本次模型训练基于百度飞浆的Baseline:
19届智能车百度创意组识别 - 飞桨AI Studio星河社区 (baidu.com)
一、收集数据及数据处理
- 用摄像头拍摄实物,这里先选用baseline中给好的数据集。
- 创建VOC文件夹,文件夹里包含Annotations和JPEGImages两个文件夹。需要进行标注操作的图片将会放在JPEGImages文件夹里,标注生成的xml文件将会放在Annotations文件夹里。
- 图片重命名。统一命名格式,便于进行增广操作。
命名格式示例:000001.jpg
、00XXXX.jpg
。 - 上述重命名步骤会用到的python文件:
python
import os
# 指定图片所在的文件夹名称
folder_name = 'image_set'
# 获取当前工作目录
current_directory = os.getcwd()
# 构建文件夹的完整路径
folder_path = os.path.join(current_directory, folder_name)
# 检查文件夹是否存在
if not os.path.exists(folder_path):
print(f"警告:未找到名为 '{folder_name}' 的文件夹。")
else:
# 确保文件夹路径以斜杠结束
if not folder_path.endswith('/'):
folder_path += '/'
# 获取文件夹内所有的文件名列表
file_list = os.listdir(folder_path)
# 初始化计数器
counter = 1
# 遍历文件列表并重命名图片
for filename in sorted(file_list, key=lambda x: x.lower()): # 按字母顺序排序
if filename.lower().endswith(('.png', '.jpg', '.jpeg', '.bmp', '.gif')):
# 构建新的文件名,确保编号始终为5位数字
new_filename = f'{counter:06d}{os.path.splitext(filename)[1]}'
# 构建完整的原始文件路径和新文件路径
old_file_path = os.path.join(folder_path, filename)
new_file_path = os.path.join(folder_path, new_filename)
# 重命名文件
os.rename(old_file_path, new_file_path)
# 更新计数器
counter += 1
print("图片重命名完成。")
使用方法:将该python文件与"JPEGImages"文件夹放在同一目录下(即VOC文件夹),打开Windows终端,输入python指令运行即可。python img_rename.py
。使用方法也可根据自己的需求灵活变化。
二、用labelimg进行数据集图片标注
lbelimg和labelme的使用方法很相似,安装的步骤也很相似。但是labelimg可以选择的标注类型比较多,有voc的xml,也有yolo。而labelme的好像只有json格式的,所以本次目标检测数据集标注选择labelimg。
相关教程:labelme的开源GitHub库:labelme_github
labelimg的GitHub开源地址:labeimg_github
CSDN的安装教程:labelme的安装及使用_labelme安装-CSDN博客
labelimg安装教程:图像标注工具labelImg安装教程及使用方法_labelimg的安装和使用
labelimg的简单安装:
pip install labelimg -i https://pypi.tuna.tsinghua.edu.cn/simple
- 打开labelimg标注工具。打开"Anaconda Prompt"终端,输入
activate labelme
(这里填写你自己配的装有labelimg的conda环境);输入labelimg
,运行工具。 - 标注结果如下图所示:
三、数据集增广
数据集增广需要用到"ImgAug"软件。
- 增广选项:
- Noise噪声、G-Blur高斯模糊、Bright亮度,这三个是常用的,根据具体场景不同可以加入HSV色域、V-Flip垂直翻转。(V-Flip在翻转图片的同时,也会对xml文件进行处理,使得标注结果仍然准确。这个软件做的还是很细的。)
- 时刻注意已有图片编号,每次标注前都要调整"起始输出编号"。
- 增广结果如下:
- 增广之后生成的xml文件可能有小错误:filename与path的文件名部分不匹配,这里是匹配的,如果遇到不匹配的情况,如要使用下面提到的工具来处理。
- 使用方法:将该python文件与Annotations文件夹放在同一目录下,打开终端运行该python文件即可。
python
import os
import xml.etree.ElementTree as ET
def process_xml(xml_file):
# 解析XML文件
tree = ET.parse(xml_file)
root = tree.getroot()
# 获取<filename>和<path>元素
filename_elem = root.find('filename')
path_elem = root.find('path')
if filename_elem is not None and path_elem is not None:
# 获取filename和path的文本内容
filename = filename_elem.text
path = path_elem.text
# 从path中提取文件名
path_filename = os.path.basename(path)
# 比较filename和path中的文件名
if filename != path_filename:
# 将path中的文件名替换为filename
new_path = os.path.join(os.path.dirname(path), filename)
path_elem.text = new_path
# 将修改后的内容写回XML文件
tree.write(xml_file)
def process_xml_files(xml_dir):
# 遍历指定文件夹下的所有文件
for filename in os.listdir(xml_dir):
# 只处理XML文件
if filename.endswith('.xml'):
xml_file = os.path.join(xml_dir, filename)
# 对每个XML文件进行处理
process_xml(xml_file)
# 指定包含XML文件的文件夹路径
xml_dir = 'Annotations'
# 处理文件夹中的所有XML文件
process_xml_files(xml_dir)
四、将VOC类型的数据集转换成COCO类型
- VOC与COCO的讲解:VOC和COCO数据集讲解_voc数据集和coco数据集区别-CSDN博客
- 在步骤"一.2"中,我们已经创建了VOC文件夹,将以下python代码放在与VOC文件夹的同一目录下,打开终端运行即可。
python
import os
import random
import shutil
import json
import glob
import xml.etree.ElementTree as ET
def get(root, name):
vars = root.findall(name)
return vars
def get_and_check(root, name, length):
vars = root.findall(name)
if len(vars) == 0:
raise ValueError("Can not find %s in %s." % (name, root.tag))
if length > 0 and len(vars) != length:
raise ValueError(
"The size of %s is supposed to be %d, but is %d."
% (name, length, len(vars))
)
if length == 1:
vars = vars[0]
return vars
def get_filename_as_int(filename):
try:
filename = filename.replace("\\", "/")
filename = os.path.splitext(os.path.basename(filename))[0]
return int(filename)
except:
raise ValueError("Filename %s is supposed to be an integer." % (filename))
# 获取数据集中类别的名字
def get_categories(xml_files):
classes_names = []
for xml_file in xml_files:
tree = ET.parse(xml_file)
root = tree.getroot()
for member in root.findall("object"):
classes_names.append(member[0].text)
classes_names = list(set(classes_names))
classes_names.sort()
print(f"类别名字为{classes_names}")
return {name: i for i, name in enumerate(classes_names)}
def convert(xml_files, json_file):
json_dict = {"images": [], "type": "instances", "annotations": [], "categories": []}
if PRE_DEFINE_CATEGORIES is not None:
categories = PRE_DEFINE_CATEGORIES
else:
categories = get_categories(xml_files)
bnd_id = START_BOUNDING_BOX_ID
for xml_file in xml_files:
tree = ET.parse(xml_file)
root = tree.getroot()
path = get(root, "path")
if len(path) == 1:
filename = os.path.basename(path[0].text)
elif len(path) == 0:
filename = get_and_check(root, "filename", 1).text
else:
raise ValueError("%d paths found in %s" % (len(path), xml_file))
## The filename must be a number
image_id = get_filename_as_int(filename)
size = get_and_check(root, "size", 1)
width = int(get_and_check(size, "width", 1).text)
height = int(get_and_check(size, "height", 1).text)
image = {
"file_name": filename,
"height": height,
"width": width,
"id": image_id,
}
json_dict["images"].append(image)
## Currently we do not support segmentation.
# segmented = get_and_check(root, 'segmented', 1).text
# assert segmented == '0'
for obj in get(root, "object"):
category = get_and_check(obj, "name", 1).text
if category not in categories:
new_id = len(categories)
categories[category] = new_id
category_id = categories[category]
bndbox = get_and_check(obj, "bndbox", 1)
xmin = int(get_and_check(bndbox, "xmin", 1).text) - 1
ymin = int(get_and_check(bndbox, "ymin", 1).text) - 1
xmax = int(get_and_check(bndbox, "xmax", 1).text)
ymax = int(get_and_check(bndbox, "ymax", 1).text)
assert xmax > xmin
assert ymax > ymin
o_width = abs(xmax - xmin)
o_height = abs(ymax - ymin)
ann = {
"area": o_width * o_height,
"iscrowd": 0,
"bbox": [xmin, ymin, o_width, o_height],
"category_id": category_id,
"ignore": 0,
"image_id": image_id,
"id": bnd_id,
# "segmentation": [], # segmentation暂时用不上,paddle里也没有用这个
}
json_dict["annotations"].append(ann)
bnd_id = bnd_id + 1
for cate, cid in categories.items():
cat = {"supercategory": "none", "id": cid, "name": cate}
json_dict["categories"].append(cat)
os.makedirs(os.path.dirname(json_file), exist_ok=True)
json_fp = open(json_file, "w")
json_str = json.dumps(json_dict)
json_fp.write(json_str)
json_fp.close()
# 新建文件夹
def mkdir(path):
path = path.strip()
path = path.rstrip("\\")
isExists = os.path.exists(path)
if not isExists:
os.makedirs(path)
print(path + ' ----- folder created')
return True
else:
print(path + ' ----- folder existed')
return False
if __name__ == '__main__':
# 验证集比例
valRatio = 0.2
# 测试集比例
testRatio = 0.1
# 获取当前脚本路径
main_path = os.getcwd()
# voc格式的图片和xml存放路径
voc_images = os.path.join(main_path, 'VOC', 'JPEGImages')
voc_annotations = os.path.join(main_path, 'VOC', 'Annotations')
# 获取xml数量
xmlNum = len(os.listdir(voc_annotations))
val_files_num = int(xmlNum * valRatio)
test_files_num = int(xmlNum * testRatio)
coco_path = os.path.join(main_path, 'COCO')
# coco_images = os.path.join(main_path, 'COCO', 'images')
coco_json_annotations = os.path.join(main_path, 'COCO', 'annotations')
coco_train2017 = os.path.join(main_path, 'COCO', 'train')
coco_val2017 = os.path.join(main_path, 'COCO', 'valid')
coco_test2017 = os.path.join(main_path, 'COCO', 'test')
xml_val = os.path.join(main_path, 'xml', 'xml_val')
xml_test = os.path.join(main_path, 'xml', 'xml_test')
xml_train = os.path.join(main_path, 'xml', 'xml_train')
mkdir(coco_path)
# mkdir(coco_images)
mkdir(coco_json_annotations)
mkdir(xml_val)
mkdir(xml_test)
mkdir(xml_train)
mkdir(coco_train2017)
mkdir(coco_val2017)
if testRatio:
mkdir(coco_test2017)
for i in os.listdir(voc_images):
img_path = os.path.join(voc_images, i)
shutil.copy(img_path, coco_train2017)
# voc images copy to coco images
for i in os.listdir(voc_annotations):
img_path = os.path.join(voc_annotations, i)
shutil.copy(img_path, xml_train)
print("\n\n %s files copied to %s" % (val_files_num, xml_val))
for i in range(val_files_num):
if len(os.listdir(xml_train)) > 0:
random_file = random.choice(os.listdir(xml_train))
# print("%d) %s"%(i+1,random_file))
source_file = "%s/%s" % (xml_train, random_file)
# 分离文件名
font, ext = random_file.split('.')
valJpgPathList = [j for j in os.listdir(coco_train2017) if j.startswith(font)]
if random_file not in os.listdir(xml_val):
shutil.move(source_file, xml_val)
shutil.move(os.path.join(coco_train2017, valJpgPathList[0]), coco_val2017)
else:
random_file = random.choice(os.listdir(xml_train))
source_file = "%s/%s" % (xml_train, random_file)
shutil.move(source_file, xml_val)
# 分离文件名
font, ext = random_file.split('.')
valJpgPathList = [j for j in os.listdir(coco_train2017) if j.startswith(font)]
shutil.move(os.path.join(coco_train2017, valJpgPathList[0]), coco_val2017)
else:
print('The folders are empty, please make sure there are enough %d file to move' % (val_files_num))
break
for i in range(test_files_num):
if len(os.listdir(xml_train)) > 0:
random_file = random.choice(os.listdir(xml_train))
# print("%d) %s"%(i+1,random_file))
source_file = "%s/%s" % (xml_train, random_file)
# 分离文件名
font, ext = random_file.split('.')
testJpgPathList = [j for j in os.listdir(coco_train2017) if j.startswith(font)]
if random_file not in os.listdir(xml_test):
shutil.move(source_file, xml_test)
shutil.move(os.path.join(coco_train2017, testJpgPathList[0]), coco_test2017)
else:
random_file = random.choice(os.listdir(xml_train))
source_file = "%s/%s" % (xml_train, random_file)
shutil.move(source_file, xml_test)
# 分离文件名
font, ext = random_file.split('.')
testJpgPathList = [j for j in os.listdir(coco_train2017) if j.startswith(font)]
shutil.move(os.path.join(coco_train2017, testJpgPathList[0]), coco_test2017)
else:
print('The folders are empty, please make sure there are enough %d file to move' % (val_files_num))
break
print("\n\n" + "*" * 27 + "[ Done ! Go check your file ]" + "*" * 28)
START_BOUNDING_BOX_ID = 1
PRE_DEFINE_CATEGORIES = None
xml_val_files = glob.glob(os.path.join(xml_val, "*.xml"))
xml_test_files = glob.glob(os.path.join(xml_test, "*.xml"))
xml_train_files = glob.glob(os.path.join(xml_train, "*.xml"))
convert(xml_val_files, os.path.join(coco_json_annotations, 'valid.json'))
convert(xml_train_files, os.path.join(coco_json_annotations, 'train.json'))
if testRatio:
convert(xml_test_files, os.path.join(coco_json_annotations, 'test.json'))
# 删除文件夹
try:
shutil.rmtree(xml_train)
shutil.rmtree(xml_val)
shutil.rmtree(xml_test)
shutil.rmtree(os.path.join(main_path, 'xml'))
except:
print(f'xml文件删除失败,请手动删除{xml_train, xml_val, xml_test}')
- VOC2COCO的结果:
- 文件夹train、valid、test里存放的是图片文件,本次目标检测模型训练中暂时用不到这三个文件。
五、PaddleDetection模型训练
- 将上述生成的三个json文件下载到AIStudio平台中。
- images文件夹下放的是本次模型训练需要用到的所有图片(也就是train、valid、test里存放的图片文件的总和)。
- **修改yml文件参数:num_classes
- 参考baseline的指引开始模型的训练、导出、推理。
- 推理结果如下: