tmeasures.pytorch.transformations package

Submodules

tmeasures.pytorch.transformations.affine module

Module contents

class tmeasures.pytorch.transformations.IdentityTransformation[source]

Bases: PyTorchTransformation

parameters() → Tensor[source]

Returns an iterator over module parameters.

This is typically passed to an optimizer.

Args:
recurse (bool): if True, then yields parameters of this module

and all submodules. Otherwise, yields only parameters that are direct members of this module.

Yields:

Parameter: module parameter

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for param in model.parameters():
>>>     print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)
training: bool
class tmeasures.pytorch.transformations.IdentityTransformationSet[source]

Bases: PyTorchTransformationSet

class tmeasures.pytorch.transformations.PyTorchTransformation[source]

Bases: Transformation, Module

abstract parameters() → Tensor[source]

Returns an iterator over module parameters.

This is typically passed to an optimizer.

Args:
recurse (bool): if True, then yields parameters of this module

and all submodules. Otherwise, yields only parameters that are direct members of this module.

Yields:

Parameter: module parameter

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for param in model.parameters():
>>>     print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)
training: bool
class tmeasures.pytorch.transformations.PyTorchTransformationSet(members)[source]

Bases: TransformationSet, Iterable[PyTorchTransformation]

parameter_range() → List[Tensor][source]