zoo.orca.learn package

Submodules

zoo.orca.learn.metrics module

class zoo.orca.learn.metrics.AUC(threshold_num=200)[source]

Bases: zoo.orca.learn.metrics.Metrics

Metric for binary(0/1) classification, support single label and multiple labels.

# Arguments threshold_num: The number of thresholds. The quality of approximation

may vary depending on threshold_num.
>>> meter = AUC(20)
get_metrics()[source]
class zoo.orca.learn.metrics.Accuracy(zero_based_label=True)[source]

Bases: zoo.orca.learn.metrics.Metrics

Measures top1 accuracy for multi-class classification or accuracy for binary classification.

# Arguments zero_based_label: Boolean. Whether target labels start from 0. Default is True.

If False, labels start from 1. Note that this only takes effect for multi-class classification. For binary classification, labels ought to be 0 or 1.
>>> acc = Accuracy()
get_metrics()[source]
class zoo.orca.learn.metrics.BinaryAccuracy[source]

Bases: zoo.orca.learn.metrics.Metrics

Measures top1 accuracy for binary classification with zero-based index.

>>> acc = BinaryAccuracy()
get_metrics()[source]
class zoo.orca.learn.metrics.CategoricalAccuracy[source]

Bases: zoo.orca.learn.metrics.Metrics

Measures top1 accuracy for multi-class classification when target is one-hot encoded.

>>> acc = CategoricalAccuracy()
get_metrics()[source]
class zoo.orca.learn.metrics.MAE[source]

Bases: zoo.orca.learn.metrics.Metrics

Metric for mean absoluate error, similar from MAE criterion

>>> mae = MAE()
get_metrics()[source]
class zoo.orca.learn.metrics.Metrics[source]

Bases: abc.ABC

static convert_metrics_list(metrics)[source]
get_metrics()[source]
class zoo.orca.learn.metrics.SparseCategoricalAccuracy[source]

Bases: zoo.orca.learn.metrics.Metrics

Measures top1 accuracy for multi-class classification with sparse target.

>>> acc = SparseCategoricalAccuracy()
get_metrics()[source]
class zoo.orca.learn.metrics.Top5Accuracy[source]

Bases: zoo.orca.learn.metrics.Metrics

Measures top5 accuracy for multi-class classification.

# Arguments zero_based_label: Boolean. Whether target labels start from 0. Default is True.

If False, labels start from 1.
>>> acc = Top5Accuracy()
get_metrics()[source]

zoo.orca.learn.trigger module

class zoo.orca.learn.trigger.EveryEpoch[source]

Bases: zoo.orca.learn.trigger.Trigger

A trigger specifies a timespot or several timespots during training, and a corresponding action will be taken when the timespot(s) is reached. EveryEpoch is a trigger that triggers an action when each epoch finishs. Could be used as trigger in setvalidation and setcheckpoint in Optimizer, and also in TrainSummary.set_summary_trigger.

>>> everyEpoch = EveryEpoch()
get_trigger()[source]
class zoo.orca.learn.trigger.SeveralIteration(interval)[source]

Bases: zoo.orca.learn.trigger.Trigger

A trigger specifies a timespot or several timespots during training, and a corresponding action will be taken when the timespot(s) is reached. SeveralIteration is a trigger that triggers an action every “n” iterations. Could be used as trigger in setvalidation and setcheckpoint in Optimizer, and also in TrainSummary.set_summary_trigger.

>>> serveralIteration = SeveralIteration(2)
get_trigger()[source]
class zoo.orca.learn.trigger.Trigger[source]

Bases: abc.ABC

static convert_trigger(trigger)[source]
get_trigger()[source]

Module contents