一、YOLOV5下载安装
git clone https://github.com/ultralytics/yolov5.git
conda create -n yolov5 python=3.8 -y
conda activate yolov5
cd yolov5
pip install -r requirements.txt
二、KITTI数据集
1、简介
KITTI数据集是由 Motional 的团队开发的用于自动驾驶的公共大规模数据集。传感器在采集车上的布置如图3所示。数据采集车装配有2个灰度摄像机，2个彩色摄像机，一个Velodyne 64线3D激光雷达，4个光学镜头，以及1个GPS导航系统。
2、下载
地址：http://www.semantic-kitti.org/dataset.html#download
选择我们需要的图片与标签文件，并按照以下的目录结构放入YOLOV5在中,在yolov5/dataset下创建文件夹kitti，kiiti中放入我们的数据；标签数据暂时不放入，后面进行格式转换
|——kitti
├── imgages
│ ├── train
│ │ ├── 00XXXA.png
│ │ └── .......
│ ├── val
│ │ ├── 00XXXB.png
│ │ └── .......
│ └── test
│ └── 00XXXC.png
│ └── .......
│
└── labels
├── train
│ ├── 00XXXA.txt
│ └── .......
├── val
│ ├── 00XXXB.txt
│ └── .......
└── test
├── 00XXXC.txt
└── .......
三、数据集三分类
kitti标签内容：000000.txt
Pedestrian 0.00 0 -0.20 712.40 143.00 810.73 307.92 1.89 0.48 1.20 1.84 1.47 8.41 0.01
yolov5中COCO标签内容： 000000000659.txt
0 0.132172 0.552259 0.118562 0.537176
0 0.249211 0.569659 0.104453 0.456165
0 0.0285469 0.491588 0.0545625 0.312024
0 0.0884609 0.379012 0.0463594 0.112612
6 0.446703 0.554741 0.554625 0.794565
0 0.165211 0.391718 0.0635781 0.0516706
0 0.165625 0.400082 0.0372188 0.130424
0 0.178945 0.354788 0.0235156 0.0436471
26 0.174266 0.664047 0.0525 0.119341
将kitti标签内容转成yolov5需要的标签，转换代码：
1、将原来的8类物体转换为我们现在需要的3类：
{‘Misc’, ‘Cyclist’, ‘Van’, ‘Pedestrian’, ‘Person_sitting’, ‘Truck’, ‘Car’, ‘DontCare’, ‘Tram’}转成{‘Car’, ‘Cyclist’, ‘Pedestrian’}
# modify_annotations_txt.py
import glob
import string
txt_list = glob.glob('H:/dataset/kitti-yolov5/labels/label_2/*.txt') # 存储Labels文件夹所有txt文件路径 注意要保留/*
def show_category(txt_list):
category_list= []
for item in txt_list:
try:
with open(item) as tdf:
for each_line in tdf:
labeldata = each_line.strip().split(' ') # 去掉前后多余的字符并把其分开
category_list.append(labeldata[0]) # 只要第一个字段，即类别
except IOError as ioerr:
print('File error:'+str(ioerr))
print(set(category_list)) # 输出集合
def merge(line):
each_line=''
for i in range(len(line)):
if i!= (len(line)-1):
each_line=each_line+line[i]+' '
else:
each_line=each_line+line[i] # 最后一条字段后面不加空格
each_line=each_line+'\n'
return (each_line)
print('before modify categories are:\n')
show_category(txt_list)
for item in txt_list:
new_txt=[]
try:
with open(item, 'r') as r_tdf:
for each_line in r_tdf:
labeldata = each_line.strip().split(' ')
if labeldata[0] in ['Truck','Van','Tram']: # 合并汽车类
labeldata[0] = labeldata[0].replace(labeldata[0],'Car')
if labeldata[0] == 'Person_sitting': # 合并行人类
labeldata[0] = labeldata[0].replace(labeldata[0],'Pedestrian')
if labeldata[0] == 'DontCare': # 忽略Dontcare类
continue
if labeldata[0] == 'Misc': # 忽略Misc类
continue
new_txt.append(merge(labeldata)) # 重新写入新的txt文件
with open(item,'w+') as w_tdf: # w+是打开原文件将内容删除，另写新内容进去
for temp in new_txt:
w_tdf.write(temp)
except IOError as ioerr:
print('File error:'+str(ioerr))
print('\nafter modify categories are:\n')
show_category(txt_list)
2、将txt文件转换为xml文件
创建一个Annotations文件夹用于存放xml
文件夹结构
|——kitti
├── imgages
│ └── image_2
│ ├── 000001.png
│ └── .......
└── labels
├── label_2
│ ├── 000001.txt
│ └── .......
└── xml
# kitti_txt_to_xml.py
# kitti_txt_to_xml.py
# encoding:utf-8
# 根据一个给定的XML Schema，使用DOM树的形式从空白文件生成一个XML
from xml.dom.minidom import Document
import cv2
import glob
import os
def generate_xml(name,split_lines,img_size,class_ind):
doc = Document() # 创建DOM文档对象
annotation = doc.createElement('annotation')
doc.appendChild(annotation)
title = doc.createElement('folder')
title_text = doc.createTextNode('KITTI')
title.appendChild(title_text)
annotation.appendChild(title)
img_name=name+'.jpg'
title = doc.createElement('filename')
title_text = doc.createTextNode(img_name)
title.appendChild(title_text)
annotation.appendChild(title)
source = doc.createElement('source')
annotation.appendChild(source)
title = doc.createElement('database')
title_text = doc.createTextNode('The KITTI Database')
title.appendChild(title_text)
source.appendChild(title)
title = doc.createElement('annotation')
title_text = doc.createTextNode('KITTI')
title.appendChild(title_text)
source.appendChild(title)
size = doc.createElement('size')
annotation.appendChild(size)
title = doc.createElement('width')
title_text = doc.createTextNode(str(img_size[1]))
title.appendChild(title_text)
size.appendChild(title)
title = doc.createElement('height')
title_text = doc.createTextNode(str(img_size[0]))
title.appendChild(title_text)
size.appendChild(title)
title = doc.createElement('depth')
title_text = doc.createTextNode(str(img_size[2]))
title.appendChild(title_text)
size.appendChild(title)
for split_line in split_lines:
line=split_line.strip().split()
if line[0] in class_ind:
object = doc.createElement('object')
annotation.appendChild(object)
title = doc.createElement('name')
title_text = doc.createTextNode(line[0])
title.appendChild(title_text)
object.appendChild(title)
bndbox = doc.createElement('bndbox')
object.appendChild(bndbox)
title = doc.createElement('xmin')
title_text = doc.createTextNode(str(int(float(line[4]))))
title.appendChild(title_text)
bndbox.appendChild(title)
title = doc.createElement('ymin')
title_text = doc.createTextNode(str(int(float(line[5]))))
title.appendChild(title_text)
bndbox.appendChild(title)
title = doc.createElement('xmax')
title_text = doc.createTextNode(str(int(float(line[6]))))
title.appendChild(title_text)
bndbox.appendChild(title)
title = doc.createElement('ymax')
title_text = doc.createTextNode(str(int(float(line[7]))))
title.appendChild(title_text)
bndbox.appendChild(title)
# 将DOM对象doc写入文件
f = open(r'H:/dataset/kitti-yolov5/labels/xml/'+name+'.xml','w') #（1）生成的xml文件所在路径
f.write(doc.toprettyxml(indent = ''))
f.close()
if __name__ == '__main__':
class_ind=('Pedestrian', 'Car', 'Cyclist')
# cur_dir=os.getcwd()
labels_dir= r"H:\dataset\kitti-yolov5\labels\label_2" #（2）txt文件所在路径
# labels_dir=os.path.join(cur_dir,'label_2')
for parent, dirnames, filenames in os.walk(labels_dir):# 分别得到根目录，子目录和根目录下文件
for file_name in filenames:
full_path=os.path.join(parent, file_name) # 获取文件全路径
f=open(full_path)
split_lines = f.readlines() #以行为单位读
name= file_name[:-4] # 后四位是扩展名.txt，只取前面的文件名
img_name=name+'.png'
img_path=os.path.join('H:\dataset\kitti-yolov5\images\image_2',img_name) # （3）图片所在路径
img_size=cv2.imread(img_path).shape
generate_xml(name,split_lines,img_size,class_ind)
print('txts has converted into xmls')
3、格式的转化与数据集划分
把.xml转化为适合于yolo训练的标签模式，按照8:1:1构造数据集、测试集、验证集;将此文件放置在你的数据集根目录下
|——kitti
├── imgages
│ ├── train
│ │ ├── 00XXXA.png
│ │ └── .......
│ ├── val
│ │ ├── 00XXXB.png
│ │ └── .......
│ └── test
│ └── 00XXXC.png
│ └── .......
│
└── labels
├── train
│ ├── 00XXXA.txt
│ └── .......
├── val
│ ├── 00XXXB.txt
│ └── .......
└── test
├── 00XXXC.txt
└── .......
# xml_to_txt_yolo.py
import xml.etree.ElementTree as ET
import os
import shutil
import random
xml_file_path = 'H:/dataset/kitti-yolov5/labels/xml/' # 检查和自己的xml文件夹名称是否一致
images_file_path = 'H:/dataset/kitti-yolov5/images/image_2/' # 检查和自己的图像文件夹名称是否一致
# 改成自己的类别名称
classes = ['Pedestrian', 'Car', 'Cyclist']
# 数据集划分比例，训练集80%，验证集10%，测试集10%
train_percent = 0.8
val_percent = 0.1
test_percent = 0.1
# 此处不要改动，只是创一个临时文件夹
if not os.path.exists('temp_labels/'):
os.makedirs('temp_labels/')
txt_file_path = 'temp_labels/'
def convert(size, box):
dw = 1. / size[0]
dh = 1. / size[1]
x = (box[0] + box[1]) / 2.0
y = (box[2] + box[3]) / 2.0
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_annotations(image_name):
in_file = open(xml_file_path + image_name + '.xml')
out_file = open(txt_file_path + image_name + '.txt', '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
cls = obj.find('name').text
# if cls not in classes or int(difficult) == 1:
# continue
if cls not in classes == 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))
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
total_xml = os.listdir(xml_file_path)
num_xml = len(total_xml) # XML文件总数
for i in range(num_xml):
name = total_xml[i][:-4]
convert_annotations(name)
# *********************************************** #
# parent folder
# --data
# ----images
# ----train
# ----val
# ----test
# ----labels
# ----train
# ----val
# ----test
def create_dir():
if not os.path.exists('images/'):
os.makedirs('images/')
if not os.path.exists('labels/'):
os.makedirs('labels/')
if not os.path.exists('images/train'):
os.makedirs('images/train')
if not os.path.exists('images/val'):
os.makedirs('images/val')
if not os.path.exists('images/test'):
os.makedirs('images/test/')
if not os.path.exists('labels/train'):
os.makedirs('labels/train')
if not os.path.exists('labels/val'):
os.makedirs('labels/val')
if not os.path.exists('labels/test'):
os.makedirs('labels/test')
return
# *********************************************** #
# 读取所有的txt文件
create_dir()
total_txt = os.listdir(txt_file_path)
num_txt = len(total_txt)
list_all_txt = range(num_txt) # 范围 range(0, num)
num_train = int(num_txt * train_percent)
num_val = int(num_txt * val_percent)
num_test = num_txt - num_train - num_val
train = random.sample(list_all_txt, num_train)
# train从list_all_txt取出num_train个元素
# 所以list_all_txt列表只剩下了这些元素：val_test
val_test = [i for i in list_all_txt if not i in train]
# 再从val_test取出num_val个元素，val_test剩下的元素就是test
val = random.sample(val_test, num_val)
# 检查两个列表元素是否有重合的元素
# set_c = set(val_test) & set(val)
# list_c = list(set_c)
# print(list_c)
# print(len(list_c))
print("训练集数目：{}, 验证集数目：{},测试集数目：{}".format(len(train), len(val), len(val_test) - len(val)))
for i in list_all_txt:
name = total_txt[i][:-4]
srcImage = images_file_path + name + '.png'
srcLabel = txt_file_path + name + '.txt'
if i in train:
dst_train_Image = 'images/train/' + name + '.png'
dst_train_Label = 'labels/train/' + name + '.txt'
shutil.copyfile(srcImage, dst_train_Image)
shutil.copyfile(srcLabel, dst_train_Label)
elif i in val:
dst_val_Image = 'images/val/' + name + '.png'
dst_val_Label = 'labels/val/' + name + '.txt'
shutil.copyfile(srcImage, dst_val_Image)
shutil.copyfile(srcLabel, dst_val_Label)
else:
dst_test_Image = 'images/test/' + name + '.png'
dst_test_Label = 'labels/test/' + name + '.txt'
shutil.copyfile(srcImage, dst_test_Image)
shutil.copyfile(srcLabel, dst_test_Label)
print("complete")
四、数据集五分类
数据集的标注一共分为9个类别：
’Car’，’Van’，’Truck’，‘Tram’，’Pedestrian’，’Person_sitting’，’Cyclist’，’Misc’和’DontCare’。
第1步：在代码中，将’Pedestrian’, ’Person_sitting’合并为’Pedestrian’ ，删除’Misc’和’DontCare’,’Cyclist’
首先我们把类别归一一下，因为我们需要用到5个类（代码中的路径需要修改）
import glob
txt_list = glob.glob('F:/数据集/KITTI-5/labels/*.txt') # 存储Labels文件夹所有txt文件路径
print(txt_list)
def show_category(txt_list):
category_list = []
for item in txt_list:
try:
with open(item) as tdf:
for each_line in tdf:
labeldata = each_line.strip().split(' ') # 去掉前后多余的字符并把其分开
category_list.append(labeldata[0]) # 只要第一个字段，即类别
except IOError as ioerr:
print('File error:' + str(ioerr))
print(set(category_list)) # 输出集合
def merge(line):
each_line = ''
for i in range(len(line)):
if i != (len(line) - 1):
each_line = each_line + line[i] + ' '
else:
each_line = each_line + line[i] # 最后一条字段后面不加空格
each_line = each_line + '\n'
return each_line
print('before modify categories are:\n')
show_category(txt_list)
for item in txt_list:
new_txt = []
try:
with open(item, 'r') as r_tdf:
for each_line in r_tdf:
labeldata = each_line.strip().split(' ')
# if labeldata[0] in ['Truck','Van','Tram']: # 合并汽车类
# labeldata[0] = labeldata[0].replace(labeldata[0],'Car')
if labeldata[0] == 'Person_sitting': # 合并行人类
labeldata[0] = labeldata[0].replace(labeldata[0], 'Pedestrian')
if labeldata[0] in ['DontCare', 'Misc', 'Cyclist']: # 忽略Dontcare, Misc, and Cyclist类
continue
new_txt.append(merge(labeldata)) # 重新写入新的txt文件
with open(item, 'w+') as w_tdf: # w+是打开原文件将内容删除，另写新内容进去
for temp in new_txt:
w_tdf.write(temp)
except IOError as ioerr:
print('File error:' + str(ioerr))
print('\nafter modify categories are:\n')
show_category(txt_list)
效果如下：
第2步：将其转换为xml文件，在Labels目录创建一个xml文件夹存放xml
# kitti_txt_to_xml.py
# encoding:utf-8
# 根据一个给定的XML Schema，使用DOM树的形式从空白文件生成一个XML
from xml.dom.minidom import Document
import cv2
import glob
import os
def generate_xml(name,split_lines,img_size,class_ind):
doc = Document() # 创建DOM文档对象
annotation = doc.createElement('annotation')
doc.appendChild(annotation)
title = doc.createElement('folder')
title_text = doc.createTextNode('KITTI')
title.appendChild(title_text)
annotation.appendChild(title)
img_name=name+'.jpg'
title = doc.createElement('filename')
title_text = doc.createTextNode(img_name)
title.appendChild(title_text)
annotation.appendChild(title)
source = doc.createElement('source')
annotation.appendChild(source)
title = doc.createElement('database')
title_text = doc.createTextNode('The KITTI Database')
title.appendChild(title_text)
source.appendChild(title)
title = doc.createElement('annotation')
title_text = doc.createTextNode('KITTI')
title.appendChild(title_text)
source.appendChild(title)
size = doc.createElement('size')
annotation.appendChild(size)
title = doc.createElement('width')
title_text = doc.createTextNode(str(img_size[1]))
title.appendChild(title_text)
size.appendChild(title)
title = doc.createElement('height')
title_text = doc.createTextNode(str(img_size[0]))
title.appendChild(title_text)
size.appendChild(title)
title = doc.createElement('depth')
title_text = doc.createTextNode(str(img_size[2]))
title.appendChild(title_text)
size.appendChild(title)
for split_line in split_lines:
line=split_line.strip().split()
if line[0] in class_ind:
object = doc.createElement('object')
annotation.appendChild(object)
title = doc.createElement('name')
title_text = doc.createTextNode(line[0])
title.appendChild(title_text)
object.appendChild(title)
bndbox = doc.createElement('bndbox')
object.appendChild(bndbox)
title = doc.createElement('xmin')
title_text = doc.createTextNode(str(int(float(line[4]))))
title.appendChild(title_text)
bndbox.appendChild(title)
title = doc.createElement('ymin')
title_text = doc.createTextNode(str(int(float(line[5]))))
title.appendChild(title_text)
bndbox.appendChild(title)
title = doc.createElement('xmax')
title_text = doc.createTextNode(str(int(float(line[6]))))
title.appendChild(title_text)
bndbox.appendChild(title)
title = doc.createElement('ymax')
title_text = doc.createTextNode(str(int(float(line[7]))))
title.appendChild(title_text)
bndbox.appendChild(title)
# 将DOM对象doc写入文件
f = open('F:/datasets/KITTI-5/xml/'+name+'.xml','w')#xml
f.write(doc.toprettyxml(indent = ''))
f.close()
if __name__ == '__main__':
class_ind=('Car', 'Truck', 'Van', 'Pedestrian', 'Tram')
# cur_dir=os.getcwd()
labels_dir= "F:/datasets/KITTI-5/labels"
# labels_dir=os.path.join(cur_dir,'label_2')
for parent, dirnames, filenames in os.walk(labels_dir):# 分别得到根目录，子目录和根目录下文件
for file_name in filenames:
full_path=os.path.join(parent, file_name) # 获取文件全路径
f=open(full_path)
split_lines = f.readlines() #以行为单位读
name= file_name[:-4] # 后四位是扩展名.txt，只取前面的文件名
img_name=name+'.png'
img_path=os.path.join('F:/datasets/KITTI-5/images',img_name) # 路径需要自行修改
img_size=cv2.imread(img_path).shape
generate_xml(name,split_lines,img_size,class_ind)
print('txts has converted into xmls')
第3步：格式的转化与数据集划分
把.xml转化为适合于yolo训练的标签模式，按照8:1:1构造数据集、测试集、验证集;将此文件放置在你的数据集根目录下
|——kitti
├── imgages
│ ├── train
│ │ ├── 00XXXA.png
│ │ └── .......
│ ├── val
│ │ ├── 00XXXB.png
│ │ └── .......
│ └── test
│ └── 00XXXC.png
│ └── .......
│
└── labels
├── train
│ ├── 00XXXA.txt
│ └── .......
├── val
│ ├── 00XXXB.txt
│ └── .......
└── test
├── 00XXXC.txt
└── .......
# kitti_txt_to_xml.py
# kitti_txt_to_xml.py
# encoding:utf-8
# 根据一个给定的XML Schema，使用DOM树的形式从空白文件生成一个XML
from xml.dom.minidom import Document
import cv2
import glob
import os
def generate_xml(name,split_lines,img_size,class_ind):
doc = Document() # 创建DOM文档对象
annotation = doc.createElement('annotation')
doc.appendChild(annotation)
title = doc.createElement('folder')
title_text = doc.createTextNode('KITTI')
title.appendChild(title_text)
annotation.appendChild(title)
img_name=name+'.jpg'
title = doc.createElement('filename')
title_text = doc.createTextNode(img_name)
title.appendChild(title_text)
annotation.appendChild(title)
source = doc.createElement('source')
annotation.appendChild(source)
title = doc.createElement('database')
title_text = doc.createTextNode('The KITTI Database')
title.appendChild(title_text)
source.appendChild(title)
title = doc.createElement('annotation')
title_text = doc.createTextNode('KITTI')
title.appendChild(title_text)
source.appendChild(title)
size = doc.createElement('size')
annotation.appendChild(size)
title = doc.createElement('width')
title_text = doc.createTextNode(str(img_size[1]))
title.appendChild(title_text)
size.appendChild(title)
title = doc.createElement('height')
title_text = doc.createTextNode(str(img_size[0]))
title.appendChild(title_text)
size.appendChild(title)
title = doc.createElement('depth')
title_text = doc.createTextNode(str(img_size[2]))
title.appendChild(title_text)
size.appendChild(title)
for split_line in split_lines:
line=split_line.strip().split()
if line[0] in class_ind:
object = doc.createElement('object')
annotation.appendChild(object)
title = doc.createElement('name')
title_text = doc.createTextNode(line[0])
title.appendChild(title_text)
object.appendChild(title)
bndbox = doc.createElement('bndbox')
object.appendChild(bndbox)
title = doc.createElement('xmin')
title_text = doc.createTextNode(str(int(float(line[4]))))
title.appendChild(title_text)
bndbox.appendChild(title)
title = doc.createElement('ymin')
title_text = doc.createTextNode(str(int(float(line[5]))))
title.appendChild(title_text)
bndbox.appendChild(title)
title = doc.createElement('xmax')
title_text = doc.createTextNode(str(int(float(line[6]))))
title.appendChild(title_text)
bndbox.appendChild(title)
title = doc.createElement('ymax')
title_text = doc.createTextNode(str(int(float(line[7]))))
title.appendChild(title_text)
bndbox.appendChild(title)
# 将DOM对象doc写入文件
f = open(r'H:/dataset/kitti-yolov5/labels/xml/'+name+'.xml','w') #（1）生成的xml文件所在路径
f.write(doc.toprettyxml(indent = ''))
f.close()
if __name__ == '__main__':
class_ind=('Pedestrian', 'Car', 'Cyclist')
# cur_dir=os.getcwd()
labels_dir= r"H:\dataset\kitti-yolov5\labels\label_2" #（2）txt文件所在路径
# labels_dir=os.path.join(cur_dir,'label_2')
for parent, dirnames, filenames in os.walk(labels_dir):# 分别得到根目录，子目录和根目录下文件
for file_name in filenames:
full_path=os.path.join(parent, file_name) # 获取文件全路径
f=open(full_path)
split_lines = f.readlines() #以行为单位读
name= file_name[:-4] # 后四位是扩展名.txt，只取前面的文件名
img_name=name+'.png'
img_path=os.path.join('H:\dataset\kitti-yolov5\images\image_2',img_name) # （3）图片所在路径
img_size=cv2.imread(img_path).shape
generate_xml(name,split_lines,img_size,class_ind)
print('txts has converted into xmls')
3、格式的转化与数据集划分
把.xml转化为适合于yolo训练的标签模式，按照8:1:1构造数据集、测试集、验证集;将此文件放置在你的数据集根目录下
|——kitti
├── imgages
│ ├── train
│ │ ├── 00XXXA.png
│ │ └── .......
│ ├── val
│ │ ├── 00XXXB.png
│ │ └── .......
│ └── test
│ └── 00XXXC.png
│ └── .......
│
└── labels
├── train
│ ├── 00XXXA.txt
│ └── .......
├── val
│ ├── 00XXXB.txt
│ └── .......
└── test
├── 00XXXC.txt
└── .......
# xml_to_txt_yolo.py
import xml.etree.ElementTree as ET
import os
import shutil
import random
xml_file_path = 'F:/datasets/KITTI-5/xml/' # 检查和自己的xml文件夹名称是否一致
images_file_path = 'F:/datasets/KITTI-5/images_2/' # 检查和自己的图像文件夹名称是否一致
# 改成自己的类别名称
classes = ['Car', 'Truck', 'Van', 'Pedestrian', 'Tram']
# 数据集划分比例，训练集80%，验证集10%，测试集10%
train_percent = 0.8
val_percent = 0.1
test_percent = 0.1
# 此处不要改动，只是创一个临时文件夹
if not os.path.exists('temp_labels/'):
os.makedirs('temp_labels/')
txt_file_path = 'temp_labels/'
def convert(size, box):
dw = 1. / size[0]
dh = 1. / size[1]
x = (box[0] + box[1]) / 2.0
y = (box[2] + box[3]) / 2.0
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_annotations(image_name):
in_file = open(xml_file_path + image_name + '.xml')
out_file = open(txt_file_path + image_name + '.txt', '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
cls = obj.find('name').text
# if cls not in classes or int(difficult) == 1:
# continue
if cls not in classes == 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))
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
total_xml = os.listdir(xml_file_path)
num_xml = len(total_xml) # XML文件总数
for i in range(num_xml):
name = total_xml[i][:-4]
convert_annotations(name)
# *********************************************** #
# parent folder
# --data
# ----images
# ----train
# ----val
# ----test
# ----labels
# ----train
# ----val
# ----test
def create_dir():
if not os.path.exists('images/'):
os.makedirs('images/')
if not os.path.exists('labels/'):
os.makedirs('labels/')
if not os.path.exists('images/train'):
os.makedirs('images/train')
if not os.path.exists('images/val'):
os.makedirs('images/val')
if not os.path.exists('images/test'):
os.makedirs('images/test/')
if not os.path.exists('labels/train'):
os.makedirs('labels/train')
if not os.path.exists('labels/val'):
os.makedirs('labels/val')
if not os.path.exists('labels/test'):
os.makedirs('labels/test')
return
# *********************************************** #
# 读取所有的txt文件
create_dir()
total_txt = os.listdir(txt_file_path)
num_txt = len(total_txt)
list_all_txt = range(num_txt) # 范围 range(0, num)
num_train = int(num_txt * train_percent)
num_val = int(num_txt * val_percent)
num_test = num_txt - num_train - num_val
train = random.sample(list_all_txt, num_train)
# train从list_all_txt取出num_train个元素
# 所以list_all_txt列表只剩下了这些元素：val_test
val_test = [i for i in list_all_txt if not i in train]
# 再从val_test取出num_val个元素，val_test剩下的元素就是test
val = random.sample(val_test, num_val)
# 检查两个列表元素是否有重合的元素
# set_c = set(val_test) & set(val)
# list_c = list(set_c)
# print(list_c)
# print(len(list_c))
print("训练集数目：{}, 验证集数目：{},测试集数目：{}".format(len(train), len(val), len(val_test) - len(val)))
for i in list_all_txt:
name = total_txt[i][:-4]
srcImage = images_file_path + name + '.png'
srcLabel = txt_file_path + name + '.txt'
if i in train:
dst_train_Image = 'images/train/' + name + '.png'
dst_train_Label = 'labels/train/' + name + '.txt'
shutil.copyfile(srcImage, dst_train_Image)
shutil.copyfile(srcLabel, dst_train_Label)
elif i in val:
dst_val_Image = 'images/val/' + name + '.png'
dst_val_Label = 'labels/val/' + name + '.txt'
shutil.copyfile(srcImage, dst_val_Image)
shutil.copyfile(srcLabel, dst_val_Label)
else:
dst_test_Image = 'images/test/' + name + '.png'
dst_test_Label = 'labels/test/' + name + '.txt'
shutil.copyfile(srcImage, dst_test_Image)
shutil.copyfile(srcLabel, dst_test_Label)
print("complete")
效果如下：
五、修改配置文件
1、修改数据集配置文件
将data目录下的coco128.yaml复制一份修改为kitti.yaml；修改内容如下：
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
#path: ../dataset/kitti # dataset root dir
train: /home/mengwen/yolov5/dataset/kitti/images/train # train images (relative to 'path') 128 images
val: /home/mengwen/yolov5/dataset/kitti/images/val # val images (relative to 'path') 128 images
test: /home/mengwen/yolov5/dataset/kitti/images/test # test images (optional)
# Classes
names:
0: Pedestrian
1: Car
2: Cyclist
# Download script/URL (optional)
#download: https://ultralytics.com/assets/coco128.zip
2、修改models配置文件
修改nc（类别数量)
# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
# Parameters
nc: 3 # 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
3、修改训练文件train.py
def parse_opt(known=False):
"""Parses command-line arguments for YOLOv5 training, validation, and testing."""
parser = argparse.ArgumentParser()
parser.add_argument("--weights", type=str, default=ROOT / "yolov5s.pt", help="initial weights path")
parser.add_argument("--cfg", type=str, default="models/yolov5s.yaml", help="model.yaml path")
parser.add_argument("--data", type=str, default=ROOT / "data/kitti.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(
"--evolve_population", type=str, default=ROOT / "data/hyps", help="location for loading population"
)
epochs： 指的就是训练过程中整个数据集将被迭代多少次,显卡不行你就调小点。
batch-size： 一次看完多少张图片才进行权重更新，梯度下降的mini-batch,显卡不行你就调小点。
cfg： 存储模型结构的配置文件
data： 存储训练、测试数据的文件
img-size： 输入图片宽高,显卡不行你就调小点。
rect： 进行矩形训练
resume： 恢复最近保存的模型开始训练
nosave： 仅保存最终checkpoint
notest： 仅测试最后的epoch
evolve： 进化超参数
bucket： gsutil bucket
cache-images： 缓存图像以加快训练速度
weights： 权重文件路径
name： 重命名results.txt to results_name.txt
device： cuda device, i.e. 0 or 0,1,2,3 or cpu
adam： 使用adam优化
multi-scale： 多尺度训练，img-size +/- 50%
single-cls： 单类别的训练集
六、训练
1、训练指令
python train.py --img 640 --batch 16 --epoch 100 --data data/kitti.yaml --cfg models/yolov5s.yaml --weights yolov5s.pt --device '0'
2、效果
1）结果统计
2）val_batch0_labels
七、测试
1、修改detect.py
@smart_inference_mode()
def run(
weights=ROOT / "runs/train/exp4/weights/best.pt", # model path or triton URL
source=ROOT / "classify/data/videos", # file/dir/URL/glob/screen/0(webcam)
data=ROOT / "data/kitti.yaml", # dataset.yaml path
imgsz=(640, 640), # inference size (height, width)
conf_thres=0.25, # confidence threshold
iou_thres=0.45, # NMS IOU threshold
max_det=1000, # maximum detections per image
device="", # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=False, # show results
save_txt=False, # save results to *.txt
save_csv=False, # save results in CSV format
save_conf=False, # save confidences in --save-txt labels
save_crop=False, # save cropped prediction boxes
nosave=False, # do not save images/videos
classes=None, # filter by class: --class 0, or --class 0 2 3
agnostic_nms=False, # class-agnostic NMS
augment=False, # augmented inference
visualize=False, # visualize features
update=False, # update all models
project=ROOT / "runs/detect", # save results to project/name
name="exp", # save results to project/name
exist_ok=False, # existing project/name ok, do not increment
line_thickness=3, # bounding box thickness (pixels)
hide_labels=False, # hide labels
hide_conf=False, # hide confidences
half=False, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for ONNX inference
vid_stride=1, # video frame-rate stride
):
...
def parse_opt():
"""Parses command-line arguments for YOLOv5 detection, setting inference options and model configurations."""
parser = argparse.ArgumentParser()
parser.add_argument("--weights", nargs="+", type=str, default=ROOT / "runs/train/exp4/weights/best.pt", help="model path or triton URL")
parser.add_argument("--source", type=str, default=ROOT / "/home/mengwen/yolov5/classify/data/videos", help="file/dir/URL/glob/screen/0(webcam)")
parser.add_argument("--data", type=str, default=ROOT / "data/kitti.yaml", help="(optional) dataset.yaml path")
parser.add_argument("--imgsz", "--img", "--img-size", nargs="+", type=int, default=[640], help="inference size h,w")
parser.add_argument("--conf-thres", type=float, default=0.25, help="confidence threshold")
parser.add_argument("--iou-thres", type=float, default=0.45, help="NMS IoU threshold")
parser.add_argument("--max-det", type=int, default=1000, help="maximum detections per image")
parser.add_argument("--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu")
parser.add_argument("--view-img", action="store_true", help="show results")
parser.add_argument("--save-txt", action="store_true", help="save results to *.txt")
parser.add_argument("--save-csv", action="store_true", help="save results in CSV format")
parser.add_argument("--save-conf", action="store_true", help="save confidences in --save-txt labels")
parser.add_argument("--save-crop", action="store_true", help="save cropped prediction boxes")
parser.add_argument("--nosave", action="store_true", help="do not save images/videos")
parser.add_argument("--classes", nargs="+", type=int, help="filter by class: --classes 0, or --classes 0 2 3")
parser.add_argument("--agnostic-nms", action="store_true", help="class-agnostic NMS")
parser.add_argument("--augment", action="store_true", help="augmented inference")
parser.add_argument("--visualize", action="store_true", help="visualize features")
parser.add_argument("--update", action="store_true", help="update all models")
parser.add_argument("--project", default=ROOT / "runs/detect", help="save results to project/name")
parser.add_argument("--name", default="exp", help="save results to project/name")
parser.add_argument("--exist-ok", action="store_true", help="existing project/name ok, do not increment")
parser.add_argument("--line-thickness", default=3, type=int, help="bounding box thickness (pixels)")
parser.add_argument("--hide-labels", default=False, action="store_true", help="hide labels")
parser.add_argument("--hide-conf", default=False, action="store_true", help="hide confidences")
parser.add_argument("--half", action="store_true", help="use FP16 half-precision inference")
parser.add_argument("--dnn", action="store_true", help="use OpenCV DNN for ONNX inference")
parser.add_argument("--vid-stride", type=int, default=1, help="video frame-rate stride")
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
print_args(vars(opt))
return opt
2、视频效果
1）视频截取：
import numpy as np
import cv2
import os
import time
START_HOUR = 0
START_MIN = 0
START_SECOND = 36
START_TIME = START_HOUR * 3600 + START_MIN * 60 + START_SECOND # 设置开始时间(单位秒)
END_HOUR = 0
END_MIN = 0
END_SECOND = 50
END_TIME = END_HOUR * 3600 + END_MIN * 60 + END_SECOND # 设置结束时间(单位秒)
video = "E:/044_2M_20230306_172207_ningxia_yinchuan_0B_0_5.mp4"
cap = cv2.VideoCapture(video)
FPS = cap.get(cv2.CAP_PROP_FPS)
print(FPS)
FPS = 10
# size = (cap.get(cv2.CAP_PROP_FRAME_WIDTH), cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
size = (1920,1080)
print(size)
TOTAL_FRAME = int(cap.get(cv2.CAP_PROP_FRAME_COUNT)) # 获取视频总帧数
frameToStart = START_TIME * FPS # 开始帧 = 开始时间*帧率
print(frameToStart)
frametoStop = END_TIME * FPS # 结束帧 = 结束时间*帧率
print(frametoStop)
videoWriter =cv2.VideoWriter('E:/video/video1.avi',cv2.VideoWriter_fourcc('X','V','I','D'),FPS,size)
# cap.set(cv2.CAP_PROP_POS_FRAMES, frameToStart) # 设置读取的位置,从第几帧开始读取视频
COUNT = 0
while True:
success, frame = cap.read()
if success:
COUNT += 1
if COUNT <= frametoStop and COUNT > frameToStart: # 选取起始帧
print('correct= ', COUNT)
videoWriter.write(frame)
# print('mistake= ', COUNT)
if COUNT > frametoStop:
break
print('end')
2）效果
video1
1万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
