matchzoo.tasks

Submodules

• matchzoo.tasks.classification
• matchzoo.tasks.ranking

Package Contents

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

Bases: matchzoo.engine.base_task.BaseTask

Classification task.

Examples

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

TYPE = classification

num_classes :int

number of classes to classify.

Type:return

output_shape :tuple

output shape of a single sample of the task.

Type:return

output_dtype

target data type, expect int as output.

Type:return

classmethod list_available_losses(cls)

Returns:a list of available losses.

classmethod list_available_metrics(cls)

Returns:a list of available metrics.

__str__(self)

Returns:Task name as string.

class matchzoo.tasks.Ranking

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

TYPE = ranking

output_shape :tuple

output shape of a single sample of the task.

Type:return

output_dtype

target data type, expect float as output.

Type:return

classmethod list_available_losses(cls)

Returns:a list of available losses.

classmethod list_available_metrics(cls)

Returns:a list of available metrics.

__str__(self)

Returns:Task name as string.