oneflow.nn.SmoothL1Loss

class oneflow.nn.SmoothL1Loss(reduction: str = 'mean', beta: float = 1.0)

Creates a criterion that uses a squared term if the absolute element-wise error falls below beta and an L1 term otherwise. The interface is consistent with PyTorch. The documentation is referenced from: https://pytorch.org/docs/1.10/generated/torch.nn.SmoothL1Loss.html.

It is less sensitive to outliers than torch.nn.MSELoss and in some cases prevents exploding gradients (e.g. see the paper Fast R-CNN by Ross Girshick)..

For a batch of size \(N\), the unreduced loss can be described as:

\[\ell(x, y) = L = \{l_1, ..., l_N\}^T\]

with

\[\begin{split}l_n = \begin{cases} 0.5 (x_n - y_n)^2 / beta, & \text{if } |x_n - y_n| < beta \\ |x_n - y_n| - 0.5 * beta, & \text{otherwise } \end{cases}\end{split}\]

If reduction is not none, then:

\[\begin{split}\ell(x, y) = \begin{cases} \operatorname{mean}(L), & \text{if reduction} = \text{`mean';}\\ \operatorname{sum}(L), & \text{if reduction} = \text{`sum'.} \end{cases}\end{split}\]

Note

Smooth L1 loss can be seen as exactly L1Loss, but with the \(|x - y| < beta\) portion replaced with a quadratic function such that its slope is 1 at \(|x - y| = beta\). The quadratic segment smooths the L1 loss near \(|x - y| = 0\).

Note

Smooth L1 loss is closely related to HuberLoss, being equivalent to \(huber(x, y) / beta\) (note that Smooth L1’s beta hyper-parameter is also known as delta for Huber). This leads to the following differences:

• As beta -> 0, Smooth L1 loss converges to L1Loss, while HuberLoss converges to a constant 0 loss.

• As beta -> \(+\infty\), Smooth L1 loss converges to a constant 0 loss, while HuberLoss converges to MSELoss.

• For Smooth L1 loss, as beta varies, the L1 segment of the loss has a constant slope of 1. For HuberLoss, the slope of the L1 segment is beta.

Parameters

• size_average (bool, optional) – Deprecated (see reduction). By default, the losses are averaged over each loss element in the batch. Note that for some losses, there are multiple elements per sample. If the field size_average is set to False, the losses are instead summed for each minibatch. Ignored when reduce is False. Default: True

• reduce (bool, optional) – Deprecated (see reduction). By default, the losses are averaged or summed over observations for each minibatch depending on size_average. When reduce is False, returns a loss per batch element instead and ignores size_average. Default: True

• reduction (string, optional) – Specifies the reduction to apply to the output: '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. Note: size_average and reduce are in the process of being deprecated, and in the meantime, specifying either of those two args will override reduction. Default: 'mean'

• beta (float, optional) – Specifies the threshold at which to change between L1 and L2 loss. The value must be non-negative. Default: 1.0

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 the input

For example:

>>> import oneflow as flow
>>> import numpy as np

>>> x = flow.tensor(np.array([0.1, 0.4, 0.3, 0.5, 0.9]).astype(np.float32), dtype=flow.float32)
>>> y = flow.tensor(np.array([0.3, 0.9, 2.5, 0.4, 0.3]).astype(np.float32), dtype=flow.float32)
>>> m = flow.nn.SmoothL1Loss(reduction="none")
>>> out = m(x, y)
>>> out
tensor([0.0200, 0.1250, 1.7000, 0.0050, 0.1800], dtype=oneflow.float32)

>>> m = flow.nn.SmoothL1Loss(reduction="mean")
>>> out = m(x, y)
>>> out
tensor(0.4060, dtype=oneflow.float32)

>>> m = flow.nn.SmoothL1Loss(reduction="sum")
>>> out = m(x, y)
>>> out
tensor(2.0300, dtype=oneflow.float32)

__init__(reduction: str = 'mean', beta: float = 1.0) → 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__([reduction, beta])	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.