BatchIoUEncode2D

class hybrid_learning.datasets.transforms.encoder.BatchIoUEncode2D(proto_shape=None, kernel_size=None, smooth=1e-07)

Bases: BatchConvOp

Apply intersection over union encoding to an input batch. The batch is assumed to be of shape (batch_size, 1, height, width).

Idea

The idea of intersection over union (IoU) encoding is to have a generalized and continuous bounding box score. The better a given proto-shape (e.g. a box) overlaps with the ground truth shape, the higher the value in [0,1]. More precisely, in an IoU encoding of a segmentation target, a pixel holds the IoU value of the actual segmentation with a pre-defined proto-shape centered at this pixel. In a traditional segmentation a pixel holds the information whether it is part of a visual object in the image.

Such a proto shape is defined by a (not necessarily binary) mask, which may be at most the size of the target mask.

Theoretical Notes

Since the pixel values of proto shape and segmentation mask need not be binary, they are treated as fuzzy sets. Intersection and union of masks are calculated with respect to the product t-norm (see BatchIntersectEncode2D). The area values are collected by reduction by sum.

Implementation Notes

To change from 2D to other image dimensionality, replace the padding and pooling layer and adapt AREA_DIMS accordingly.

Public Data Attributes:

proto_shape	The proto shape used for IoU calculation
settings	Settings to reproduce instance.

Inherited from : py: class:BatchConvOp

proto_shape	The proto shape used for IoU calculation
kernel_size	The kernel size of the proto-type shape.
settings	Settings to reproduce instance.

Inherited from : py: class:BatchWindowOp

AREA_DIMS	Indices of axes in which the image area is defined.
kernel_size	The kernel size of the proto-type shape.
settings	Settings to reproduce 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:

smooth_division(dividend, divisor)	Smoothed division using smoothening summand to avoid division by 0.
conv_op(masks)	Encode given masks as IoU masks.

Inherited from : py: class:BatchWindowOp

forward(masks)	Wrapper for the convolutional operation on batch of masks.
conv_op(masks)	Encode given masks as IoU masks.

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:

__init__([proto_shape, kernel_size, smooth])

Init.

Inherited from : py: class:BatchWindowOp

__repr__()

Representation based on this instances settings.

Inherited from : py: class:Module

__init__([proto_shape, kernel_size, smooth])	Init.
__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.

---

Parameters

• proto_shape (ndarray) –

• kernel_size (Tuple[int, ...]) –

• smooth (float) –

__init__(proto_shape=None, kernel_size=None, smooth=1e-07)

Init.

Parameters

• proto_shape (Optional[ndarray]) – the proto shape definition in a form accepted by numpy.ndarray()

• kernel_size (Optional[Tuple[int, ...]]) – if proto_shape is None, use all-ones rectangular shape of kernel_size

• smooth (float) – smoothing summand for smooth division

conv_op(masks)

Encode given masks as IoU masks.

Parameters

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

Returns

torch.Tensor of the same size as masks tensor holding IoU encoding of the latter

Return type

Tensor

smooth_division(dividend, divisor)

Smoothed division using smoothening summand to avoid division by 0.

Returns

result of smooth division.

area_proto_shape: float

Area of the proto shape; calculate only once for speed-up

property proto_shape: numpy.ndarray

The proto shape used for IoU calculation

property settings: Dict[str, Any]

Settings to reproduce instance.

smooth: float

Smoothening summand for smooth division.

training: bool