【YOLO改进】换遍IoU损失函数之EIoU Loss（基于MMYOLO）

最新推荐文章于 2024-05-15 19:01:29 发布

五山一胖

最新推荐文章于 2024-05-15 19:01:29 发布

阅读量1.2k

点赞数 17

分类专栏： YOLO改进文章标签： YOLO

本文链接：https://blog.csdn.net/vlone_pp/article/details/138365883

版权

YOLO改进专栏收录该内容

38 篇文章 9 订阅

订阅专栏

本文介绍了EIoU损失函数，一种改进的IoU（IntersectionoverUnion）方法，它在评估目标检测模型时解决了IoU仅关注重叠部分的问题，考虑了中心点距离和边界框尺寸的相对差异。文章详细阐述了EIoU的计算步骤，并给出了在PyTorch中的实现示例，以及如何将其应用于MMYOLO模型中进行配置调整。

摘要由CSDN通过智能技术生成

EIoU损失函数

设计原理

一、IoU的局限性

IoU（Intersection over Union）是一种常用于评估目标检测模型性能的指标，特别是在计算预测边界框与真实边界框之间的重叠程度时。然而，IoU存在一些局限性，尤其是当两个边界框没有任何交集时，IoU 的值为0，这使得梯度更新停滞，不利于模型的进一步学习和优化。

二、EIoU的引入

为了解决这一问题，引入了EIoU（Enhanced Intersection over Union）损失函数。EIoU 不仅考虑了边界框间的重叠区域，还引入了其他度量，如边界框中心点的距离，以及边界框的宽度和高度的相对差异。这样的设计使得即使两个边界框不重叠，损失函数仍然可以提供有效的梯度，从而促进模型的训练和收敛。

计算步骤

一、计算IoU

计算两个边界框A和B的交集面积I。
计算两个边界框的并集面积U。
IoU计算公式为：I/U

二、计算中心点距离的公式

中心点距离是预测框和真实框中心点之间的欧氏距离。设预测框中心为 $(x_p,y_p)$ ，真实框中心为 $(x_g,y_g)$ ，则中心距离 $D_c$ 计算为：

$D_c = \sqrt{(x_p - x_g)^2 + (y_p - y_g)^2}$

三、计算宽高比的差异

宽度差异 $w_{diff}$ 和高度差异 $h_{diff}$ 分别为预测框和真实框宽度和高度的相对差值。计算方法可以是简单的差值或者比例差等。

四、整合以上度量

EIoU将上述度量整合到一个损失函数中，通常形式为：

$\text{EIoU Loss} = 1 - \text{IoU} + \lambda_1 D_c + \lambda_2 (w_{\text{diff}} + h_{\text{diff}})$

其中， $\lambda_1$ 和 $\lambda_2$ 是调节中心距离和宽高差异影响的超参数。

使用PyTorch实现EIoU计算的源代码

import torch
import torch.nn.functional as F

def bbox_iou(boxes1, boxes2):
    """
    计算两组边界框的IoU。
    boxes1, boxes2: [N, 4] (x1, y1, x2, y2)
    """
    area1 = (boxes1[:, 2] - boxes1[:, 0]) * (boxes1[:, 3] - boxes1[:, 1])
    area2 = (boxes2[:, 2] - boxes2[:, 0]) * (boxes2[:, 3] - boxes2[:, 1])

    inter_x1 = torch.max(boxes1[:, 0], boxes2[:, 0])
    inter_y1 = torch.max(boxes1[:, 1], boxes2[:, 1])
    inter_x2 = torch.min(boxes1[:, 2], boxes2[:, 2])
    inter_y2 = torch.min(boxes1[:, 3], boxes2[:, 3])

    inter_area = torch.clamp(inter_x2 - inter_x1, min=0) * torch.clamp(inter_y2 - inter_y1, min=0)
    union_area = area1 + area2 - inter_area

    return inter_area / union_area

def eiou_loss(pred_boxes, target_boxes, lambda1=1, lambda2=1):
    """
    计算EIoU损失。
    pred_boxes, target_boxes: [N, 4] (x1, y1, x2, y2)
    """
    iou = bbox_iou(pred_boxes, target_boxes)

    # 计算中心点
    center_pred = (pred_boxes[:, :2] + pred_boxes[:, 2:4]) / 2
    center_target = (target_boxes[:, :2] + target_boxes[:, 2:4]) / 2

    # 计算中心点距离
    dc = torch.sqrt(torch.sum((center_pred - center_target) ** 2, dim=1))

    # 计算宽高差异
    wh_pred = pred_boxes[:, 2:4] - pred_boxes[:, :2]
    wh_target = target_boxes[:, 2:4] - target_boxes[:, :2]
    wh_diff = torch.abs(wh_pred - wh_target).sum(dim=1)

    # 计算EIoU损失
    loss = 1 - iou + lambda1 * dc + lambda2 * wh_diff
    return loss.mean()

# 示例用法
pred_boxes = torch.tensor([[25, 25, 75, 75], [50, 50, 100, 100]], dtype=torch.float32)
target_boxes = torch.tensor([[30, 30, 70, 70], [70, 70, 120, 120]], dtype=torch.float32)

loss = eiou_loss(pred_boxes, target_boxes)
print(f"EIoU Loss: {loss}")

替换EIoU损失函数(基于MMYOLO)

由于MMYOLO中没有实现EIoU损失函数，所以需要在mmyolo/models/iou_loss.py中添加EIoU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 == "eiou":

        # CIoU = IoU - ( (ρ^2(b_pred,b_gt) / c^2) + (alpha x v) )

        # calculate enclose area (c^2)
        enclose_area = enclose_w**2 + enclose_h**2 + eps

        # calculate ρ^2(b_pred,b_gt):
        # euclidean distance between b_pred(bbox2) and b_gt(bbox1)
        # center point, because bbox format is xyxy -> left-top xy and
        # right-bottom xy, so need to / 4 to get center point.
        rho2_left_item = ((bbox2_x1 + bbox2_x2) - (bbox1_x1 + bbox1_x2))**2 / 4
        rho2_right_item = ((bbox2_y1 + bbox2_y2) -
                           (bbox1_y1 + bbox1_y2))**2 / 4
        rho2 = rho2_left_item + rho2_right_item  # rho^2 (ρ^2)
        rho_w2 = ((bbox2_x2 - bbox2_x1) - (bbox1_x2 - bbox1_x1)) ** 2
        rho_h2 = ((bbox2_y2 - bbox2_y1) - (bbox1_y2 - bbox1_y1)) ** 2
        cw2 = enclose_w ** 2 + eps
        ch2 = enclose_h ** 2 + eps
        ious = ious - (rho2 / enclose_area + rho_w2 / cw2 + rho_h2 / ch2)

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='eiou',
            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')