crested.tl.metrics.SpearmanCorrelationPerClass

Contents

crested.tl.metrics.SpearmanCorrelationPerClass#

class crested.tl.metrics.SpearmanCorrelationPerClass(num_classes, name='multiclass_spearman_correlation', **kwargs)#: Spearman correlation metric for multiclass models.

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.
`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#

SpearmanCorrelationPerClass.dtype#

SpearmanCorrelationPerClass.variables#

Methods#

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

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

classmethod SpearmanCorrelationPerClass.from_config(config)#

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

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

SpearmanCorrelationPerClass.result()#: Calculate the result of the metric.

SpearmanCorrelationPerClass.stateless_reset_state()#

SpearmanCorrelationPerClass.stateless_result(metric_variables)#

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

SpearmanCorrelationPerClass.update_state(y_true, y_pred, sample_weight=None)#

Update the state of the metric.

Args:: y_true (tensor): Ground truth labels of shape (batch_size, num_classes). y_pred (tensor): Predicted outputs of shape (batch_size, num_classes).