Thread by @fchollet

Built-in losses and metrics in Keras follow the signature `loss(y_true, y_pred, sample_weight=None)`. If you have exotic losses or metrics, a simple way to add them w/o having to implement your own training loop from scratch is to define them in an "endpoint layer". Like this:

It feels a bit more like the "Estimator" training style.

Full Colab notebook: colab.research.google.com/drive/1zzLcJ2A…

This usage pattern enables you to use `fit`/etc with losses or metrics that have completely arbitrary signatures. Such endpoint layer may also have different behavior during training or inference.