class arpes.deep_learning.transforms.ComposeBoth(transforms: List[Any])[source]

Like torchvision.transforms.Compose but this operates on data & target in each transform.

__init__(transforms: List[Any]) None


__call__(x, y)

If this transform has separate data and target functions, apply separately.

__delattr__(name, /)

Implement delattr(self, name).


Default dir() implementation.


Return self==value.

__format__(format_spec, /)

Default object formatter.

__ge__(value, /)

Return self>=value.

__getattribute__(name, /)

Return getattr(self, name).

__gt__(value, /)

Return self>value.



This method is called when a class is subclassed.

__le__(value, /)

Return self<=value.

__lt__(value, /)

Return self<value.

__ne__(value, /)

Return self!=value.



Replace missing transforms with identities.


Helper for pickle.

__reduce_ex__(protocol, /)

Helper for pickle.


Show both of the constitutent parts of this transform.

__setattr__(name, value, /)

Implement setattr(self, name, value).


Size of object in memory, in bytes.


Return str(self).


Abstract classes can override this to customize issubclass().


Pull the target back in the transform stack as far as possible.










list of weak references to the object (if defined)