文章目录
1.普通文本操作
#普通文本操作
import os
file=open('/hdd2/wh/pascalraw/PASCALRAW/trainval/train.txt')
#file=open('val.txt')
file_list = []
labelMat = []
for line in file.readlines():
#line = line + ".txt"
#type(line)
s = ""
curLine = line.strip().split(" ")
curLine = s.join(curLine) + ".jpg"
file_list.append(curLine)
print(file_list)
path = "/hdd2/wh/pascalraw/PASCALRAW/jpg"
abs_path = os.path.abspath(path)
os.listdir(abs_path)
result = "/hdd2/wh/datasets/COCO/train2017/"
result_dir = os.path.abspath(result)
#print(result)
os.listdir(result)
#os.path.join(abs_path,"2014_004248.xml")
#print(os.path.join(abs_path,"2014_004248.xml"))
for file in file_list:
shutil.copyfile(os.path.join(abs_path,file), result_dir)
shutil.copy()
print("done.")
2.文本操作分离尾数是奇数或者偶数的文件
2.1 方法1：使用glob.glob() 分离奇数偶数图片。
这个字符串的书写和我们使用linux的shell命令相似，或者说基本一样。也就是说，只要我们按照平常使用cd命令时的参数就能够找到我们所需要的文件的路径。字符串中可以包括“”、“?”和"["、"]"，其中“”表示匹配任意字符串，“?”匹配任意单个字符，[0-9]与[a-z]表示匹配0-9的单个数字与a-z的单个字符
import os
import shutil
import xml.etree.ElementTree as ET
import glob
# 复制图像到另一个文件夹
# 文件所在文件夹
file_dir = '/hdd2/wh/pascalraw/PASCALRAW/jpg/'
# 创建一个子文件存放文件
result_dir_0 = '/hdd2/wh/datasets/COCO/train2017'
result_dir_1 = '/hdd2/wh/datasets/COCO/val2017'
file_list = os.listdir(file_dir)
#print(file_list)
even_files = glob.glob(os.path.join(file_dir, "*[02468].jpg"))
#print("odd_files", odd_files)
odd_files = glob.glob(os.path.join(file_dir, "*[13579].jpg"))
#print("even_files", even_files)
for image in even_files:
shutil.copy(os.path.join(file_dir, image), result_dir_0)
for image in even_files:
shutil.copy(os.path.join(file_dir, image), result_dir_1)
2.2 方法2：用最无脑的方法:str.endswith(file or image , match_str)
for image in file_list:
#print(image)
#if image == "2014_00???[0,2,4,6,8].jpg": //不行 不能用==直接连接
if str.endswith(image, "0.jpg") or str.endswith(image, "2.jpg") or str.endswith(image, "4.jpg") or str.endswith(image, "6.jpg") or str.endswith(image, "8.jpg"):
if os.path.exists(file_dir):
shutil.copy(os.path.join(file_dir, image), result_dir_0)
if str.endswith(image, "1.jpg") or str.endswith(image, "3.jpg") or str.endswith(image, "5.jpg") or str.endswith(image, "7.jpg") or str.endswith(image, "9.jpg"):
if os.path.exists(file_dir):
shutil.copy(os.path.join(file_dir, image), result_dir_1)
'''
print("done!")
done
3. Python批量替换文件中指定字符串
# -*- coding:utf-8 -*-
__author__ = 'ShawDa'
import glob
xmls = glob.glob('xml_files/*.xml')
for one_xml in xmls:
print(one_xml)
f = open(one_xml, 'r+', encoding='utf-8')
all_the_lines = f.readlines()
f.seek(0)
f.truncate()
for line in all_the_lines:
line = line.replace('dog', 'pig')
line = line.replace('cat', 'bike')
f.write(line)
f.close()
# 可视化coco格式json标注中的box到图片上
import json
import shutil
import cv2
import os
def select(json_path, outpath, image_path):
cat_class = []
count = 0
json_file = open(json_path)
infos = json.load(json_file)
images = infos["images"]
annos = infos["annotations"]
assert len(images) == len(images)
for i in range(len(images)):
im_id = images[i]["id"]
im_path = image_path + "/" + images[i]["file_name"]
img = cv2.imread(im_path)
print(img.shape)
for j in range(len(annos)):
if annos[j]["image_id"] == im_id:
cate_id = annos[j]["category_id"]
#if cate_id == '0':
# cat_class.append("bicycle")
#if cate_id == '1':
# cat_class.append("car")
#if cate_id == '2':
# cat_class.append("person")
print(cate_id)
x, y, w, h = annos[j]["bbox"]
x, y, w, h = int(x), int(y), int(w), int(h)
x2, y2 = x + w, y + h
# object_name = annos[j][""]
img = cv2.rectangle(img, (x, y), (x2, y2), (255, 0, 0), thickness=2)
cv2.putText(img, str(cate_id), (200, 200), cv2.FONT_HERSHEY_COMPLEX, 2.0, (100, 200, 200), 3)
count = count + 1
img_name = outpath + "/" + images[i]["file_name"]
cv2.imwrite(img_name, img)
break
print(i)
#print(cat_class)
if __name__ == "__main__":
json_path = "/hdd2/wh/datasets/coco_raw/annotations/instances_train2017_jpg.json"
out_path = "/hdd2/wh/datasets/vis/"
if os.path.exists(out_path):
shutil.rmtree(out_path)
os.mkdir(out_path)
image_path = "/hdd2/wh/datasets/coco_raw/train2017/"
select(json_path, out_path, image_path)
4. voc2coco.py
#!/usr/bin/python
# pip install lxml
import sys
import os
import json
import xml.etree.ElementTree as ET
import glob
START_BOUNDING_BOX_ID = 1
PRE_DEFINE_CATEGORIES = None
# If necessary, pre-define category and its id
# PRE_DEFINE_CATEGORIES = {"aeroplane": 1, "bicycle": 2, "bird": 3, "boat": 4,
# "bottle":5, "bus": 6, "car": 7, "cat": 8, "chair": 9,
# "cow": 10, "diningtable": 11, "dog": 12, "horse": 13,
# "motorbike": 14, "person": 15, "pottedplant": 16,
# "sheep": 17, "sofa": 18, "train": 19, "tvmonitor": 20}
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))
def get_categories(xml_files):
"""Generate category name to id mapping from a list of xml files.
Arguments:
xml_files {list} -- A list of xml file paths.
Returns:
dict -- category name to id mapping.
"""
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()
return {
name: (i + 1) 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)
print("get_categories:", categories)
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) + 1
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,
"image_id": image_id,
"bbox": [xmin, ymin, o_width, o_height],
"category_id": category_id,
"id": bnd_id,
"ignore": 0,
"segmentation": [],
}
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()
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(
description="Convert Pascal VOC annotation to COCO format."
)
parser.add_argument("xml_dir", help="Directory path to xml files.", type=str, default='')
parser.add_argument("json_file", help="Output COCO format json file.", type=str, default='')
args = parser.parse_args()
#xml_files = glob.glob(os.path.join(r"C:\Users\chenwei\Study\ONE\Example Segmentation\Codes\val_2", "*.xml"))
xml_files = glob.glob(os.path.join(xml_dir, "*.xml"))
# If you want to do train/test split, you can pass a subset of xml files to convert function.
print("Number of xml files: {}".format(len(xml_files)))
convert(xml_files, args.json_file)
#convert(xml_files, r"C:\Users\chenwei\Study\ONE\Example Segmentation\Codes\train_2\val_raw.json")
print("Success: {}".format(args.json_file))
5.check_image.py
from PIL import Image
import imghdr
import argparse
import os
# 功能：查看图片能否打开，有没有这个图片、是不是完好、没有损坏的图片
# 参数：图片路径
# 返回：True
error_image = []
def check_pic(path_pic):
#print(os.listdir(path_pic))
for image in sorted(os.listdir(path_pic)):
if not image.startswith('._', 0, 2):
#print(image)
#print(Image.open(image))
try:
img = Image.open(os.path.join(path_pic, image) )# 如果图片不存在，报错FileNotFoundError
img.load() # 如果图片不完整，报错OSError: image file is truncated
'''
result_type = imghdr.what(os.path.join(path_pic, image))
print(result_type)
if result_type == 'jpg':
print(image)
error_image.append(image)
print('error')
'''
except (FileNotFoundError):
print('FileNotFoundError!')
error_image.append(image)
except(OSError):
print("OSError:image file is truncated!")
error_image.append(image)
print("image" + image +' is ok')
else:
continue
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--input", default='/hdd2/wh/pascalraw/PASCALRAW/jpg', help='plz input your image path')
args = parser.parse_args()
print(args.input)
check_pic(args.input)
print(error_image)
#flag = check_pic(r"C:\\Users\\chenwei\\Desktop\\JPG")
#img = Image.open(os.path.join("C:\\Users\\chenwei\\Desktop\\JPG", '2014_004216.jpg') )# 如果图片不存在，报错FileNotFoundError
#print(img.load())
if __name__ == '__main__':
main()
6. vis_bbox_and_catogaries.py
可视化bbox和标签
# 可视化coco格式json标注中的box到图片上
import json
import shutil
import cv2
def select(json_path, outpath, image_path):
class = []
count = 0
json_file = open(json_path)
infos = json.load(json_file)
images = infos["images"]
annos = infos["annotations"]
assert len(images) == len(images)
for i in range(len(images)):
im_id = images[i]["id"]
im_path = image_path + "/" + images[i]["file_name"]
img = cv2.imread(im_path)
for j in range(len(annos)):
if annos[j]["image_id"] == im_id:
cate_id = annos[j]["category_id"]
if(cate_id == '0'):
class.append("bicycle")
if(cate_id == '1'):
class.append("car")
if(cate_id == '2'):
class.append("person")
x, y, w, h = annos[j]["bbox"]
x, y, w, h = int(x), int(y), int(w), int(h)
x2, y2 = x + w, y + h
# object_name = annos[j][""]
img = cv2.rectangle(img, (x, y), (x2, y2), (255, 0, 0), thickness=2)
cv.putText(img, class[count], (x, y + 20), cv.FONT_HERSHEY_COMPLEX, 2.0, (100, 200, 200), 3)
count = count + 1
img_name = outpath + "/" + images[i]["file_name"]
cv2.imwrite(img_name, img)
# continue
print(i)
print(class)
if __name__ == "__main__":
json_path = "/hdd2/wh/datasets/coco_raw/annotations/instances_train2017_jpg.json"
out_path = "/hdd2/wh/datasets/vis/"
image_path = "/hdd2/wh/datasets/coco_raw/train2017/"
select(json_path, out_path, image_path)
参考：
https://blog.csdn.net/mantoureganmian/article/details/47949101
https://blog.csdn.net/weixin_44692101/article/details/108502859