目录
1.1.1 通过split_train_val.py得到trainval.txt、val.txt、test.txt
1.1.2 通过voc_label.py得到适合yolov5训练需要的
1.数据集介绍
缺陷类型：crack
数据集数量：195张
1.1数据增强，扩充数据集
通过medianBlur、GaussianBlur、Blur3倍扩充得到780张图片
按照train、val、test进行8:1：1进行划分
1.1.1 通过split_train_val.py得到trainval.txt、val.txt、test.txt
# coding:utf-8
import os
import random
import argparse
parser = argparse.ArgumentParser()
#xml文件的地址，根据自己的数据进行修改 xml一般存放在Annotations下
parser.add_argument('--xml_path', default='Annotations', type=str, help='input xml label path')
#数据集的划分，地址选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='ImageSets/Main', type=str, help='output txt label path')
opt = parser.parse_args()
trainval_percent = 0.9
train_percent = 0.8
xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)
if not os.path.exists(txtsavepath):
os.makedirs(txtsavepath)
num = len(total_xml)
list_index = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list_index, tv)
train = random.sample(trainval, tr)
file_trainval = open(txtsavepath + '/trainval.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')
for i in list_index:
name = total_xml[i][:-4] + '\n'
if i in trainval:
file_trainval.write(name)
if i in train:
file_train.write(name)
else:
file_val.write(name)
else:
file_test.write(name)
file_trainval.close()
file_train.close()
file_val.close()
file_test.close()1.1.2 通过voc_label.py得到适合yolov5训练需要的
# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
from os import getcwd
sets = ['train', 'val']
classes = ["crack"] # 改成自己的类别
abs_path = os.getcwd()
print(abs_path)
def convert(size, box):
dw = 1. / (size[0])
dh = 1. / (size[1])
x = (box[0] + box[1]) / 2.0 - 1
y = (box[2] + box[3]) / 2.0 - 1
w = box[1] - box[0]
h = box[3] - box[2]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
return x, y, w, h
def convert_annotation(image_id):
in_file = open('Annotations/%s.xml' % (image_id), encoding='UTF-8')
out_file = open('labels/%s.txt' % (image_id), 'w')
tree = ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
#difficult = obj.find('Difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
float(xmlbox.find('ymax').text))
b1, b2, b3, b4 = b
# 标注越界修正
if b2 > w:
b2 = w
if b4 > h:
b4 = h
b = (b1, b2, b3, b4)
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
wd = getcwd()
for image_set in sets:
if not os.path.exists('labels/'):
os.makedirs('labels/')
image_ids = open('ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
list_file = open('%s.txt' % (image_set), 'w')
for image_id in image_ids:
list_file.write(abs_path + '/images/%s.jpg\n' % (image_id))
convert_annotation(image_id)
list_file.close()2.基于yolov5的道路缺陷识别
2.1配置 crack.yaml
train: ./data/crack/train.txt
val: ./data/crack/val.txt
# number of classes
nc: 1
# class names
names: ["crack"]2.2 修改yolov5s_crack.yaml
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Parameters
nc: 1 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
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
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
2.3训练道路缺陷模型
配置train.py超参数
def parse_opt(known=False):
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default=ROOT / 'weights/yolov5s.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default='models/yolov5s_crack.yaml', help='model.yaml path')
parser.add_argument('--data', type=str, default=ROOT / 'data/crack.yaml', help='dataset.yaml path')
parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-low.yaml', help='hyperparameters path')
parser.add_argument('--epochs', type=int, default=100, help='total training epochs')
parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs, -1 for autobatch')
parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
parser.add_argument('--rect', action='store_true', help='rectangular training')
parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
parser.add_argument('--noval', action='store_true', help='only validate final epoch')
parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor')
parser.add_argument('--noplots', action='store_true', help='save no plot files')
parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
parser.add_argument('--cache', type=str, nargs='?', const='ram', help='image --cache ram/disk')
parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
parser.add_argument('--device', default='2', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
parser.add_argument('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW'], default='SGD', help='optimizer')
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
parser.add_argument('--workers', type=int, default=0, help='max dataloader workers (per RANK in DDP mode)')
parser.add_argument('--project', default=ROOT / 'runs/train_crack', help='save to project/name')
parser.add_argument('--name', default='exp', help='save to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
parser.add_argument('--quad', action='store_true', help='quad dataloader')
parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler')
parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)')
parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2')
parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
parser.add_argument('--seed', type=int, default=0, help='Global training seed')
parser.add_argument('--local_rank', type=int, default=-1, help='Automatic DDP Multi-GPU argument, do not modify')开启python train.py
3.性能评价
原始map 0.954
3.1 加入ASFF特征金字塔融合
博客地址：https://blog.csdn.net/m0_63774211/article/details/129619356
map 从0.954上升到0.973
3.2 ECVBlock
基于YoloV5 ECVBlock的小目标检测（CFPNet即插即用，助力检测涨点，YOLOv7/YOLOv5均有效)_AI&CV的博客-CSDN博客
EVC在道路缺陷crack提升效果不明显
3.3 解耦头Decoupled_Detect
涨点技巧：Detect系列---Yolov5/Yolov7加入解耦头Decoupled_Detect，涨点明显_AI&CV的博客-CSDN博客
map 从0.954上升到0.962
3.4 GSConv+Slim Neck
涨点神器：Yolov5引入GSConv+Slim Neck，提升小目标检测精度_AI&CV的博客-CSDN博客
3.4.1 slimneck-yolov5s.yaml
map 从0.954上升到0.961
3.4.2 GSConv-yolov5s.yaml
map 从0.954上升到0.966
3.4.2 yolov5s_InceptionDWConv2d.yaml
https://cv2023.blog.csdn.net/article/details/129946896?spm=1001.2014.3001.5502
map 从0.954上升到0.967
depth=2，map 从0.954上升到0.974
3.5 WIoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism
https://cv2023.blog.csdn.net/article/details/130198660?spm=1001.2014.3001.5502
map 从0.954上升到0.968
3.6 TSCODE解耦头
https://cv2023.blog.csdn.net/article/details/130267277?spm=1001.2014.3001.5502
map 从0.954上升到0.976
3.7 困难样本挖掘 Loss Rank Mining
https://cv2023.blog.csdn.net/article/details/130343340
map 从0.954上升到0.982
3.8 自注意机制MobileViTAttention
https://cv2023.blog.csdn.net/article/details/130898507
原始map 0.954提升至0.982
3.9 VanillaBlock 华为诺亚提出VanillaNet2023
https://cv2023.blog.csdn.net/article/details/130900471
map 0.954提升至 0.979
258
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
