话不多说，先奉上imgaug官网：imgaug — imgaug 0.4.0 documentation
官网的目录，从中可以知道它能够做到的增强范围：
一、imgaug安装
安装依赖库
pip install six numpy scipy matplotlib scikit-image opencv-python imageio然后，直接在终端进行安装，用anaconda的可以在Prompt进行安装：
pip install imgaug这里如果不幸，会在一切看似顺利的安装过程中，突然出现一连串的红色错误，如下
G:\python\Pyhton36\Scripts>pip install imgaug
Collecting imgaug
Downloading https://files.pythonhosted.org/packages/af/fc/c56a7da8c23122b7c5325b941850013880a7a93c21dc95e2b1ecd4750108/imgaug-0.2.7-py3-none-any.whl (644kB)
100% |████████████████████████████████| 645kB 73kB/s
Requirement already satisfied: scikit-image>=0.11.0 in g:\python\pyhton36\lib\site-packages (from imgaug) (0.14.1)
Collecting imageio (from imgaug)
Downloading https://files.pythonhosted.org/packages/28/b4/cbb592964dfd71a9de6a5b08f882fd334fb99ae09ddc82081dbb2f718c81/imageio-2.4.1.tar.gz (3.3MB)
100% |████████████████████████████████| 3.3MB 438kB/s
Collecting Shapely (from imgaug)
Downloading https://files.pythonhosted.org/packages/a2/fb/7a7af9ef7a35d16fa23b127abee272cfc483ca89029b73e92e93cdf36e6b/Shapely-1.6.4.post2.tar.gz (225kB)
100% |████████████████████████████████| 235kB 181kB/s
Complete output from command python setup.py egg_info:
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "C:\Users\34905\AppData\Local\Temp\pip-install-43zide7u\Shapely\setup.py", line 80, in <module>
from shapely._buildcfg import geos_version_string, geos_version, \
File "C:\Users\34905\AppData\Local\Temp\pip-install-43zide7u\Shapely\shapely\_buildcfg.py", line 200, in <module>
lgeos = CDLL("geos_c.dll")
File "g:\python\pyhton36\lib\ctypes\__init__.py", line 348, in __init__
self._handle = _dlopen(self._name, mode)
OSError: [WinError 126] 找不到指定的模块。
----------------------------------------
Command "python setup.py egg_info" failed with error code 1 in C:\Users\34905\AppData\Local\Temp\pip-install-43zide7u\Shapely\查阅了网上前辈的资料，需要先安装shapely
通过这个网址 https://www.lfd.uci.edu/~gohlke/pythonlibs/#shapely （这是一个非常好的扩展包非正式网址，里面有许多的工具可供使用） 中找到适合自己python版本的shapely下载到指定路径
我是windows,64位操作系统，python3.5，我选择下面这个
然后通过如下命令进行安装：
G:\python\Pyhton36\Scripts>python -m pip install Shapely‑1.6.4.post2‑cp35‑cp35m‑win_amd64.whl
最后再重复之前安装imgaug的命令：
pip install imgaug
搞定，收工，安装完成
参考：Windows10在cmd中用pip安装imgaug的时候报错_LebronChen666的博客-CSDN博客
二、github原代码遇见问题，批量的BoundingBox带XML文件的增强
github原作者地址：GitHub - xinyu-ch/Data-Augment: imgaug--Bounding Boxes augment
存在一丢丢的错误，这里进行了修改，往下看（第三节），已调试，可用，这里讲下遇见的一些小问题
1.如果不幸的遇见了下面的问题，这是一个常见问题，解决方式较为统一：解决UnicodeDecodeError: 'gbk' codec can't decode byte 0xb9 in position x: illegal multibyte sequence_强殖装甲凯普的博客-CSDN博客
解决方式如下：
第一种解决方法，增加encoding=‘UTF-8’：
FILE_OBJECT= open( 'train.txt','r', encoding='UTF-8' )第二种方法，二进制读取：
FILE_OBJECT= open( 'train.txt', 'rb' )之后，就可以看第三节，是对上文作者github部分做了修改后的，调试可用
三、调试后批量的BoundingBox带XML文件的增强（可直接用）
- 创建要保存增强后的图像和xml文件的文件夹
- 提前设定好采用什么方式进行图像的增强，是旋转，还是加噪声，是提升亮度，还是平移补充
- 然后读进来一张图片，和该图像对应的xml内标签的坐标信息
- 对图像和矩形框进行变换
- 最后保存增强后的图片和xml文件
import xml.etree.ElementTree as ET
import pickle
import os
from os import getcwd
import numpy as np
from PIL import Image
import shutil
import matplotlib.pyplot as plt
import imgaug as ia
from imgaug import augmenters as iaa
ia.seed(1)
def read_xml_annotation(root, image_id):
in_file = open(os.path.join(root, image_id), encoding='UTF-8')
tree = ET.parse(in_file)
root = tree.getroot()
bndboxlist = []
for object in root.findall('object'): # 找到root节点下的所有country节点
bndbox = object.find('bndbox') # 子节点下节点rank的值
xmin = int(bndbox.find('xmin').text)
xmax = int(bndbox.find('xmax').text)
ymin = int(bndbox.find('ymin').text)
ymax = int(bndbox.find('ymax').text)
# print(xmin,ymin,xmax,ymax)
bndboxlist.append([xmin, ymin, xmax, ymax])
# print(bndboxlist)
# ndbox = root.find('object').find('bndbox')
return bndboxlist
# (506.0000, 330.0000, 528.0000, 348.0000) -> (520.4747, 381.5080, 540.5596, 398.6603)
def change_xml_annotation(root, image_id, new_target):
new_xmin = new_target[0]
new_ymin = new_target[1]
new_xmax = new_target[2]
new_ymax = new_target[3]
in_file = open(os.path.join(root, str(image_id) + '.xml'), encoding='UTF-8' ) # 这里root分别由两个意思
tree = ET.parse(in_file)
xmlroot = tree.getroot()
object = xmlroot.find('object')
bndbox = object.find('bndbox')
xmin = bndbox.find('xmin')
xmin.text = str(new_xmin)
ymin = bndbox.find('ymin')
ymin.text = str(new_ymin)
xmax = bndbox.find('xmax')
xmax.text = str(new_xmax)
ymax = bndbox.find('ymax')
ymax.text = str(new_ymax)
tree.write(os.path.join(root, str("%06d" % (str(id) + '.xml'))))
def change_xml_list_annotation(root, image_id, new_target, saveroot, id):
in_file = open(os.path.join(root, str(image_id) + '.xml'), encoding='UTF-8' ) # 这里root分别由两个意思
tree = ET.parse(in_file)
elem = tree.find('filename')
elem.text = (str("%06d" % int(id)) + '.png')
xmlroot = tree.getroot()
index = 0
for object in xmlroot.findall('object'): # 找到root节点下的所有country节点
bndbox = object.find('bndbox') # 子节点下节点rank的值
# xmin = int(bndbox.find('xmin').text)
# xmax = int(bndbox.find('xmax').text)
# ymin = int(bndbox.find('ymin').text)
# ymax = int(bndbox.find('ymax').text)
new_xmin = new_target[index][0]
new_ymin = new_target[index][1]
new_xmax = new_target[index][2]
new_ymax = new_target[index][3]
xmin = bndbox.find('xmin')
xmin.text = str(new_xmin)
ymin = bndbox.find('ymin')
ymin.text = str(new_ymin)
xmax = bndbox.find('xmax')
xmax.text = str(new_xmax)
ymax = bndbox.find('ymax')
ymax.text = str(new_ymax)
index += 1
print("index=",index)
tree.write(os.path.join(saveroot, str("%06d" % int(id)) + '.xml'))
def mkdir(path):
# 去除首位空格
path = path.strip()
# 去除尾部 \ 符号
path = path.rstrip("\\")
# 判断路径是否存在
# 存在 True
# 不存在 False
isExists = os.path.exists(path)
# 判断结果
if not isExists:
# 如果不存在则创建目录
# 创建目录操作函数
os.makedirs(path)
print(path + ' 创建成功')
return True
else:
# 如果目录存在则不创建，并提示目录已存在
print(path + ' 目录已存在')
return False
if __name__ == "__main__":
IMG_DIR = "F:\\image\\raw_xml"
XML_DIR = "F:\\image\\xml"
AUG_XML_DIR = "./Annotations" # 存储增强后的XML文件夹路径
try:
shutil.rmtree(AUG_XML_DIR)
except FileNotFoundError as e:
a = 1
mkdir(AUG_XML_DIR)
AUG_IMG_DIR = "./JPEGImages" # 存储增强后的影像文件夹路径
try:
shutil.rmtree(AUG_IMG_DIR)
except FileNotFoundError as e:
a = 1
mkdir(AUG_IMG_DIR)
AUGLOOP = 2 # 每张影像增强的数量
boxes_img_aug_list = []
new_bndbox = []
new_bndbox_list = []
# 影像增强
seq = iaa.Sequential([
iaa.Flipud(0.5), # vertically flip 20% of all images
iaa.Fliplr(0.5), # 镜像
iaa.Sharpen(alpha=(0, 1.0), lightness=(0.75, 1.5)),
iaa.Crop(px=(0, 16)),
iaa.Add((-10, 10), per_channel=0.5),
iaa.Multiply((1.2, 1.5)), # change brightness, doesn't affect BBs
iaa.Affine(
translate_px={"x": 15, "y": 15},
scale=(0.8, 0.95)
#rotate=(-30, 30)
) # translate by 40/60px on x/y axis, and scale to 50-70%, affects BBs
])
for root, sub_folders, files in os.walk(XML_DIR):
for name in files:
bndbox = read_xml_annotation(XML_DIR, name)
shutil.copy(os.path.join(XML_DIR, name), AUG_XML_DIR)
shutil.copy(os.path.join(IMG_DIR, name[:-4] + '.png'), AUG_IMG_DIR)
print(os.path.join(IMG_DIR, name[:-4] + '.png'))
for epoch in range(AUGLOOP):
seq_det = seq.to_deterministic() # 保持坐标和图像同步改变，而不是随机
# 读取图片
img = Image.open(os.path.join(IMG_DIR, name[:-4] + '.png'))
# sp = img.size
img = np.asarray(img)
# bndbox 坐标增强
for i in range(len(bndbox)):
bbs = ia.BoundingBoxesOnImage([
ia.BoundingBox(x1=bndbox[i][0], y1=bndbox[i][1], x2=bndbox[i][2], y2=bndbox[i][3]),
], shape=img.shape)
bbs_aug = seq_det.augment_bounding_boxes([bbs])[0]
boxes_img_aug_list.append(bbs_aug)
# new_bndbox_list:[[x1,y1,x2,y2],...[],[]]
n_x1 = int(max(1, min(img.shape[1], bbs_aug.bounding_boxes[0].x1)))
n_y1 = int(max(1, min(img.shape[0], bbs_aug.bounding_boxes[0].y1)))
n_x2 = int(max(1, min(img.shape[1], bbs_aug.bounding_boxes[0].x2)))
n_y2 = int(max(1, min(img.shape[0], bbs_aug.bounding_boxes[0].y2)))
if n_x1 == 1 and n_x1 == n_x2:
n_x2 += 1
if n_y1 == 1 and n_y2 == n_y1:
n_y2 += 1
if n_x1 >= n_x2 or n_y1 >= n_y2:
print('error', name)
new_bndbox_list.append([n_x1, n_y1, n_x2, n_y2])
# 存储变化后的图片
image_aug = seq_det.augment_images([img])[0]
path = os.path.join(AUG_IMG_DIR,str("%06d" % (len(files) + int(name[:-4]) + epoch * 250)) + '.png')
image_auged = bbs.draw_on_image(image_aug, thickness=0)####################################
Image.fromarray(image_auged).save(path)
# 存储变化后的XML
change_xml_list_annotation(XML_DIR, name[:-4], new_bndbox_list, AUG_XML_DIR,len(files) + int(name[:-4]) + epoch * 250)
print(str("%06d" % (len(files) + int(name[:-4]) + epoch * 250)) + '.png')
new_bndbox_list = []
代码中写死了对数据的读取方式：elem.text = (str("%06d" % int(id)) + '.png')
如果没必要，就按下面这种形式进行命名
增强后，用labelImg查看的结果如下：
https://blog.csdn.net/coooo0l/article/details/84492916#commentsedit
扫一扫
9715
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
