BatchWindowOp

class hybrid_learning.datasets.transforms.encoder.BatchWindowOp

Bases: ABC, Module

Base class for encoder that use windowing operations. E.g. convolutions or pooling.

Public Data Attributes:

AREA_DIMS	Indices of axes in which the image area is defined.
kernel_size	The kernel size of the window.
settings	Settings to reproduce the instance.

Inherited from : py: class:Module

dump_patches	This allows better BC support for load_state_dict().
T_destination	alias of TypeVar('T_destination', bound=Mapping[str, Tensor])

Public Methods:

forward(masks)	Wrapper for the convolutional operation on batch of masks.
conv_op(masks)	The convolutional operation on the masks (without validation).

Inherited from : py: class:Module

forward(masks)	Wrapper for the convolutional operation on batch of masks.
register_buffer(name, tensor[, persistent])	Adds a buffer to the module.
register_parameter(name, param)	Adds a parameter to the module.
add_module(name, module)	Adds a child module to the current module.
get_submodule(target)	Returns the submodule given by target if it exists, otherwise throws an error.
get_parameter(target)	Returns the parameter given by target if it exists, otherwise throws an error.
get_buffer(target)	Returns the buffer given by target if it exists, otherwise throws an error.
apply(fn)	Applies fn recursively to every submodule (as returned by .children()) as well as self.
cuda([device])	Moves all model parameters and buffers to the GPU.
xpu([device])	Moves all model parameters and buffers to the XPU.
cpu()	Moves all model parameters and buffers to the CPU.
type(dst_type)	Casts all parameters and buffers to dst_type.
float()	Casts all floating point parameters and buffers to float datatype.
double()	Casts all floating point parameters and buffers to double datatype.
half()	Casts all floating point parameters and buffers to half datatype.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
to_empty(*, device)	Moves the parameters and buffers to the specified device without copying storage.
to(*args, **kwargs)	Moves and/or casts the parameters and buffers.
register_backward_hook(hook)	Registers a backward hook on the module.
register_full_backward_hook(hook)	Registers a backward hook on the module.
register_forward_pre_hook(hook)	Registers a forward pre-hook on the module.
register_forward_hook(hook)	Registers a forward hook on the module.
state_dict([destination, prefix, keep_vars])	Returns a dictionary containing a whole state of the module.
load_state_dict(state_dict[, strict])	Copies parameters and buffers from state_dict into this module and its descendants.
parameters([recurse])	Returns an iterator over module parameters.
named_parameters([prefix, recurse])	Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
buffers([recurse])	Returns an iterator over module buffers.
named_buffers([prefix, recurse])	Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
children()	Returns an iterator over immediate children modules.
named_children()	Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
modules()	Returns an iterator over all modules in the network.
named_modules([memo, prefix, remove_duplicate])	Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
train([mode])	Sets the module in training mode.
eval()	Sets the module in evaluation mode.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
zero_grad([set_to_none])	Sets gradients of all model parameters to zero.
share_memory()	See torch.Tensor.share_memory_()
extra_repr()	Set the extra representation of the module

Special Methods:

__repr__()

Representation based on this instances settings.

Inherited from : py: class:Module

__init__()	Initializes internal Module state, shared by both nn.Module and ScriptModule.
__call__(*input, **kwargs)	Call self as a function.
__setstate__(state)
__getattr__(name)
__setattr__(name, value)	Implement setattr(self, name, value).
__delattr__(name)	Implement delattr(self, name).
__repr__()	Representation based on this instances settings.
__dir__()	Default dir() implementation.

---

__repr__()

Representation based on this instances settings.

abstract conv_op(masks)

The convolutional operation on the masks (without validation).

Parameters

masks (Tensor) – torch.Tensor of shape (batch_size, 1, width, height) holding masks for one batch.

Return type

Tensor

forward(masks)

Wrapper for the convolutional operation on batch of masks. Validates the masks and ensures the encoder is on the correct device.

Parameters

masks (Tensor) – torch.Tensor of shape (batch_size, 1, width, height) holding masks for one batch.

Return type

Tensor

AREA_DIMS: Tuple[int] = (2, 3)

Indices of axes in which the image area is defined. The targets are expected to have size with the following dimensions:

• size()[0]: batch_dim

• size()[1]: channels

• size()[AREA_DIMS]: size dimensions of one filter’s activation map, e.g. (2, 3) for 2D and (2, 3, 4) for 3D

property kernel_size: Tuple[int, ...]

The kernel size of the window.

property settings: Dict[str, Any]

Settings to reproduce the instance.