM
(#15874848)
Pretty interesting. I'm guessing this is something that Google uses internally for their Kubernetes workflows.
[ Parent
| on HN ]
Re:Kubeflow – Machine Learning Toolkit for Kubernetes
by TheIronYuppie on Thursday December 07, 2017 @07:58PM
(#15875845)
Its very close to how we think about ML internally, but not what we use. Your best bet to read that is look at the TFX paper[1] which describes our internal thoughts in great detail. (Though Kubeflow is not designed to be an externalization of TFX, we're very much working in collaboration with that team)
[1] http://www.kdd.org/kdd2017/papers/view/tfx-a-tensorflow-base...
Disclosure: I work at Google on Kubeflow
Re:Kubeflow – Machine Learning Toolkit for Kubernetes
by quadrature on Thursday December 07, 2017 @09:26PM
(#15876231)
Does google intend on open sourcing TFX ?. I only ask because we're building a lot of the same infrastructure.
Re:Kubeflow – Machine Learning Toolkit for Kubernetes
by TheIronYuppie on Thursday December 07, 2017 @09:57PM
(#15876343)
We're absolutely looking at it! Please join our discussion, we'd love to talk about what you're building and if we can help and/or what you'd like us to OSS.
Disclosure: I work at Google on Kubeflow
Re:Kubeflow – Machine Learning Toolkit for Kubernetes
by quadrature on Thursday December 07, 2017 @10:57PM
(#15876560)
Sure, is there an issue/doc/pr to comment on ?.
Re:Kubeflow – Machine Learning Toolkit for Kubernetes
by TheIronYuppie on Friday December 08, 2017 @12:23PM
(#15880258)
No, would you mind adding one?
Re:Kubeflow – Machine Learning Toolkit for Kubernetes
by nikolay on Thursday December 07, 2017 @05:34PM
(#15875017)
I am at KubeCon 2017 in Austin, TX and, yeah, based on the presentation, it looks like an internal tool they just opened to the public with some bold goals.
Re:Kubeflow – Machine Learning Toolkit for Kubernetes
by TheIronYuppie on Thursday December 07, 2017 @08:00PM
(#15875862)
Hi! It was actually designed from the start to be an extension of GitHub.com/tensor flow/k8s and then it took on larger goals = Making an entire ML stack (of any ML framework) easy to use, portable and composable on k8s.
Disclosure: I work at Google on Kubeflow