【YOLO改进】换遍IoU损失函数之Innerciou Loss(基于MMYOLO)

2024-05-04 19:36

本文主要是介绍【YOLO改进】换遍IoU损失函数之Innerciou Loss(基于MMYOLO),希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!

替换Inner CIoU损失函数(基于MMYOLO)

由于MMYOLO中没有实现Inner CIoU损失函数,所以需要在mmyolo/models/iou_loss.py中添加Inner CIoU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 == "innerciou":ratio=1.0w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2x1 = 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_ * ratioinner_b2_x1, inner_b2_x2, inner_b2_y1, inner_b2_y2 = x2 - w2_ * ratio, x2 + w2_ * ratio, \y2 - h2_ * ratio, y2 + h2_ * ratioinner_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 + epsinner_iou = inner_inter / inner_union# 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 / 4rho2_right_item = ((bbox2_y1 + bbox2_y2) -(bbox1_y1 + bbox1_y2))**2 / 4rho2 = rho2_left_item + rho2_right_item  # rho^2 (ρ^2)# Width and height ratio (v)wh_ratio = (4 / (math.pi**2)) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)with torch.no_grad():alpha = wh_ratio / (wh_ratio - ious + (1 + eps))# innerCIoUious = inner_iou - ((rho2 / enclose_area) + (alpha * wh_ratio))

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='innerciou',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')

这篇关于【YOLO改进】换遍IoU损失函数之Innerciou Loss(基于MMYOLO)的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!



http://www.chinasem.cn/article/959954

相关文章

Python的time模块一些常用功能(各种与时间相关的函数)

《Python的time模块一些常用功能(各种与时间相关的函数)》Python的time模块提供了各种与时间相关的函数,包括获取当前时间、处理时间间隔、执行时间测量等,:本文主要介绍Python的... 目录1. 获取当前时间2. 时间格式化3. 延时执行4. 时间戳运算5. 计算代码执行时间6. 转换为指

Python正则表达式语法及re模块中的常用函数详解

《Python正则表达式语法及re模块中的常用函数详解》这篇文章主要给大家介绍了关于Python正则表达式语法及re模块中常用函数的相关资料,正则表达式是一种强大的字符串处理工具,可以用于匹配、切分、... 目录概念、作用和步骤语法re模块中的常用函数总结 概念、作用和步骤概念: 本身也是一个字符串,其中

shell编程之函数与数组的使用详解

《shell编程之函数与数组的使用详解》:本文主要介绍shell编程之函数与数组的使用,具有很好的参考价值,希望对大家有所帮助,如有错误或未考虑完全的地方,望不吝赐教... 目录shell函数函数的用法俩个数求和系统资源监控并报警函数函数变量的作用范围函数的参数递归函数shell数组获取数组的长度读取某下的

MySQL高级查询之JOIN、子查询、窗口函数实际案例

《MySQL高级查询之JOIN、子查询、窗口函数实际案例》:本文主要介绍MySQL高级查询之JOIN、子查询、窗口函数实际案例的相关资料,JOIN用于多表关联查询,子查询用于数据筛选和过滤,窗口函... 目录前言1. JOIN(连接查询)1.1 内连接(INNER JOIN)1.2 左连接(LEFT JOI

MySQL中FIND_IN_SET函数与INSTR函数用法解析

《MySQL中FIND_IN_SET函数与INSTR函数用法解析》:本文主要介绍MySQL中FIND_IN_SET函数与INSTR函数用法解析,本文通过实例代码给大家介绍的非常详细,感兴趣的朋友一... 目录一、功能定义与语法1、FIND_IN_SET函数2、INSTR函数二、本质区别对比三、实际场景案例分

C++ Sort函数使用场景分析

《C++Sort函数使用场景分析》sort函数是algorithm库下的一个函数,sort函数是不稳定的,即大小相同的元素在排序后相对顺序可能发生改变,如果某些场景需要保持相同元素间的相对顺序,可使... 目录C++ Sort函数详解一、sort函数调用的两种方式二、sort函数使用场景三、sort函数排序

C语言函数递归实际应用举例详解

《C语言函数递归实际应用举例详解》程序调用自身的编程技巧称为递归,递归做为一种算法在程序设计语言中广泛应用,:本文主要介绍C语言函数递归实际应用举例的相关资料,文中通过代码介绍的非常详细,需要的朋... 目录前言一、递归的概念与思想二、递归的限制条件 三、递归的实际应用举例(一)求 n 的阶乘(二)顺序打印

C/C++错误信息处理的常见方法及函数

《C/C++错误信息处理的常见方法及函数》C/C++是两种广泛使用的编程语言,特别是在系统编程、嵌入式开发以及高性能计算领域,:本文主要介绍C/C++错误信息处理的常见方法及函数,文中通过代码介绍... 目录前言1. errno 和 perror()示例:2. strerror()示例:3. perror(

Kotlin 作用域函数apply、let、run、with、also使用指南

《Kotlin作用域函数apply、let、run、with、also使用指南》在Kotlin开发中,作用域函数(ScopeFunctions)是一组能让代码更简洁、更函数式的高阶函数,本文将... 目录一、引言:为什么需要作用域函数?二、作用域函China编程数详解1. apply:对象配置的 “流式构建器”最

Android Kotlin 高阶函数详解及其在协程中的应用小结

《AndroidKotlin高阶函数详解及其在协程中的应用小结》高阶函数是Kotlin中的一个重要特性,它能够将函数作为一等公民(First-ClassCitizen),使得代码更加简洁、灵活和可... 目录1. 引言2. 什么是高阶函数?3. 高阶函数的基础用法3.1 传递函数作为参数3.2 Lambda