matchzoo.tasks package

Submodules

matchzoo.tasks.classification module

Classification task.

class matchzoo.tasks.classification.Classification(num_classes=2, **kwargs)

Bases: matchzoo.engine.base_task.BaseTask

Classification task.

Examples

>>> classification_task = Classification(num_classes=2)
>>> classification_task.metrics = ['precision']
>>> classification_task.num_classes
2
>>> classification_task.output_shape
(2,)
>>> classification_task.output_dtype
<class 'int'>
>>> print(classification_task)
Classification Task with 2 classes

classmethod list_available_losses()

Return type:list Returns:a list of available losses.

classmethod list_available_metrics()

Return type:list Returns:a list of available metrics.

num_classes

number of classes to classify.

Type:return Return type:int

output_dtype

target data type, expect int as output.

Type:return

output_shape

output shape of a single sample of the task.

Type:return Return type:tuple

matchzoo.tasks.ranking module

Ranking task.

class matchzoo.tasks.ranking.Ranking(loss=None, metrics=None)

Bases: matchzoo.engine.base_task.BaseTask

Ranking Task.

Examples

>>> ranking_task = Ranking()
>>> ranking_task.metrics = ['map', 'ndcg']
>>> ranking_task.output_shape
(1,)
>>> ranking_task.output_dtype
<class 'float'>
>>> print(ranking_task)
Ranking Task

classmethod list_available_losses()

Return type:list Returns:a list of available losses.

classmethod list_available_metrics()

Return type:list Returns:a list of available metrics.

output_dtype

target data type, expect float as output.

Type:return

output_shape

output shape of a single sample of the task.

Type:return Return type:tuple

Module contents