ViewCategory.py
查看class具体内容代码如下。
# import os
# from unicodedata import name
# import xml.etree.ElementTree as ET
# import glob
#
#
# def count_num(indir):
# label_list = []
# # 提取xml文件列表
# os.chdir(indir)
# annotations = os.listdir('.')
# annotations = glob.glob(str(annotations) + '*.xml')
#
# dict = {} # 新建字典,用于存放各类标签名及其对应的数目
# for i, file in enumerate(annotations): # 遍历xml文件
#
# # actual parsing
# in_file = open(file, encoding='utf-8')
# tree = ET.parse(in_file)
# root = tree.getroot()
#
# # 遍历文件的所有标签
# for obj in root.iter('object'):
# name = obj.find('name').text
# if (name in dict.keys()):
# dict[name] += 1 # 如果标签不是第一次出现,则+1
# else:
# dict[name] = 1 # 如果标签是第一次出现,则将该标签名对应的value初始化为1
#
# # 打印结果
# print("各类标签的数量分别为:")
# for key in dict.keys():
# print(key + ': ' + str(dict[key]))
# label_list.append(key)
# print("标签类别如下:")
# print(label_list)
#
#
# if __name__ == '__main__':
# # xml文件所在的目录,修改此处
# indir = 'data/Annotations'
# count_num(indir) # 调用函数统计各类标签数目
import os
from unicodedata import name
import xml.etree.ElementTree as ET
import glob
def count_num(indir):
label_list = []
# 提取xml文件列表
os.chdir(indir)
annotations = os.listdir('.')
annotations = glob.glob(str(annotations) + '*.xml')
dict = {} # 新建字典,用于存放各类标签名及其对应的数目
for i, file in enumerate(annotations): # 遍历xml文件
# actual parsing
in_file = open(file, encoding='utf-8')
tree = ET.parse(in_file)
root = tree.getroot()
# 遍历文件的所有标签
for obj in root.iter('object'):
name = obj.find('action').text
if (name in dict.keys()):
dict[name] += 1 # 如果标签不是第一次出现,则+1
else:
dict[name] = 1 # 如果标签是第一次出现,则将该标签名对应的value初始化为1
# 打印结果
print("各类标签的数量分别为:")
for key in dict.keys():
print(key + ': ' + str(dict[key]))
label_list.append(key)
print("标签类别如下:")
print(label_list)
if __name__ == '__main__':
# xml文件所在的目录,修改此处
indir = 'datasets/Annotations'
count_num(indir) # 调用函数统计各类标签数目
splitDataset.py
import os
import random
trainval_percent = 0.8 # 训练集与验证集占全体数据的比例
train_percent = 0.75 # 训练集占训练集与验证集总体的比例
xmlfilepath = 'datasets/Annotations'
txtsavepath = 'datasets/ImageSets'
total_xml = os.listdir(xmlfilepath)
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
ftrainval = open('datasets/ImageSets/trainval.txt', 'w')
ftest = open('datasets/ImageSets/test.txt', 'w')
ftrain = open('datasets/ImageSets/train.txt', 'w')
fval = open('datasets/ImageSets/val.txt', 'w')
for i in list:
name = total_xml[i][:-4] + '\n'
if i in trainval:
ftrainval.write(name)
if i in train:
ftrain.write(name)
else:
fval.write(name)
else:
ftest.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()
XML-YOLO.py
XML格式转TXT格式如下代码所示。
需要改动的:
# 定义类别和其对应的标签
# 定义输入输出路径
输入输出路径要已经创建相应的文件夹,不然会报错。
# -*- coding: utf-8 -*-
# xml解析包
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets = ['train', 'test', 'val']
# classes = ['KENAN','XINYI','XIAOLAN','AI']
classes = ['applauding', 'blowing_bubbles', 'brushing_teeth', 'cleaning_the_floor', 'climbing', 'cooking', 'cutting_trees', 'cutting_vegetables', 'drinking', 'feeding_a_horse', 'fishing', 'fixing_a_bike', 'fixing_a_car', 'gardening', 'holding_an_umbrella', 'jumping', 'looking_through_a_microscope', 'looking_through_a_telescope', 'phoning', 'playing_guitar', 'playing_violin', 'pouring_liquid', 'pushing_a_cart', 'reading', 'riding_a_bike', 'riding_a_horse', 'rowing_a_boat', 'running', 'shooting_an_arrow', 'smoking', 'taking_photos', 'texting_message', 'throwing_frisby', 'using_a_computer', 'walking_the_dog', 'washing_dishes', 'watching_TV', 'waving_hands', 'writing_on_a_board', 'writing_on_a_book']
# 进行归一化操作
def convert(size, box): # size:(原图w,原图h) , box:(xmin,xmax,ymin,ymax)
dw = 1. / size[0] # 1/w
dh = 1. / size[1] # 1/h
x = (box[0] + box[1]) / 2.0 # 物体在图中的中心点x坐标
y = (box[2] + box[3]) / 2.0 # 物体在图中的中心点y坐标
w = box[1] - box[0] # 物体实际像素宽度
h = box[3] - box[2] # 物体实际像素高度
x = x * dw # 物体中心点x的坐标比(相当于 x/原图w)
w = w * dw # 物体宽度的宽度比(相当于 w/原图w)
y = y * dh # 物体中心点y的坐标比(相当于 y/原图h)
h = h * dh # 物体宽度的宽度比(相当于 h/原图h)
return (x, y, w, h) # 返回 相对于原图的物体中心点的x坐标比,y坐标比,宽度比,高度比,取值范围[0-1]
# year ='2012', 对应图片的id(文件名)
def convert_annotation(image_id):
'''
将对应文件名的xml文件转化为label文件,xml文件包含了对应的bunding框以及图片长款大小等信息,
通过对其解析,然后进行归一化最终读到label文件中去,也就是说
一张图片文件对应一个xml文件,然后通过解析和归一化,能够将对应的信息保存到唯一一个label文件中去
labal文件中的格式:calss x y w h 同时,一张图片对应的类别有多个,所以对应的bunding的信息也有多个
'''
# 对应的通过year 找到相应的文件夹,并且打开相应image_id的xml文件,其对应bund文件
in_file = open('datasets/Annotations/%s.xml' % (image_id), encoding='utf-8')
# 准备在对应的image_id 中写入对应的label,分别为
# <object-class> <x> <y> <width> <height>
out_file = open('datasets/labels/%s.txt' % (image_id), 'w', encoding='utf-8')
# 解析xml文件
tree = ET.parse(in_file)
# 获得对应的键值对
root = tree.getroot()
# 获得图片的尺寸大小
size = root.find('size')
# 如果xml内的标记为空,增加判断条件
if size != None:
# 获得宽
w = int(size.find('width').text)
# 获得高
h = int(size.find('height').text)
# 遍历目标obj
for obj in root.iter('object'):
# 获得difficult ??
# difficult = obj.find('difficult').text
# 获得类别 =string 类型
cls = obj.find('action').text
# 如果类别不是对应在我们预定好的class文件中,或difficult==1则跳过
if cls not in classes:
continue
# 通过类别名称找到id
cls_id = classes.index(cls)
# 找到bndbox 对象
xmlbox = obj.find('bndbox')
# 获取对应的bndbox的数组 = ['xmin','xmax','ymin','ymax']
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
float(xmlbox.find('ymax').text))
print(image_id, cls, b)
# 带入进行归一化操作
# w = 宽, h = 高, b= bndbox的数组 = ['xmin','xmax','ymin','ymax']
bb = convert((w, h), b)
# bb 对应的是归一化后的(x,y,w,h)
# 生成 calss x y w h 在label文件中
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
# 返回当前工作目录
wd = getcwd()
print(wd)
for image_set in sets:
'''
对所有的文件数据集进行遍历
做了两个工作:
1.将所有图片文件都遍历一遍,并且将其所有的全路径都写在对应的txt文件中去,方便定位
2.同时对所有的图片文件进行解析和转化,将其对应的bundingbox 以及类别的信息全部解析写到label 文件中去
最后再通过直接读取文件,就能找到对应的label 信息
'''
# 先找labels文件夹如果不存在则创建
if not os.path.exists('datasets/labels/'):
os.makedirs('datasets/labels/')
# 读取在ImageSets/Main 中的train、test..等文件的内容
# 包含对应的文件名称
image_ids = open('datasets/ImageSets/%s.txt' % (image_set)).read().strip().split()
# 打开对应的2012_train.txt 文件对其进行写入准备
list_file = open('datasets/%s.txt' % (image_set), 'w')
# 将对应的文件_id以及全路径写进去并换行
for image_id in image_ids:
list_file.write('datasets/images/%s.jpg\n' % (image_id))
# 调用 year = 年份 image_id = 对应的文件名_id
convert_annotation(image_id)
# 关闭文件
list_file.close()
action.yaml
#path: ../datasets # dataset root dir
train: D:/software/yolov5-master/datasets/train.txt # train images (relative to 'path') 128 images
val: D:/software/yolov5-master/datasets/val.txt # val images (relative to 'path') 128 images
test: D:/software/yolov5-master/datasets/test.txt # test images (optional)
# Classes
nc: 40
names: ['applauding', 'blowing_bubbles', 'brushing_teeth', 'cleaning_the_floor', 'climbing', 'cooking', 'cutting_trees', 'cutting_vegetables', 'drinking', 'feeding_a_horse', 'fishing', 'fixing_a_bike', 'fixing_a_car', 'gardening', 'holding_an_umbrella', 'jumping', 'looking_through_a_microscope', 'looking_through_a_telescope', 'phoning', 'playing_guitar', 'playing_violin', 'pouring_liquid', 'pushing_a_cart', 'reading', 'riding_a_bike', 'riding_a_horse', 'rowing_a_boat', 'running', 'shooting_an_arrow', 'smoking', 'taking_photos', 'texting_message', 'throwing_frisby', 'using_a_computer', 'walking_the_dog', 'washing_dishes', 'watching_TV', 'waving_hands', 'writing_on_a_board', 'writing_on_a_book']
yolov5s.yaml
nc: 40 # number of classes
train.py
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/action.yaml', help='dataset.yaml path')
parser.add_argument('--device', default='0', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')