Azure ML Deploy Inference Endpoint

[@chayutkanthawong2301]

This very helpful. It's like I found your website(needle) from the sea

[@robkerrai]

Glad it was helpful!

[@toulasantha]

Thank you. Please do a video for batch and webapp endpoints too. Thanks

[@robkerrai]

Thanks for the suggestion!

[@narendraparmar1631]

Thanks Rob

[@robkerrai]

Your welcome!

[@mtagab007]

thank you, very helpful

[@robkerrai]

Glad it was helpful!

[@dorin.nicolae]

I am trying to follow with the example but what is the whole line when you want to split the data "X, y = df[['Pregnancies','PlasmaGlucose',...." Line 6 in the second code section, It is in the section of training the model, here: kzbin.info/www/bejne/jnaWgYqOd5dpZrc

[@chacemccallum983]

This video has been fantastic, but I have a possibly stupid question: When you ran the code, you automatically had a job created; what did you do to get that? When I run mine that does not happen.

[@robkerrai]

Not sure I understand. Which portion of the video are you referring to?

[@gcarboni1]

Thanks for this demo. It was very useful and clear. I think that the only bad point on azureml endpoint, is that you can add only one model on a single deployment, and it become very expensive in terms of money, because you need a single VM for each model. Do you know some alternatives on azureml? Thank again Gabriele

[@robkerrai]

The GUI-based tools are definitely geared around one model per endpoint. Multiple models are possible but require more configuration work. I can't paste URLs here, but if you search the learn site for "multiple local models deployment" it should turn up some doc pages how to get it working.

[@gcarboni1]

@@robkerraiI see a solution inside a container istance. But I'll search again. thank you.