matchzoo.tasks package

Submodules

matchzoo.tasks.classification module

Classification task.

class matchzoo.tasks.classification.Classification(num_classes=2)

基类：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()

返回类型:list 返回:a list of available losses.

classmethod list_available_metrics()

返回类型:list 返回:a list of available metrics.

num_classes

return -- number of classes to classify.

返回类型:int

output_dtype

return -- target data type, expect int as output.

output_shape

return -- output shape of a single sample of the task.

返回类型:tuple

matchzoo.tasks.ranking module

Ranking task.

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

基类：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()

返回类型:list 返回:a list of available losses.

classmethod list_available_metrics()

返回类型:list 返回:a list of available metrics.

output_dtype

return -- target data type, expect float as output.

output_shape

return -- output shape of a single sample of the task.

返回类型:tuple

matchzoo.tasks.utils module

Task utilities.

matchzoo.tasks.utils.list_available_task_types()

Return a list of task type class objects.

返回类型:List[Type[BaseTask]]

Module contents