MLServer custom example missing standarization during inference

[smolendawid]

https://github.com/SeldonIO/MLServer/blob/master/docs/examples/custom/README.md

In the above example ^

I see that in the training phase the data in standardized (lambda function) and this doesn't happen in the inference, so the model would not work @adriangonz is that right?

[adriangonz]

That's a great point @smolendawid .

The example mainly showcases how you can build and deploy a custom runtime in MLServer. Therefore, it doesn't focus too much on the data science aspects or the correctness of the model.

Having said that, it would be cool to showcase how you can also have extra custom steps, like standarisation, as part of inference within your custom runtime.

@smolendawid would you be open to submitting a PR for this one?