BalancedBCELoss

class hybrid_learning.concepts.train_eval.kpis.batch_kpis.BalancedBCELoss(factor_pos_class=None, reduction='mean', from_logit=False)[source]

Bases: Module

Balanced binary cross entropy loss. This is a wrapper around torch.nn.functional.binary_cross_entropy which allows to enter a class weighting factor \(b\) to have for a batch \(B\) of outputs and targets \((x, y)\) the formula

\[\text{BalancedBCELoss}(B) = \text{reduction}( \sum_{(x,y)\in B} b \cdot y \cdot \log(x) + (1-b)(1-y)\log(1-x) )\]

If no fixed factor_pos_class is given, this is determined batch-wise as 1-target.mean(). Target values are assumed to be binary. Input values are assumed to be in \((0,1]\) if from_logit is false, else they are assumed to be in logit space. The reduction can be mean, sum, or none.

Public Data Attributes:

settings

Settings dict 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(inputs, targets)

Pytorch forward method.
Inherited from : py: class:Module

forward(inputs, targets)

Pytorch forward method.

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__([factor_pos_class, reduction, ...])

Init.

__repr__()

Return repr(self).

__str__()

Return str(self).
Inherited from : py: class:Module

__init__([factor_pos_class, reduction, ...])

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__()

Return repr(self).

__dir__()

Default dir() implementation.
Parameters
__init__(factor_pos_class=None, reduction='mean', from_logit=False)[source]

Init.

Parameters

  • factor_pos_class (Optional[float]) – balancing factor in [0,1] applied to the zero class

  • reduction (str) –

    one of

    • none: no reduction

    • mean: mean over batch dimension 0;

    • sum: sum over batch dimension 0

  • from_logit (bool) –

__repr__()[source]

Return repr(self).

Return type

str

__str__()[source]

Return str(self).

Return type

str

forward(inputs, targets)[source]

Pytorch forward method.

Parameters
Return type

Tensor

factor_pos_class: Optional[float]

Balancing factor \(b\) applied to the positive class; \((1-b)\) is applied to the negative class. If set to None, it is calculated batch-wise as 1-targets.mean().

from_logit: bool

Whether to treat the input values as logits or as values in \((0, 1]\).

reduction: str

Reduction method to aggregate batch results. One of ‘none’, ‘mean’, ‘sum’

property settings: Dict[str, Any]

Settings dict to reproduce the instance

training: bool