【YOLO改进】换遍IoU损失函数之SIoU Loss（基于MMYOLO）

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 $(x_p,y_p)$ ，真实框中心为 $(x_g,y_g)$ 。
- 中心点距离 D 可以使用欧氏距离计算： $D = \sqrt{(x_p - x_g)^2 + (y_p - y_g)^2}$
长宽比和角度误差：
- 计算预测框和真实框的长宽比 $r_p$ 和 $r_g$ 。
- 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

import torch
import torch.nn as nnclass 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_lossreturn 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GIoU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 pathnum_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 epochsmodel_test_cfg = dict(# The config of multi-label for multi-class prediction.multi_label=True,# The number of boxes before NMSnms_pre=30000,score_thr=0.001,  # Threshold to filter out boxes.nms=dict(type='nms', iou_threshold=0.65),  # NMS type and thresholdmax_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_divisorsize_divisor=32,# Additional paddings for pixel scaleextra_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 layersloss_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_dataloaderparam_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_evaluatortrain_cfg = dict(type='EpochBasedTrainLoop',max_epochs=max_epochs,val_interval=save_checkpoint_intervals)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')