How-to guide to cover multi-output models and their evaluation

[vfdev-5]

The idea is to show how to tackle a use-case like:

x, y1, y2 = batch
y_pred1, y_pred2, aux = model(x)

and where we would like to compute metrics between y_pred1 vs y1 and y_pred2 vs y2.

• Show that we can create custom evaluator that returns a dict
• We attach metric and specify output_transform for each metric

Context: discussed on discord, "questions" channel, multi-output thread.