Spaces:
Runtime error
Runtime error
File size: 7,410 Bytes
b334e29 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 |
import mmcv
import torch.nn as nn
import torch.nn.functional as F
from ..builder import LOSSES
from .utils import weighted_loss
@mmcv.jit(derivate=True, coderize=True)
@weighted_loss
def quality_focal_loss(pred, target, beta=2.0):
r"""Quality Focal Loss (QFL) is from `Generalized Focal Loss: Learning
Qualified and Distributed Bounding Boxes for Dense Object Detection
<https://arxiv.org/abs/2006.04388>`_.
Args:
pred (torch.Tensor): Predicted joint representation of classification
and quality (IoU) estimation with shape (N, C), C is the number of
classes.
target (tuple([torch.Tensor])): Target category label with shape (N,)
and target quality label with shape (N,).
beta (float): The beta parameter for calculating the modulating factor.
Defaults to 2.0.
Returns:
torch.Tensor: Loss tensor with shape (N,).
"""
assert len(target) == 2, """target for QFL must be a tuple of two elements,
including category label and quality label, respectively"""
# label denotes the category id, score denotes the quality score
label, score = target
# negatives are supervised by 0 quality score
pred_sigmoid = pred.sigmoid()
scale_factor = pred_sigmoid
zerolabel = scale_factor.new_zeros(pred.shape)
loss = F.binary_cross_entropy_with_logits(
pred, zerolabel, reduction='none') * scale_factor.pow(beta)
# FG cat_id: [0, num_classes -1], BG cat_id: num_classes
bg_class_ind = pred.size(1)
pos = ((label >= 0) & (label < bg_class_ind)).nonzero().squeeze(1)
pos_label = label[pos].long()
# positives are supervised by bbox quality (IoU) score
scale_factor = score[pos] - pred_sigmoid[pos, pos_label]
loss[pos, pos_label] = F.binary_cross_entropy_with_logits(
pred[pos, pos_label], score[pos],
reduction='none') * scale_factor.abs().pow(beta)
loss = loss.sum(dim=1, keepdim=False)
return loss
@mmcv.jit(derivate=True, coderize=True)
@weighted_loss
def distribution_focal_loss(pred, label):
r"""Distribution Focal Loss (DFL) is from `Generalized Focal Loss: Learning
Qualified and Distributed Bounding Boxes for Dense Object Detection
<https://arxiv.org/abs/2006.04388>`_.
Args:
pred (torch.Tensor): Predicted general distribution of bounding boxes
(before softmax) with shape (N, n+1), n is the max value of the
integral set `{0, ..., n}` in paper.
label (torch.Tensor): Target distance label for bounding boxes with
shape (N,).
Returns:
torch.Tensor: Loss tensor with shape (N,).
"""
dis_left = label.long()
dis_right = dis_left + 1
weight_left = dis_right.float() - label
weight_right = label - dis_left.float()
loss = F.cross_entropy(pred, dis_left, reduction='none') * weight_left \
+ F.cross_entropy(pred, dis_right, reduction='none') * weight_right
return loss
@LOSSES.register_module()
class QualityFocalLoss(nn.Module):
r"""Quality Focal Loss (QFL) is a variant of `Generalized Focal Loss:
Learning Qualified and Distributed Bounding Boxes for Dense Object
Detection <https://arxiv.org/abs/2006.04388>`_.
Args:
use_sigmoid (bool): Whether sigmoid operation is conducted in QFL.
Defaults to True.
beta (float): The beta parameter for calculating the modulating factor.
Defaults to 2.0.
reduction (str): Options are "none", "mean" and "sum".
loss_weight (float): Loss weight of current loss.
"""
def __init__(self,
use_sigmoid=True,
beta=2.0,
reduction='mean',
loss_weight=1.0):
super(QualityFocalLoss, self).__init__()
assert use_sigmoid is True, 'Only sigmoid in QFL supported now.'
self.use_sigmoid = use_sigmoid
self.beta = beta
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): Predicted joint representation of
classification and quality (IoU) estimation with shape (N, C),
C is the number of classes.
target (tuple([torch.Tensor])): Target category label with shape
(N,) and target quality label with shape (N,).
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.
Defaults to None.
"""
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 * quality_focal_loss(
pred,
target,
weight,
beta=self.beta,
reduction=reduction,
avg_factor=avg_factor)
else:
raise NotImplementedError
return loss_cls
@LOSSES.register_module()
class DistributionFocalLoss(nn.Module):
r"""Distribution Focal Loss (DFL) is a variant of `Generalized Focal Loss:
Learning Qualified and Distributed Bounding Boxes for Dense Object
Detection <https://arxiv.org/abs/2006.04388>`_.
Args:
reduction (str): Options are `'none'`, `'mean'` and `'sum'`.
loss_weight (float): Loss weight of current loss.
"""
def __init__(self, reduction='mean', loss_weight=1.0):
super(DistributionFocalLoss, self).__init__()
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): Predicted general distribution of bounding
boxes (before softmax) with shape (N, n+1), n is the max value
of the integral set `{0, ..., n}` in paper.
target (torch.Tensor): Target distance label for bounding boxes
with shape (N,).
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.
Defaults to None.
"""
assert reduction_override in (None, 'none', 'mean', 'sum')
reduction = (
reduction_override if reduction_override else self.reduction)
loss_cls = self.loss_weight * distribution_focal_loss(
pred, target, weight, reduction=reduction, avg_factor=avg_factor)
return loss_cls
|