Innersiou损失函数
设计原理
IoU（Intersection over Union）是用于评估物体检测算法性能的常用指标，它衡量了预测边界框和真实边界框之间的重叠程度。然而，IoU存在一些局限性，例如在处理高度重叠的物体时，IoU难以提供足够的区分度。为了解决这个问题，Inner SIoU（Inner Section over Union）被提出作为一种改进的损失函数，用于训练物体检测模型。
一、IoU的局限性
IoU是通过计算两个边界框的交集面积除以它们的并集面积来衡量它们的重叠程度。但是，当两个边界框高度重叠时，IoU可能无法提供足够的区分度，导致难以准确地评估物体检测算法的性能。
二、Innersiou的引入
Inner SIoU是一种改进的损失函数，它通过考虑边界框内部区域的重叠情况来提高重叠边界框的区分度。Inner SIoU的计算方式如下：
- 首先，计算两个边界框的交集面积。
- 然后，计算第一个边界框的面积。
- 最后，将交集面积除以第一个边界框的面积得到Inner SIoU。
计算步骤
假设有两个边界框A和B，它们的坐标分别为(x1, y1, x2, y2)和(x3, y3, x4, y4)。则Inner SIoU的计算步骤如下：
-
计算两个边界框的交集面积：
- 交集区域的左上角坐标为(max(x1, x3), max(y1, y3))。
- 交集区域的右下角坐标为(min(x2, x4), min(y2, y4))。
- 交集区域的宽度为max(0, right - left)，高度为max(0, bottom - top)。
- 交集面积为交集区域的宽度乘以高度。
-
计算第一个边界框的面积：
- 第一个边界框的宽度为x2 - x1，高度为y2 - y1。
- 第一个边界框的面积为宽度乘以高度。
-
计算Inner SIoU：
- Inner SIoU为交集面积除以第一个边界框的面积。
使用PyTorch实现Inner SIoU计算的源代码
import torch
def calculate_inner_siou(box1, box2):
# box1: [x1, y1, x2, y2]
# box2: [x3, y3, x4, y4]
# 计算交集的左上角和右下角坐标
inter_left_top = torch.stack((torch.maximum(box1[0], box2[0]), torch.maximum(box1[1], box2[1])), dim=0)
inter_right_bottom = torch.stack((torch.minimum(box1[2], box2[2]), torch.minimum(box1[3], box2[3])), dim=0)
# 计算交集的宽度和高度
inter_width = torch.maximum(inter_right_bottom[0] - inter_left_top[0], torch.tensor(0.))
inter_height = torch.maximum(inter_right_bottom[1] - inter_left_top[1], torch.tensor(0.))
# 计算交集面积和第一个边界框的面积
inter_area = inter_width * inter_height
box1_area = (box1[2] - box1[0]) * (box1[3] - box1[1])
# 计算Inner SIoU
inner_siou = inter_area / box1_area
return inner_siou
# 示例使用
box1 = torch.tensor([0., 0., 5., 5.]) # [x1, y1, x2, y2]
box2 = torch.tensor([2., 2., 7., 7.]) # [x3, y3, x4, y4]
inner_siou = calculate_inner_siou(box1, box2)
print(inner_siou.item()) # 打印Inner SIoU值
替换Inner SIoU损失函数(基于MMYOLO)
由于MMYOLO中没有实现Inner SIoU损失函数，所以需要在mmyolo/models/iou_loss.py中添加Inner SIoU的计算和对应的iou_mode，修改完以后在终端运行
python setup.py install再在配置文件中进行修改即可。修改例子如下：
elif iou_mode == "innersiou":
ratio=1.0
w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2
x1 = bbox1_x1 + w1_
y1 = bbox1_y1 + h1_
x2 = bbox2_x1 + w2_
y2 = bbox2_y1 + h2_
inner_b1_x1, inner_b1_x2, inner_b1_y1, inner_b1_y2 = x1 - w1_ * ratio, x1 + w1_ * ratio, \
y1 - h1_ * ratio, y1 + h1_ * ratio
inner_b2_x1, inner_b2_x2, inner_b2_y1, inner_b2_y2 = x2 - w2_ * ratio, x2 + w2_ * ratio, \
y2 - h2_ * ratio, y2 + h2_ * ratio
inner_inter = (torch.min(inner_b1_x2, inner_b2_x2) - torch.max(inner_b1_x1, inner_b2_x1)).clamp(0) * \
(torch.min(inner_b1_y2, inner_b2_y2) - torch.max(inner_b1_y1, inner_b2_y1)).clamp(0)
inner_union = w1 * ratio * h1 * ratio + w2 * ratio * h2 * ratio - inner_inter + eps
inner_iou = inner_inter / inner_union
cw = torch.max(bbox1_x2, bbox2_x2) - torch.min(bbox1_x1, bbox2_x1) # convex width
ch = torch.max(bbox1_y2, bbox2_y2) - torch.min(bbox1_y1, bbox2_y1) # convex height
s_cw = (bbox2_x1 + bbox2_x2 - bbox1_x1 - bbox1_x2) * 0.5 + eps
s_ch = (bbox2_y1 + bbox2_y2 - bbox1_y1 - bbox1_y2) * 0.5 + eps
sigma = torch.pow(s_cw ** 2 + s_ch ** 2, 0.5)
sin_alpha_1 = torch.abs(s_cw) / sigma
sin_alpha_2 = torch.abs(s_ch) / sigma
threshold = pow(2, 0.5) / 2
sin_alpha = torch.where(sin_alpha_1 > threshold, sin_alpha_2, sin_alpha_1)
angle_cost = torch.cos(torch.arcsin(sin_alpha) * 2 - math.pi / 2)
rho_x = (s_cw / cw) ** 2
rho_y = (s_ch / ch) ** 2
gamma = angle_cost - 2
distance_cost = 2 - torch.exp(gamma * rho_x) - torch.exp(gamma * rho_y)
omiga_w = torch.abs(w1 - w2) / torch.max(w1, w2)
omiga_h = torch.abs(h1 - h2) / torch.max(h1, h2)
shape_cost = torch.pow(1 - torch.exp(-1 * omiga_w), 4) + torch.pow(1 - torch.exp(-1 * omiga_h), 4)
ious = inner_iou - 0.5 * (distance_cost + shape_cost)
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='innersiou',
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')
![[华为OD]C卷 机场航班调度 ，XX市机场停放了多架飞机，每架飞机都有自己的航班号100](https://img-blog.csdnimg.cn/direct/35f7096d02d44fe29dfba0756625d85e.png)
