EasyCV/easycv/models/loss/focal_loss.py

388 lines
16 KiB
Python

# Copyright (c) OpenMMLab. All rights reserved.
import torch
import torch.nn as nn
import torch.nn.functional as F
from mmcv.ops import sigmoid_focal_loss as _sigmoid_focal_loss
from easycv.models.builder import LOSSES
from easycv.models.loss.utils import weight_reduce_loss
def reduce_loss(loss, reduction):
"""Reduce loss as specified.
Args:
loss (Tensor): Elementwise loss tensor.
reduction (str): Options are "none", "mean" and "sum".
Return:
Tensor: Reduced loss tensor.
"""
reduction_enum = F._Reduction.get_enum(reduction)
# none: 0, elementwise_mean:1, sum: 2
if reduction_enum == 0:
return loss
elif reduction_enum == 1:
return loss.mean()
elif reduction_enum == 2:
return loss.sum()
else:
raise ValueError('reduction_enum should be 0,1,2')
def varifocal_loss(pred,
target,
weight=None,
alpha=0.75,
gamma=2.0,
iou_weighted=True,
reduction='mean',
avg_factor=None):
"""`Varifocal Loss <https://arxiv.org/abs/2008.13367>`_
Args:
pred (torch.Tensor): The prediction with shape (N, C), C is the
number of classes
target (torch.Tensor): The learning target of the iou-aware
classification score with shape (N, C), C is the number of classes.
weight (torch.Tensor, optional): The weight of loss for each
prediction. Defaults to None.
alpha (float, optional): A balance factor for the negative part of
Varifocal Loss, which is different from the alpha of Focal Loss.
Defaults to 0.75.
gamma (float, optional): The gamma for calculating the modulating
factor. Defaults to 2.0.
iou_weighted (bool, optional): Whether to weight the loss of the
positive example with the iou target. Defaults to True.
reduction (str, optional): The method used to reduce the loss into
a scalar. Defaults to 'mean'. Options are "none", "mean" and
"sum".
avg_factor (int, optional): Average factor that is used to average
the loss. Defaults to None.
"""
# pred and target should be of the same size
assert pred.size() == target.size()
pred_sigmoid = pred.sigmoid()
target = target.type_as(pred)
if iou_weighted:
focal_weight = target * (target > 0.0).float() + \
alpha * (pred_sigmoid - target).abs().pow(gamma) * \
(target <= 0.0).float()
else:
focal_weight = (target > 0.0).float() + \
alpha * (pred_sigmoid - target).abs().pow(gamma) * \
(target <= 0.0).float()
loss = F.binary_cross_entropy_with_logits(
pred, target, reduction='none') * focal_weight
loss = weight_reduce_loss(loss, weight, reduction, avg_factor)
return loss
@LOSSES.register_module
class VarifocalLoss(nn.Module):
def __init__(self,
use_sigmoid=True,
alpha=0.75,
gamma=2.0,
iou_weighted=True,
reduction='mean',
loss_weight=1.0):
"""`Varifocal Loss <https://arxiv.org/abs/2008.13367>`_
Args:
use_sigmoid (bool, optional): Whether the prediction is
used for sigmoid or softmax. Defaults to True.
alpha (float, optional): A balance factor for the negative part of
Varifocal Loss, which is different from the alpha of Focal
Loss. Defaults to 0.75.
gamma (float, optional): The gamma for calculating the modulating
factor. Defaults to 2.0.
iou_weighted (bool, optional): Whether to weight the loss of the
positive examples with the iou target. Defaults to True.
reduction (str, optional): The method used to reduce the loss into
a scalar. Defaults to 'mean'. Options are "none", "mean" and
"sum".
loss_weight (float, optional): Weight of loss. Defaults to 1.0.
"""
super(VarifocalLoss, self).__init__()
assert use_sigmoid is True, \
'Only sigmoid varifocal loss supported now.'
assert alpha >= 0.0
self.use_sigmoid = use_sigmoid
self.alpha = alpha
self.gamma = gamma
self.iou_weighted = iou_weighted
self.reduction = reduction
self.loss_weight = loss_weight
def forward(self,
pred,
target,
weight=None,
avg_factor=None,
reduction_override=None):
"""Forward function.
Args:
pred (torch.Tensor): The prediction.
target (torch.Tensor): The learning target of the prediction.
weight (torch.Tensor, optional): The weight of loss for each
prediction. Defaults to None.
avg_factor (int, optional): Average factor that is used to average
the loss. Defaults to None.
reduction_override (str, optional): The reduction method used to
override the original reduction method of the loss.
Options are "none", "mean" and "sum".
Returns:
torch.Tensor: The calculated loss
"""
assert reduction_override in (None, 'none', 'mean', 'sum')
reduction = (
reduction_override if reduction_override else self.reduction)
if self.use_sigmoid:
loss_cls = self.loss_weight * varifocal_loss(
pred,
target,
weight,
alpha=self.alpha,
gamma=self.gamma,
iou_weighted=self.iou_weighted,
reduction=reduction,
avg_factor=avg_factor)
else:
raise NotImplementedError
return loss_cls
def py_sigmoid_focal_loss(inputs,
targets,
weight=None,
gamma=2.0,
alpha=0.25,
reduction='mean',
avg_factor=None):
"""PyTorch version of `Focal Loss <https://arxiv.org/abs/1708.02002>`_.
Args:
inputs (torch.Tensor): The prediction with shape (N, C), C is the
number of classes
targets (torch.Tensor): The learning label of the prediction.
weight (torch.Tensor, optional): Sample-wise loss weight.
gamma (float, optional): The gamma for calculating the modulating
factor. Defaults to 2.0.
alpha (float, optional): A balanced form for Focal Loss.
Defaults to 0.25.
reduction (str, optional): The method used to reduce the loss into
a scalar. Defaults to 'mean'.
avg_factor (int, optional): Average factor that is used to average
the loss. Defaults to None.
"""
prob = inputs.sigmoid()
ce_loss = F.binary_cross_entropy_with_logits(
inputs, targets, reduction='none')
p_t = prob * targets + (1 - prob) * (1 - targets)
loss = ce_loss * ((1 - p_t)**gamma)
if alpha >= 0:
alpha_t = alpha * targets + (1 - alpha) * (1 - targets)
loss = alpha_t * loss
if weight is not None:
if weight.shape != loss.shape:
if weight.size(0) == loss.size(0):
# For most cases, weight is of shape (num_priors, ),
# which means it does not have the second axis num_class
weight = weight.view(-1, 1)
else:
# Sometimes, weight per anchor per class is also needed. e.g.
# in FSAF. But it may be flattened of shape
# (num_priors x num_class, ), while loss is still of shape
# (num_priors, num_class).
assert weight.numel() == loss.numel()
weight = weight.view(loss.size(0), -1)
assert weight.ndim == loss.ndim
loss = weight_reduce_loss(loss, weight, reduction, avg_factor)
return loss
def py_focal_loss_with_prob(pred,
target,
weight=None,
gamma=2.0,
alpha=0.25,
reduction='mean',
avg_factor=None):
"""PyTorch version of `Focal Loss <https://arxiv.org/abs/1708.02002>`_.
Different from `py_sigmoid_focal_loss`, this function accepts probability
as input.
Args:
pred (torch.Tensor): The prediction probability with shape (N, C),
C is the number of classes.
target (torch.Tensor): The learning label of the prediction.
weight (torch.Tensor, optional): Sample-wise loss weight.
gamma (float, optional): The gamma for calculating the modulating
factor. Defaults to 2.0.
alpha (float, optional): A balanced form for Focal Loss.
Defaults to 0.25.
reduction (str, optional): The method used to reduce the loss into
a scalar. Defaults to 'mean'.
avg_factor (int, optional): Average factor that is used to average
the loss. Defaults to None.
"""
num_classes = pred.size(1)
target = F.one_hot(target, num_classes=num_classes + 1)
target = target[:, :num_classes]
target = target.type_as(pred)
pt = (1 - pred) * target + pred * (1 - target)
focal_weight = (alpha * target + (1 - alpha) *
(1 - target)) * pt.pow(gamma)
loss = F.binary_cross_entropy(
pred, target, reduction='none') * focal_weight
if weight is not None:
if weight.shape != loss.shape:
if weight.size(0) == loss.size(0):
# For most cases, weight is of shape (num_priors, ),
# which means it does not have the second axis num_class
weight = weight.view(-1, 1)
else:
# Sometimes, weight per anchor per class is also needed. e.g.
# in FSAF. But it may be flattened of shape
# (num_priors x num_class, ), while loss is still of shape
# (num_priors, num_class).
assert weight.numel() == loss.numel()
weight = weight.view(loss.size(0), -1)
assert weight.ndim == loss.ndim
loss = weight_reduce_loss(loss, weight, reduction, avg_factor)
return loss
def sigmoid_focal_loss(pred,
target,
weight=None,
gamma=2.0,
alpha=0.25,
reduction='mean',
avg_factor=None):
r"""A warpper of cuda version `Focal Loss
<https://arxiv.org/abs/1708.02002>`_.
Args:
pred (torch.Tensor): The prediction with shape (N, C), C is the number
of classes.
target (torch.Tensor): The learning label of the prediction.
weight (torch.Tensor, optional): Sample-wise loss weight.
gamma (float, optional): The gamma for calculating the modulating
factor. Defaults to 2.0.
alpha (float, optional): A balanced form for Focal Loss.
Defaults to 0.25.
reduction (str, optional): The method used to reduce the loss into
a scalar. Defaults to 'mean'. Options are "none", "mean" and "sum".
avg_factor (int, optional): Average factor that is used to average
the loss. Defaults to None.
"""
# Function.apply does not accept keyword arguments, so the decorator
# "weighted_loss" is not applicable
loss = _sigmoid_focal_loss(pred.contiguous(), target.contiguous(), gamma,
alpha, None, 'none')
if weight is not None:
if weight.shape != loss.shape:
if weight.size(0) == loss.size(0):
# For most cases, weight is of shape (num_priors, ),
# which means it does not have the second axis num_class
weight = weight.view(-1, 1)
else:
# Sometimes, weight per anchor per class is also needed. e.g.
# in FSAF. But it may be flattened of shape
# (num_priors x num_class, ), while loss is still of shape
# (num_priors, num_class).
assert weight.numel() == loss.numel()
weight = weight.view(loss.size(0), -1)
assert weight.ndim == loss.ndim
loss = weight_reduce_loss(loss, weight, reduction, avg_factor)
return loss
@LOSSES.register_module()
class FocalLoss(nn.Module):
def __init__(self,
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
reduction='mean',
loss_weight=1.0,
activated=False):
"""`Focal Loss <https://arxiv.org/abs/1708.02002>`_
Args:
use_sigmoid (bool, optional): Whether to the prediction is
used for sigmoid or softmax. Defaults to True.
gamma (float, optional): The gamma for calculating the modulating
factor. Defaults to 2.0.
alpha (float, optional): A balanced form for Focal Loss.
Defaults to 0.25.
reduction (str, optional): The method used to reduce the loss into
a scalar. Defaults to 'mean'. Options are "none", "mean" and
"sum".
loss_weight (float, optional): Weight of loss. Defaults to 1.0.
activated (bool, optional): Whether the input is activated.
If True, it means the input has been activated and can be
treated as probabilities. Else, it should be treated as logits.
Defaults to False.
"""
super(FocalLoss, self).__init__()
assert use_sigmoid is True, 'Only sigmoid focal loss supported now.'
self.use_sigmoid = use_sigmoid
self.gamma = gamma
self.alpha = alpha
self.reduction = reduction
self.loss_weight = loss_weight
self.activated = activated
def forward(self,
pred,
target,
weight=None,
avg_factor=None,
reduction_override=None):
"""Forward function.
Args:
pred (torch.Tensor): The prediction.
target (torch.Tensor): The learning label of the prediction.
weight (torch.Tensor, optional): The weight of loss for each
prediction. Defaults to None.
avg_factor (int, optional): Average factor that is used to average
the loss. Defaults to None.
reduction_override (str, optional): The reduction method used to
override the original reduction method of the loss.
Options are "none", "mean" and "sum".
Returns:
torch.Tensor: The calculated loss
"""
assert reduction_override in (None, 'none', 'mean', 'sum')
reduction = (
reduction_override if reduction_override else self.reduction)
if self.use_sigmoid:
if self.activated:
calculate_loss_func = py_focal_loss_with_prob
else:
if torch.cuda.is_available() and pred.is_cuda:
calculate_loss_func = sigmoid_focal_loss
else:
num_classes = pred.size(1)
target = F.one_hot(target, num_classes=num_classes + 1)
target = target[:, :num_classes]
calculate_loss_func = py_sigmoid_focal_loss
loss_cls = self.loss_weight * calculate_loss_func(
pred,
target,
weight,
gamma=self.gamma,
alpha=self.alpha,
reduction=reduction,
avg_factor=avg_factor)
else:
raise NotImplementedError
return loss_cls