Warnings about missing 'weighted_metrics' in tensorflow evaluate()

when training a network as in the example, a lot of warnings are thrown:

WARNING:tensorflow:`evaluate()` received a value for `sample_weight`, but `weighted_metrics` were not provided.  Did you mean to pass metrics to `weighted_metrics` in `compile()`?  If this is intentional you can pass `weighted_metrics=[]` to `compile()` in order to silence this warning.