首先,用labelimg打标,我这边是打成VOC格式,会生成很多xml格式的文件。
接着,将你的所有图片放在JPEGImages文件夹中,将所有的xml格式的文件放在Annotations文件夹中,如图所示:
然后进行数据集的格式处理,这也是这篇文章的核心,按我的步骤走就OK
第一步,将xml格式的文件转成txt格式,并且会生成一个txt文件夹,所有的文件都会存入到这个txt文件夹中,代码如下:
需要改变的有类别列表,还有你的路径地址
import os.path
import xml.etree.ElementTree as ET
# 1. 将这个地方改成自己类别的列表
class_names = ['Catla', 'Kendai', 'Carp', 'Silver']
# 2. 将路径修改
xmlpath = r'F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\Annotations/' # 原xml路径
txtpath = r'F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\txt/' # 转换后txt文件存放路径
files = []
if not os.path.exists(txtpath):
os.makedirs(txtpath)
for root, dirs, files in os.walk(xmlpath):
None
number = len(files)
print(number)
i = 0
while i < number:
name = files[i][0:-4]
xml_name = name + ".xml"
txt_name = name + ".txt"
xml_file_name = xmlpath + xml_name
txt_file_name = txtpath + txt_name
xml_file = open(xml_file_name)
tree = ET.parse(xml_file)
root = tree.getroot()
# filename = root.find('name').text
# image_name = root.find('filename').text
w = int(root.find('size').find('width').text)
h = int(root.find('size').find('height').text)
f_txt = open(txt_file_name, 'w+')
content = ""
first = True
for obj in root.iter('object'):
name = obj.find('name').text
class_num = class_names.index(name)
# class_num = 0
xmlbox = obj.find('bndbox')
x1 = int(xmlbox.find('xmin').text)
x2 = int(xmlbox.find('xmax').text)
y1 = int(xmlbox.find('ymin').text)
y2 = int(xmlbox.find('ymax').text)
if first:
content += str(class_num) + " " + \
str((x1 + x2) / 2 / w) + " " + str((y1 + y2) / 2 / h) + " " + \
str((x2 - x1) / w) + " " + str((y2 - y1) / h)
first = False
else:
content += "\n" + \
str(class_num) + " " + \
str((x1 + x2) / 2 / w) + " " + str((y1 + y2) / 2 / h) + " " + \
str((x2 - x1) / w) + " " + str((y2 - y1) / h)
# print(str(i / (number - 1) * 100) + "%\n")
print(content)
f_txt.write(content)
f_txt.close()
xml_file.close()
i += 1
第二步是train与val的划分,代码如下:
这时要在你的路径下创建ImageSets\Main,需要改变的是你的路径地址还有训练集验证集比例。
import os
import random
random.seed(0)
# 1. 将路径修改为自己的
xmlfilepath = r'F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\Annotations/'
saveBasePath = r'F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\ImageSets\Main/'
# ----------------------------------------------------------------------#
# 想要增加测试集修改trainval_percent
# train_percent不需要修改
# ----------------------------------------------------------------------#
trainval_percent = 1
train_percent = 0.7
temp_xml = os.listdir(xmlfilepath)
total_xml = []
for xml in temp_xml:
if xml.endswith(".xml"):
total_xml.append(xml)
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)
print("train and val size", tv)
print("traub suze", tr)
ftrainval = open(os.path.join(saveBasePath, 'trainval.txt'), 'w')
ftest = open(os.path.join(saveBasePath, 'test.txt'), 'w')
ftrain = open(os.path.join(saveBasePath, 'train.txt'), 'w')
fval = open(os.path.join(saveBasePath, '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()
第三步是复制出图片和标签,生成yolov7需要的文件夹格式
路径怎么改,类比我的路径就可以了
import os
import shutil
from tqdm import tqdm
SPLIT_PATH = r"F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\ImageSets\Main"
IMGS_PATH = r"F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\JPEGImages"
TXTS_PATH = r"F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\txt"
TO_IMGS_PATH = r'F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\images'
TO_TXTS_PATH = r'F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\labels'
data_split = ['train.txt', 'val.txt']
to_split = ['train2007', 'val2007']
for index, split in enumerate(data_split):
split_path = os.path.join(SPLIT_PATH, split)
to_imgs_path = os.path.join(TO_IMGS_PATH, to_split[index])
if not os.path.exists(to_imgs_path):
os.makedirs(to_imgs_path)
to_txts_path = os.path.join(TO_TXTS_PATH, to_split[index])
if not os.path.exists(to_txts_path):
os.makedirs(to_txts_path)
f = open(split_path, 'r')
count = 1
for line in tqdm(f.readlines(), desc="{} is copying".format(to_split[index])):
# 复制图片
src_img_path = os.path.join(IMGS_PATH, line.strip() + '.JPG')
dst_img_path = os.path.join(to_imgs_path, line.strip() + '.JPG')
if os.path.exists(src_img_path):
shutil.copyfile(src_img_path, dst_img_path)
else:
print("error file: {}".format(src_img_path))
# 复制txt标注文件
src_txt_path = os.path.join(TXTS_PATH, line.strip() + '.txt')
dst_txt_path = os.path.join(to_txts_path, line.strip() + '.txt')
if os.path.exists(src_txt_path):
shutil.copyfile(src_txt_path, dst_txt_path)
else:
print("error file: {}".format(src_txt_path))
第四步:创建出最终训练需要的train.txt和val.txt文件
# From Mr. Dinosaur
import os
def listdir(path, list_name): # 传入存储的list
for file in os.listdir(path):
file_path = os.path.join(path, file)
if os.path.isdir(file_path):
listdir(file_path, list_name)
else:
list_name.append(file_path)
list_name = []
path = r'F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\images\val2007' # 文件夹路径
listdir(path, list_name)
print(list_name)
with open(r'F:\graduate_files\PAPER\yolov7\鱼类数据集\fish_small\val.txt', 'w') as f: # 要存入的txt
write = ''
for i in list_name:
write = write + str(i) + '\n'
f.write(write)
最终你的文件夹中会有这些(选定的)
此时,数据集就标注完成了,然后我们回到yolov7的代码中,在yolov7.yaml中更改类别数量
创建你自己的训练集yaml文件
最后修改train.py
这样就完成了!
点个赞吧!