BatchReduction

class hybrid_learning.concepts.train_eval.kpis.batch_kpis.BatchReduction(value)[source]

Bases: Enum

Aggregation types to reduce the 0th (meaning the batch) dimension of a tensor. The values are tuples of description and function.

Public Data Attributes:

mean

sum

Inherited from : py: class:Enum

Public Methods:

mean

sum

Special Methods:

__call__(batch_tensor)

Reduce the given tensor according to the chosen aggregation method.

__new__(value)

Inherited from : py: class:Enum

__repr__()

Return repr(self).

__str__()

Return str(self).

__dir__()

Returns all members and all public methods

__format__(format_spec)

Returns format using actual value type unless __str__ has been overridden.

__hash__()

Return hash(self).

__reduce_ex__(proto)

Helper for pickle.


__call__(batch_tensor)[source]

Reduce the given tensor according to the chosen aggregation method.

Parameters

batch_tensor (Tensor) –

Return type

Tensor

mean = ('Reduce by mean', <function BatchReduction.<lambda>>)
sum = ('Reduce by sum', <function BatchReduction.<lambda>>)