SIoU损失函数
论文链接:https://arxiv.org/pdf/2205.12740
SIoU(Simplified IoU)损失函数是一种基于IoU(Intersection over Union)的改进损失函数,主要用于目标检测任务中的边界框回归。与传统的IoU损失函数相比,SIoU损失函数考虑了更多的几何特性,如边界框的中心点位置、长宽比和角度,从而提高了检测的准确性和鲁棒性。
设计思路
-
中心点距离:传统IoU损失主要关注边界框的重叠区域,但没有直接考虑框的中心位置。SIoU损失引入了一个中心点距离项,即预测框与真实框中心点之间的距离。这有助于优化模型以使预测框更准确地定位到目标的中心。
-
长宽比和角度:除了中心点距离外,SIoU还考虑了框的长宽比和角度的一致性。这是因为在很多实际应用中,目标的形状和方向信息对于正确的识别同样重要。通过对这些几何属性的考量,SIoU能够更好地处理不同形状和方向的目标。
-
简化计算:尽管引入了更多的几何特性,SIoU损失函数的设计还是尽可能地简化了计算过程,以便于在实际的深度学习框架中高效实现。
计算方式
-
计算中心点距离:
- 设定预测框中心为,真实框中心为。
- 中心点距离 D 可以使用欧氏距离计算:
-
长宽比和角度误差:
- 计算预测框和真实框的长宽比 和 。
- 通过一定的函数(如对数差)计算长宽比误差。
- 若考虑角度,还需要计算框的旋转角度差。
-
结合不同项的权重:
- 对上述计算出的中心点距离、长宽比误差和可能的角度误差按照一定的权重进行加权,以形成最终的SIoU损失。权重可以根据具体任务和数据集的特性进行调整。
-
优化目标:
最小化SIoU损失,即通过梯度下降等优化算法调整模型参数,以使得预测框与真实框之间的SIoU损失最小化。通过这种方式,SIoU损失能够综合考虑目标的位置、形状和方向等多个方面,使得目标检测模型能够更全面地学习到目标的特性,从而提高检测性能。
基于Pytorch实现SIoU Loss
import torch
import torch.nn as nn
class SIoULoss(nn.Module):
def __init__(self):
super(SIoULoss, self).__init__()
def forward(self, preds, targets):
# preds和targets的形状应该是[N, 4],其中每个框表示为[x_center, y_center, width, height]
# 提取预测和真实的中心点坐标
pred_centers = preds[:, :2]
target_centers = targets[:, :2]
# 提取预测和真实的宽度和高度
pred_sizes = preds[:, 2:]
target_sizes = targets[:, 2:]
# 计算中心点的欧式距离
center_distance = torch.norm(pred_centers - target_centers, dim=1)
# 计算宽高比的对数损失
pred_log_wh = torch.log(pred_sizes)
target_log_wh = torch.log(target_sizes)
wh_loss = torch.abs(pred_log_wh - target_log_wh).sum(dim=1) # 对宽度和高度的损失求和
# 综合中心点距离和宽高比损失
sious_loss = center_distance + wh_loss
return sious_loss.mean() # 返回批次的平均损失
# 示例用法
preds = torch.tensor([[15, 20, 50, 30], [30, 35, 60, 40]], dtype=torch.float32)
targets = torch.tensor([[14, 19, 48, 32], [32, 34, 59, 42]], dtype=torch.float32)
loss_fn = SIoULoss()
loss = loss_fn(preds, targets)
print("SIoU Loss:", loss.item())
替换SIoU损失函数(基于MMYOLO)
# 修改此处实现IoU损失函数的替换
loss_bbox=dict(
type='IoULoss',
iou_mode='siou',
bbox_format='xywh',
eps=1e-7,
reduction='mean',
loss_weight=loss_bbox_weight * (3 / num_det_layers),
return_iou=True),
修改后的配置文件(以configs/yolov5/yolov5_s-v61_syncbn_8xb16-300e_coco.py为例)
_base_ = ['../_base_/default_runtime.py', '../_base_/det_p5_tta.py']
# ========================Frequently modified parameters======================
# -----data related-----
data_root = 'data/coco/' # Root path of data
# Path of train annotation file
train_ann_file = 'annotations/instances_train2017.json'
train_data_prefix = 'train2017/' # Prefix of train image path
# Path of val annotation file
val_ann_file = 'annotations/instances_val2017.json'
val_data_prefix = 'val2017/' # Prefix of val image path
num_classes = 80 # Number of classes for classification
# Batch size of a single GPU during training
train_batch_size_per_gpu = 16
# Worker to pre-fetch data for each single GPU during training
train_num_workers = 8
# persistent_workers must be False if num_workers is 0
persistent_workers = True
# -----model related-----
# Basic size of multi-scale prior box
anchors = [
[(10, 13), (16, 30), (33, 23)], # P3/8
[(30, 61), (62, 45), (59, 119)], # P4/16
[(116, 90), (156, 198), (373, 326)] # P5/32
]
# -----train val related-----
# Base learning rate for optim_wrapper. Corresponding to 8xb16=128 bs
base_lr = 0.01
max_epochs = 300 # Maximum training epochs
model_test_cfg = dict(
# The config of multi-label for multi-class prediction.
multi_label=True,
# The number of boxes before NMS
nms_pre=30000,
score_thr=0.001, # Threshold to filter out boxes.
nms=dict(type='nms', iou_threshold=0.65), # NMS type and threshold
max_per_img=300) # Max number of detections of each image
# ========================Possible modified parameters========================
# -----data related-----
img_scale = (640, 640) # width, height
# Dataset type, this will be used to define the dataset
dataset_type = 'YOLOv5CocoDataset'
# Batch size of a single GPU during validation
val_batch_size_per_gpu = 1
# Worker to pre-fetch data for each single GPU during validation
val_num_workers = 2
# Config of batch shapes. Only on val.
# It means not used if batch_shapes_cfg is None.
batch_shapes_cfg = dict(
type='BatchShapePolicy',
batch_size=val_batch_size_per_gpu,
img_size=img_scale[0],
# The image scale of padding should be divided by pad_size_divisor
size_divisor=32,
# Additional paddings for pixel scale
extra_pad_ratio=0.5)
# -----model related-----
# The scaling factor that controls the depth of the network structure
deepen_factor = 0.33
# The scaling factor that controls the width of the network structure
widen_factor = 0.5
# Strides of multi-scale prior box
strides = [8, 16, 32]
num_det_layers = 3 # The number of model output scales
norm_cfg = dict(type='BN', momentum=0.03, eps=0.001) # Normalization config
# -----train val related-----
affine_scale = 0.5 # YOLOv5RandomAffine scaling ratio
loss_cls_weight = 0.5
loss_bbox_weight = 0.05
loss_obj_weight = 1.0
prior_match_thr = 4. # Priori box matching threshold
# The obj loss weights of the three output layers
obj_level_weights = [4., 1., 0.4]
lr_factor = 0.01 # Learning rate scaling factor
weight_decay = 0.0005
# Save model checkpoint and validation intervals
save_checkpoint_intervals = 10
# The maximum checkpoints to keep.
max_keep_ckpts = 3
# Single-scale training is recommended to
# be turned on, which can speed up training.
env_cfg = dict(cudnn_benchmark=True)
# ===============================Unmodified in most cases====================
model = dict(
type='YOLODetector',
data_preprocessor=dict(
type='mmdet.DetDataPreprocessor',
mean=[0., 0., 0.],
std=[255., 255., 255.],
bgr_to_rgb=True),
backbone=dict(
##使用YOLOv8的主干网络
type='YOLOv8CSPDarknet',
deepen_factor=deepen_factor,
widen_factor=widen_factor,
norm_cfg=norm_cfg,
act_cfg=dict(type='SiLU', inplace=True)
),
neck=dict(
type='YOLOv5PAFPN',
deepen_factor=deepen_factor,
widen_factor=widen_factor,
in_channels=[256, 512, 1024],
out_channels=[256, 512, 1024],
num_csp_blocks=3,
norm_cfg=norm_cfg,
act_cfg=dict(type='SiLU', inplace=True)),
bbox_head=dict(
type='YOLOv5Head',
head_module=dict(
type='YOLOv5HeadModule',
num_classes=num_classes,
in_channels=[256, 512, 1024],
widen_factor=widen_factor,
featmap_strides=strides,
num_base_priors=3),
prior_generator=dict(
type='mmdet.YOLOAnchorGenerator',
base_sizes=anchors,
strides=strides),
# scaled based on number of detection layers
loss_cls=dict(
type='mmdet.CrossEntropyLoss',
use_sigmoid=True,
reduction='mean',
loss_weight=loss_cls_weight *
(num_classes / 80 * 3 / num_det_layers)),
# 修改此处实现IoU损失函数的替换
loss_bbox=dict(
type='IoULoss',
iou_mode='siou',
bbox_format='xywh',
eps=1e-7,
reduction='mean',
loss_weight=loss_bbox_weight * (3 / num_det_layers),
return_iou=True),
loss_obj=dict(
type='mmdet.CrossEntropyLoss',
use_sigmoid=True,
reduction='mean',
loss_weight=loss_obj_weight *
((img_scale[0] / 640)**2 * 3 / num_det_layers)),
prior_match_thr=prior_match_thr,
obj_level_weights=obj_level_weights),
test_cfg=model_test_cfg)
albu_train_transforms = [
dict(type='Blur', p=0.01),
dict(type='MedianBlur', p=0.01),
dict(type='ToGray', p=0.01),
dict(type='CLAHE', p=0.01)
]
pre_transform = [
dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
dict(type='LoadAnnotations', with_bbox=True)
]
train_pipeline = [
*pre_transform,
dict(
type='Mosaic',
img_scale=img_scale,
pad_val=114.0,
pre_transform=pre_transform),
dict(
type='YOLOv5RandomAffine',
max_rotate_degree=0.0,
max_shear_degree=0.0,
scaling_ratio_range=(1 - affine_scale, 1 + affine_scale),
# img_scale is (width, height)
border=(-img_scale[0] // 2, -img_scale[1] // 2),
border_val=(114, 114, 114)),
dict(
type='mmdet.Albu',
transforms=albu_train_transforms,
bbox_params=dict(
type='BboxParams',
format='pascal_voc',
label_fields=['gt_bboxes_labels', 'gt_ignore_flags']),
keymap={
'img': 'image',
'gt_bboxes': 'bboxes'
}),
dict(type='YOLOv5HSVRandomAug'),
dict(type='mmdet.RandomFlip', prob=0.5),
dict(
type='mmdet.PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
'flip_direction'))
]
train_dataloader = dict(
batch_size=train_batch_size_per_gpu,
num_workers=train_num_workers,
persistent_workers=persistent_workers,
pin_memory=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=train_ann_file,
data_prefix=dict(img=train_data_prefix),
filter_cfg=dict(filter_empty_gt=False, min_size=32),
pipeline=train_pipeline))
test_pipeline = [
dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
dict(type='YOLOv5KeepRatioResize', scale=img_scale),
dict(
type='LetterResize',
scale=img_scale,
allow_scale_up=False,
pad_val=dict(img=114)),
dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
dict(
type='mmdet.PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'pad_param'))
]
val_dataloader = dict(
batch_size=val_batch_size_per_gpu,
num_workers=val_num_workers,
persistent_workers=persistent_workers,
pin_memory=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
data_root=data_root,
test_mode=True,
data_prefix=dict(img=val_data_prefix),
ann_file=val_ann_file,
pipeline=test_pipeline,
batch_shapes_cfg=batch_shapes_cfg))
test_dataloader = val_dataloader
param_scheduler = None
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(
type='SGD',
lr=base_lr,
momentum=0.937,
weight_decay=weight_decay,
nesterov=True,
batch_size_per_gpu=train_batch_size_per_gpu),
constructor='YOLOv5OptimizerConstructor')
default_hooks = dict(
param_scheduler=dict(
type='YOLOv5ParamSchedulerHook',
scheduler_type='linear',
lr_factor=lr_factor,
max_epochs=max_epochs),
checkpoint=dict(
type='CheckpointHook',
interval=save_checkpoint_intervals,
save_best='auto',
max_keep_ckpts=max_keep_ckpts))
custom_hooks = [
dict(
type='EMAHook',
ema_type='ExpMomentumEMA',
momentum=0.0001,
update_buffers=True,
strict_load=False,
priority=49)
]
val_evaluator = dict(
type='mmdet.CocoMetric',
proposal_nums=(100, 1, 10),
ann_file=data_root + val_ann_file,
metric='bbox')
test_evaluator = val_evaluator
train_cfg = dict(
type='EpochBasedTrainLoop',
max_epochs=max_epochs,
val_interval=save_checkpoint_intervals)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')