【人工智能学习之骨龄检测实战】

1 克隆YOLOV52 手骨关节数据集3 数据处理3.1 手骨处理bone_createCLAHE.pyxml_to_txt.pysplit_dataset.py

3.2 关节处理bone9_createCLAHE.pypic_power.py

4 网络模型训练4.1 侦测模型训练bone.yamlyolov5s.yamltrain.pybest.pt

4.2 分类模型训练my_net.pymy_model.py

5 骨龄检测bone_window.pyanalyse_bone_age.pyscreen_bone.pycommon.py

6 成果展示

1 克隆YOLOV5

YOLOV5下载链接：YOLOV5

也可以直接在你当文件夹cmd命令窗口进行克隆。

克隆 repo，并要求在 Python>=3.8.0 环境中安装 requirements.txt ，且要求 PyTorch>=1.8 。

<code>git clone https://github.com/ultralytics/yolov5 # clone

cd yolov5

pip install -r requirements.txt # install

2 手骨关节数据集

以下是我自己使用的一些数据集：

手骨数据集

关节数据集

大家也可以使用自己或者其他的一些数据集进行训练。

关节数据集是我处理过的，后文会讲述处理方法，大家可以自行调整。

3 数据处理

分析我们获取的数据集，发现很多图片有雾感（即图像中像素几乎集中在一个区间，导致图片中的对比度不强，给我们呈现出雾感），会影响模型的训练，于是采用直方图均衡化来进行处理。

3.1 手骨处理

bone_createCLAHE.py

数据集图片自适应直方图均衡化

<code>import os

import cv2

from tqdm import tqdm

def opt_img(img_path):

img = cv2.imread(img_path, 0)

clahe = cv2.createCLAHE(tileGridSize=(3, 3))

# 自适应直方图均衡化

dst1 = clahe.apply(img)

cv2.imwrite(img_path, dst1)

pic_path_folder = r'bone_imgs/JPEGImages'

if __name__ == '__main__':

for pic_folder in tqdm(os.listdir(pic_path_folder)):

data_path = os.path.join(pic_path_folder, pic_folder)

# 去雾

opt_img(data_path)

xml_to_txt.py

xml标注转为txt

import xml.etree.ElementTree as ET

import os

from PIL import Image

def convert(size, box):

x_center = (box[0] + box[1]) / 2.0

y_center = (box[2] + box[3]) / 2.0

x = x_center / size[0]

y = y_center / size[1]

w = (box[1] - box[0]) / size[0]

h = (box[3] - box[2]) / size[1]

return (x, y, w, h)

def convert_format(xml_files_path, save_txt_files_path, classes):

if not os.path.exists(save_txt_files_path):

os.makedirs(save_txt_files_path)

xml_files = os.listdir(xml_files_path)

# print(xml_files)

for xml_name in xml_files:

# print(xml_name)

xml_file = os.path.join(xml_files_path, xml_name)

out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')

out_txt_f = open(out_txt_path, 'w')

tree = ET.parse(xml_file)

root = tree.getroot()

size = root.find('size')

if size is None:

w, h = get_imgwh(xml_file)

else:

w = int(size.find('width').text)

h = int(size.find('height').text)

if w == 0 or h == 0:

w, h = get_imgwh(xml_file)

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

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))

# b=(xmin, xmax, ymin, ymax)

# print(w, h, b)

try:

bb = convert((w, h), b)

except:

print(f"convert转换异常: { xml_file}")

out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

def get_imgwh(xml_file):

img_path = xml_file.replace("Annotations", "JPEGImages").replace(".xml", image_suffix)

img_pil = Image.open(img_path)

w, h = img_pil.size

return w, h

if __name__ == "__main__":

"""

说明:

BASE_PATH: 数据集标签目录的上一级路径

注意数据集里面的标签文件: 目录名是 Annotations

保存为txt的标签目录名是: labels

"""

BASE_PATH = r"./data/bone_imgs"

image_suffix = ".png"

# 需要转换的类别，需要一一对应

classes = [

'Radius',

'Ulna',

'MCPFirst',

'ProximalPhalanx',

'DistalPhalanx',

'MiddlePhalanx',

'MCP'

]

# 2、voc格式的xml标签文件路径

xml_files = os.path.join(BASE_PATH, "Annotations")

# 3、转化为yolo格式的txt标签文件存储路径

save_txt_files = os.path.join(BASE_PATH, "labels")

convert_format(xml_files, save_txt_files, classes)

split_dataset.py

将图片和标注数据按比例切分为 训练集和测试集

"""

1.将图片和标注数据按比例切分为 训练集和测试集

2.原图片的目录名是: JPEGImages

3.对应的txt标签是之前转换的labels

4.训练集、测试集、验证集 路径和VOC2007路径保持一致

"""

import shutil

import random

import os

BASE_PATH = r"./data/bone_imgs"

# 数据集路径

image_original_path = os.path.join(BASE_PATH, "JPEGImages/")

label_original_path = os.path.join(BASE_PATH, "labels/")

# 训练集路径

train_image_path = os.path.join(BASE_PATH, "train/images/")

train_label_path = os.path.join(BASE_PATH, "train/labels/")

# 验证集路径

val_image_path = os.path.join(BASE_PATH, "val/images/")

val_label_path = os.path.join(BASE_PATH, "val/labels/")

# 测试集路径

test_image_path = os.path.join(BASE_PATH, "test/images/")

test_label_path = os.path.join(BASE_PATH, "test/labels/")

# 数据集划分比例，训练集75%，验证集15%，测试集15%，按需修改

train_percent = 0.7

val_percent = 0.15

test_percent = 0.15

# 检查文件夹是否存在

def mkdir():

if not os.path.exists(train_image_path) and train_percent > 0:

os.makedirs(train_image_path)

if not os.path.exists(train_label_path) and train_percent > 0:

os.makedirs(train_label_path)

if not os.path.exists(val_image_path) and val_percent > 0:

os.makedirs(val_image_path)

if not os.path.exists(val_label_path) and val_percent > 0:

os.makedirs(val_label_path)

if not os.path.exists(test_image_path) and test_percent > 0:

os.makedirs(test_image_path)

if not os.path.exists(test_label_path) and test_percent > 0:

os.makedirs(test_label_path)

def main():

mkdir()

total_txt = os.listdir(label_original_path)

num_txt = len(total_txt)

list_all_txt = range(num_txt) # 范围 range(0, num)

# 0.75 * num_txt

num_train = int(num_txt * train_percent)

# 0.15 * num_txt

# 如果测试集test_percent==0, 直接使用总数量减去训练集的数量

if test_percent == 0:

num_val = num_txt - num_train

else:

num_val = int(num_txt * val_percent)

num_test = num_txt - num_train - num_val

train = random.sample(list_all_txt, num_train)

# 在全部数据集中取出train

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)

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 = image_original_path + name + '.png'

srcLabel = label_original_path + name + '.txt'

if i in train:

dst_train_Image = train_image_path + name + '.png'

dst_train_Label = train_label_path + name + '.txt'

shutil.copyfile(srcImage, dst_train_Image)

shutil.copyfile(srcLabel, dst_train_Label)

elif i in val:

dst_val_Image = val_image_path + name + '.png'

dst_val_Label = val_label_path + name + '.txt'

shutil.copyfile(srcImage, dst_val_Image)

shutil.copyfile(srcLabel, dst_val_Label)

else:

dst_test_Image = test_image_path + name + '.png'

dst_test_Label = test_label_path + name + '.txt'

shutil.copyfile(srcImage, dst_test_Image)

shutil.copyfile(srcLabel, dst_test_Label)

if __name__ == '__main__':

main()

3.2 关节处理

bone9_createCLAHE.py

数据集图片自适应直方图均衡化

import os

import cv2

from tqdm import tqdm

def opt_img(img_path):

img = cv2.imread(img_path, 0)

clahe = cv2.createCLAHE(tileGridSize=(3, 3))

# 自适应直方图均衡化

dst1 = clahe.apply(img)

cv2.imwrite(img_path, dst1)

pic_path_folder = r'bone_imgs/JPEGImages'

if __name__ == '__main__':

for pic_folder in tqdm(os.listdir(pic_path_folder)):

data_path = os.path.join(pic_path_folder, pic_folder)

# 去雾

opt_img(data_path)

pic_power.py

图像增强

数据集增强至每份1800，

再按比例随机抽样到test目录下。

增强完毕过后进行预处理同一大小。

import cv2

import os

import glob

from PIL import Image

import warnings

import time

from torchvision import transforms

warnings.filterwarnings('error')

pic_transform = transforms.Compose([

# transforms.ToTensor(),

transforms.Grayscale(num_output_channels=3),

transforms.RandomHorizontalFlip(p=0.5), # 执行水平翻转的概率为0.5

transforms.RandomVerticalFlip(p=0.5), # 执行垂直翻转的概率为0.5

transforms.RandomRotation((30), expand=True),

# transforms.Resize((96, 96), antialias=True),

# transforms.Normalize(0.5,0.5),

])

size_transform = transforms.Compose([

transforms.Grayscale(num_output_channels=1),

transforms.Resize((96, 96), antialias=True)

])

base_path = "./data/bone9_imgs/test" #增强train 预处理 train、test

Max_num = 1800

Type = "DIP" #更改此处

one_hot_dic_grade = {

'DIP':11,

'DIPFirst':11,

'MCP':10,

'MCPFirst':11,

'MIP':12,

'PIP':12,

'PIPFirst':12,

'Radius':14,

'Ulna':12

}

for num in range(1,one_hot_dic_grade[Type]+1):

org_img_paths = glob.glob(os.path.join(base_path,Type,str(num),"*"))

# 均衡控制

power_num = Max_num - len(org_img_paths)

if power_num < 0 :

print(f"{ Type}/{ num} 超过上限")

while power_num > 0:

for path in org_img_paths:

try:

# png转jpg

# image_name = str(int(time.time() * 1000000)) + '.jpg'

# targe_path = path.rsplit('/', maxsplit=1)[0]

# png_image = Image.open(path)

# png_image.save(targe_path + '/' + image_name, format="jpeg")code>

# os.remove(path)

# 数据增强

png_image = Image.open(path)

targe_path = path.rsplit('\\', maxsplit=1)[0]

pic = pic_transform(png_image)

image_name = Type +'_' + str(int(time.time() * 1000000)) + '.png'

pic.save(targe_path + '/' + image_name, format="png")code>

# print(f'增强成功{path}')

power_num -= 1

if power_num == 0:

print(f"{ Type}/{ num} 已达增强上限数量！！！！！！！！！！！！！！！！！！！！")

break

# 数据检查

# img = cv2.imread(path)

# # 检查是否能灰度

# img_gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)

# print(f"已检查文件: {path}")

# # 重新保存，部分有问题图片[1,192,192]>>[3,96,96]

# img_resize = cv2.resize(img, (96, 96))

# cv2.imwrite(path, img_resize, [cv2.IMWRITE_JPEG_QUALITY, 90])

except Exception as e:

# 打印异常信息

print("发生异常：", str(e))

# 删除异常文件

os.remove(path)

print(f"已删除异常文件: { path}！！！！！！！！！！！！！！！！！！！！！！！！！！！")

'''

# 全部增强之后全部预处理

org_img_paths = glob.glob(os.path.join(base_path,"*","*","*"))

for path in org_img_paths:

png_image = Image.open(path)

pic = size_transform(png_image)

pic.save(path, format="png")code>

print(f'尺寸修改成功{path}')

'''

4 网络模型训练