crested.tl.metrics.ZeroPenaltyMetric

Contents

crested.tl.metrics.ZeroPenaltyMetric#

class crested.tl.metrics.ZeroPenaltyMetric(name='zero_penalty_metric', **kwargs)#: Zero penalty metric.

Attributes table#

`dtype`
`variables`

Methods table#

`add_variable`(shape, initializer[, dtype, ...])
`add_weight`([shape, initializer, dtype, name])
`from_config`(config)
`get_config`()	Return the serializable config of the metric.
`reset_state`()	Reset the state of the metric.
`result`()	Calculate the result of the metric by averaging the zero penalty over num batches.
`stateless_reset_state`()
`stateless_result`(metric_variables)
`stateless_update_state`(metric_variables, ...)
`update_state`(y_true, y_pred[, sample_weight])	Update the state of the metric.

Attributes#

ZeroPenaltyMetric.dtype#

ZeroPenaltyMetric.variables#

Methods#

ZeroPenaltyMetric.add_variable(shape, initializer, dtype=None, aggregation='sum', name=None)#

ZeroPenaltyMetric.add_weight(shape=(), initializer=None, dtype=None, name=None)#

classmethod ZeroPenaltyMetric.from_config(config)#

ZeroPenaltyMetric.get_config()#: Return the serializable config of the metric.

ZeroPenaltyMetric.reset_state()#: Reset the state of the metric.

ZeroPenaltyMetric.result()#: Calculate the result of the metric by averaging the zero penalty over num batches.

ZeroPenaltyMetric.stateless_reset_state()#

ZeroPenaltyMetric.stateless_result(metric_variables)#

ZeroPenaltyMetric.stateless_update_state(metric_variables, *args, **kwargs)#

ZeroPenaltyMetric.update_state(y_true, y_pred, sample_weight=None)#: Update the state of the metric.