oneflow.nn.BCEWithLogitsLoss¶

class oneflow.nn.BCEWithLogitsLoss(weight: Optional[oneflow.Tensor] = None, reduction: str = 'mean', pos_weight: Optional[oneflow.Tensor] = None)¶

This operator combines the Sigmoid and BCELoss together. For numerical stability, we apply some math tricks instead of using Sigmoid layer with BCELoss.

The equation is:

if reduction = "none":

\[out = -weight*[Pos\_weight*y*log\sigma({x}) + (1-y)*log(1-\sigma(x))]\]

if reduction = "mean":

\[out = -\frac{weight}{n}\sum_{i=1}^n[Pos\_weight*y*log\sigma({x}) + (1-y)*log(1-\sigma(x))]\]

if reduction = "sum":

\[out = -weight*\sum_{i=1}^n[Pos\_weight*y*log\sigma({x}) + (1-y)*log(1-\sigma(x))]\]

Parameters

weight (Tensor, optional) – The manual rescaling weight to the loss. Default: None
size_average (bool, optional) – Deprecated (see reduction). Default: True
reduce (bool, optional) – Deprecated (see reduction). Default: True
reduction (str, optional) – The reduce type, it can be one of "none", "mean", "sum". 'none': no reduction will be applied, 'mean': the sum of the output will be divided by the number of elements in the output, 'sum': the output will be summed. Default: "mean"
pos_weight (Tensor, optional) – The manual rescaling weight to the positive examples. Default: None

Shape:

Input: \((N,*)\) where * means, any number of additional dimensions
Target: \((N,*)\), same shape as the input
Output: scalar. If reduction is "none", then \((N,*)\), same shape as input.

For example:

>>> import oneflow as flow
>>> input = flow.tensor([[1.2, 0.2, -0.3], [0.7, 0.6, -2], [0.7, 0.6, -2]], dtype=flow.float32)
>>> target = flow.tensor([[0, 1, 0], [1, 0, 1], [1, 0, 1]], dtype=flow.float32)
>>> weight = flow.tensor([[2, 2, 2], [2, 2, 2], [2, 2, 2]], dtype=flow.float32)
>>> pos_weight = flow.tensor([1.2, 1.3, 1.4], dtype=flow.float32)

>>> m = flow.nn.BCEWithLogitsLoss(weight=weight, pos_weight=pos_weight, reduction="none")
>>> out = m(input, target)
>>> out
tensor([[2.9266, 1.5552, 1.1087],
        [0.9676, 2.0750, 5.9554],
        [0.9676, 2.0750, 5.9554]], dtype=oneflow.float32)

>>> m = flow.nn.BCEWithLogitsLoss(weight=weight, pos_weight=pos_weight, reduction="mean")
>>> out = m(input, target)
>>> out
tensor(2.6207, dtype=oneflow.float32)

>>> m = flow.nn.BCEWithLogitsLoss(weight=weight, pos_weight=pos_weight, reduction="sum")
>>> out = m(input, target)
>>> out
tensor(23.5865, dtype=oneflow.float32)

__init__(weight: Optional[oneflow.Tensor] = None, reduction: str = 'mean', pos_weight: Optional[oneflow.Tensor] = None) → None ¶: Initialize self. See help(type(self)) for accurate signature.

Methods

`__call__`(args, *kwargs)	Call self as a function.
`__delattr__`(name, /)	Implement delattr(self, name).
`__dir__`()	Default dir() implementation.
`__eq__`(value, /)	Return self==value.
`__format__`(format_spec, /)	Default object formatter.
`__ge__`(value, /)	Return self>=value.
`__getattr__`(name)
`__getattribute__`(name, /)	Return getattr(self, name).
`__gt__`(value, /)	Return self>value.
`__hash__`()	Return hash(self).
`__init__`([weight, reduction, pos_weight])	Initialize self.
`__init_subclass__`	This method is called when a class is subclassed.
`__le__`(value, /)	Return self<=value.
`__lt__`(value, /)	Return self<value.
`__ne__`(value, /)	Return self!=value.
`__new__`(**kwargs)	Create and return a new object.
`__reduce__`()	Helper for pickle.
`__reduce_ex__`(protocol, /)	Helper for pickle.
`__repr__`()	Return repr(self).
`__setattr__`(name, value)	Implement setattr(self, name, value).
`__sizeof__`()	Size of object in memory, in bytes.
`__str__`()	Return str(self).
`__subclasshook__`	Abstract classes can override this to customize issubclass().
`_apply`(fn[, applied_dict])
`_get_name`()
`_load_from_state_dict`(state_dict, prefix, …)
`_named_members`(get_members_fn[, prefix, recurse])
`_save_to_state_dict`(destination, prefix, …)
`_shallow_repr`()
`add_module`(name, module)	Adds a child module to the current module.
`apply`(fn)	Applies `fn` recursively to every submodule (as returned by `.children()`) as well as self.
`buffers`([recurse])	Returns an iterator over module buffers.
`children`()	Returns an iterator over immediate children modules.
`cpu`()	Moves all model parameters and buffers to the CPU.
`cuda`([device])	Moves all model parameters and buffers to the GPU.
`double`()	Casts all floating point parameters and buffers to `double` datatype.
`eval`()	Sets the module in evaluation mode.
`extra_repr`()	Set the extra representation of the module
`float`()	Casts all floating point parameters and buffers to `float` datatype.
`forward`(input, target)
`half`()	Casts all floating point parameters and buffers to `half` datatype.
`load_state_dict`(state_dict[, strict])	Copies parameters and buffers from `state_dict` into this module and its descendants.
`modules`()	Returns an iterator over all modules in the network.
`named_buffers`([prefix, recurse])	Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
`named_children`()	Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
`named_modules`([memo, prefix])	Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
`named_parameters`([prefix, recurse])	Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
`parameters`([recurse])	Returns an iterator over module parameters.
`register_buffer`(name, tensor[, persistent])	Adds a buffer to the module.
`register_forward_hook`(hook)	Registers a forward hook on the module.
`register_forward_pre_hook`(hook)	Registers a forward pre-hook on the module.
`register_parameter`(name, param)	Adds a parameter to the module.
`state_dict`([destination, prefix, keep_vars])	Returns a dictionary containing a whole state of the module.
`to`([device])	Moves the parameters and buffers.
`to_consistent`(args, *kwargs)	This interface is no longer available, please use `oneflow.nn.Module.to_global()` instead.
`to_global`([placement, sbp])	Convert the parameters and buffers to global.
`train`([mode])	Sets the module in training mode.
`zero_grad`([set_to_none])	Sets gradients of all model parameters to zero.