1 图片的重命名 2 对xml文件的图片来进行画框 3 制作coco数据集

# -*- coding:utf8 -*-

import os

class BatchRename():
    '''
    批量重命名文件夹中的图片文件

    '''
    def __init__(self):
        self.path = 'D:/素材/污损纸张'  #表示需要命名处理的文件夹 D:\素材\垃圾桶

    def rename(self):
        filelist = os.listdir(self.path) #获取文件路径
        total_num = len(filelist) #获取文件长度（个数）
        i = 1  #表示文件的命名是从1开始的
        for item in filelist:
            if item.endswith('.jpg'):  #初始的图片的格式为jpg格式的（或者源文件是png格式及其他格式，后面的转换格式就可以调整为自己需要的格式即可）
                src = os.path.join(os.path.abspath(self.path), item)
                dst = os.path.join(os.path.abspath(self.path), 'wl_stained_paper' + '0000' + format(str(i), '0>3s') + '.jpg')#处理后的格式也为jpg格式的，当然这里可以改成png格式
                #dst = os.path.join(os.path.abspath(self.path), '0000' + format(str(i), '0>3s') + '.jpg')    这种情况下的命名格式为0000000.jpg形式，可以自主定义想要的格式
                try:
                    os.rename(src, dst)
                    print ('converting %s to %s ...' % (src, dst))
                    i = i + 1
                except:
                    continue
        print ('total %d to rename & converted %d jpgs' % (total_num, i))

if __name__ == '__main__':
    demo = BatchRename()
    demo.rename()

画框

import os
import xml.dom.minidom
import cv2 as cv


ImgPath = '/home/liuyuankai/datasets/myNewVOC/VOC2007/JPEGImages/'  # 图片地址
AnnoPath = '/home/liuyuankai/datasets/myNewVOC/VOC2007/Annotations/'  # xml文件地址
save_path = './problem'

def draw_anchor(ImgPath, AnnoPath, save_path):
    imagelist = os.listdir(ImgPath)

    for image in imagelist:
        image_pre, ext = os.path.splitext(image)
        imgfile = ImgPath + image
        xmlfile = AnnoPath + image_pre + '.xml'
        # print(image)
        # 打开xml文档
        DOMTree = xml.dom.minidom.parse(xmlfile)
        # 得到文档元素对象
        collection = DOMTree.documentElement
        # 读取图片
        img = cv.imread(imgfile, cv.IMREAD_COLOR + cv.IMREAD_IGNORE_ORIENTATION)
        filenamelist = collection.getElementsByTagName("filename")
        filename = filenamelist[0].childNodes[0].data
        print(filename)
        # 得到标签名为object的信息
        objectlist = collection.getElementsByTagName("object")

        for objects in objectlist:
            # 每个object中得到子标签名为name的信息
            namelist = objects.getElementsByTagName('name')
            # 通过此语句得到具体的某个name的值
            objectname = namelist[0].childNodes[0].data
            # print(objectname)

            bndbox = objects.getElementsByTagName('bndbox')
            # print(bndbox)
            for box in bndbox:
                x1_list = box.getElementsByTagName('xmin')
                x1 = int(x1_list[0].childNodes[0].data)
                y1_list = box.getElementsByTagName('ymin')
                y1 = int(y1_list[0].childNodes[0].data)
                x2_list = box.getElementsByTagName('xmax')  # 注意坐标，看是否需要转换
                x2 = int(x2_list[0].childNodes[0].data)
                y2_list = box.getElementsByTagName('ymax')
                y2 = int(y2_list[0].childNodes[0].data)
                cv.rectangle(img, (x1, y1), (x2, y2), (255, 255, 255), thickness=2)
                cv.putText(img, objectname, (x1, y1), cv.FONT_HERSHEY_COMPLEX, 0.7, (0, 255, 0),
                           thickness=2)
                # cv.imshow('head', img)
                cv.imwrite(save_path + '/' + image, img)  #


if __name__ == "__main__":
    draw_anchor(ImgPath, AnnoPath, save_path)

制作coco数据集

# -*- coding=utf-8 -*-
# !/usr/bin/python

import os
import shutil
import numpy as np
import json
import xml.etree.ElementTree as ET
from tqdm.autonotebook import tqdm

# 检测框的ID起始值
START_BOUNDING_BOX_ID = 0
# 类别列表无必要预先创建，程序中会根据所有图像中包含的ID来创建并更新
PRE_DEFINE_CATEGORIES = {}


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 NotImplementedError('Can not find %s in %s.' % (name, root.tag))
    if length > 0 and len(vars) != length:
        raise NotImplementedError('The size of %s is supposed to be %d, but is %d.' % (name, length, len(vars)))
    if length == 1:
        vars = vars[0]
    return vars


# 得到图片唯一标识号
def get_filename_as_int(filename):
    try:
        filename = os.path.splitext(filename)[0]
        return int(filename)
    except:
        raise NotImplementedError('Filename %s is supposed to be an integer.' % (filename))


def convert(xml_list, xml_dir, json_file):
    '''
    :param xml_list: 需要转换的XML文件列表
    :param xml_dir: XML的存储文件夹
    :param json_file: 导出json文件的路径
    :return: None
    '''
    ID = 0
    list_fp = xml_list
    # 标注基本结构
    json_dict = {"images": [],
                 "type": "instances",
                 "annotations": [],
                 "categories": []}
    categories = PRE_DEFINE_CATEGORIES
    bnd_id = START_BOUNDING_BOX_ID
    xmlHandleBar = tqdm(list_fp)
    for line in xmlHandleBar:
        xmlHandleBar.set_description("Processing %s" % line)
        line = line.strip()
        # 解析XML
        xml_f = os.path.join(xml_dir, line)
        tree = ET.parse(xml_f)
        root = tree.getroot()
        path = get(root, 'path')
        # 取出图片名字
        filename = str(line).split('.')[0] + ".jpg"
        # if len(path) == 1:
        #     filename = get_and_check(root, 'filename', 1).text#lyk修改  old code: os.path.basename(path[0].text)
        # elif len(path) == 0:
        #     filename = get_and_check(root, 'filename', 1).text
        # else:
        #     raise NotImplementedError('%d paths found in %s'%(len(path), line))
        ## The filename must be a number
        ID = ID + 1
        image_id = ID  # get_filename_as_int(filename)  # 图片ID
        # print("===>{}".format(image_id))
        size = get_and_check(root, 'size', 1)
        # 图片的基本信息
        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)
        ## Cruuently we do not support segmentation
        #  segmented = get_and_check(root, 'segmented', 1).text
        #  assert segmented == '0'
        # 处理每个标注的检测框
        for obj in get(root, 'object'):
            # 取出检测框类别名称
            category = get_and_check(obj, 'name', 1).text
            # 更新类别ID字典
            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)
            annotation = dict()
            annotation['area'] = o_width * o_height
            annotation['iscrowd'] = 0
            annotation['image_id'] = image_id
            annotation['bbox'] = [xmin, ymin, o_width, o_height]
            annotation['category_id'] = category_id
            annotation['id'] = bnd_id
            annotation['ignore'] = 0
            # 设置分割数据，点的顺序为逆时针方向
            annotation['segmentation'] = [[xmin, ymin, xmin, ymax, xmax, ymax, xmax, ymin]]

            json_dict['annotations'].append(annotation)
            bnd_id = bnd_id + 1

    # 写入类别ID字典
    for cate, cid in categories.items():
        cat = {'supercategory': 'none', 'id': cid, 'name': cate}
        json_dict['categories'].append(cat)
    # 导出到json
    json_fp = open(json_file, 'w')
    json_str = json.dumps(json_dict, indent=4)
    json_fp.write(json_str)
    json_fp.close()


if __name__ == '__main__':
    root_path = "/home/zhanglingyun/trainval/VOC2007/"
    saveto_path = "/home/zhanglingyun/retinanet/data/coco/images/"
    xml_dir = os.path.join(root_path, 'Annotations')

    xml_labels = os.listdir(os.path.join(root_path, 'Annotations'))
    np.random.shuffle(xml_labels)
    split_point = int(len(xml_labels) / 10)  # 用1/10的来做验证

    # validation data
    print("==========validation data===========")
    xml_list = xml_labels[0:split_point]
    json_file = '/home/zhanglingyun/retinanet/data/coco/annotations/instances_val2017.json'
    convert(xml_list, xml_dir, json_file)
    progress_bar_val = tqdm(xml_list)
    for xml_file in progress_bar_val:
        progress_bar_val.set_description("coping val  data...")
        img_name = xml_file[:-4] + '.jpg'
        shutil.copy(os.path.join(root_path, 'JPEGImages', img_name),
                    os.path.join(saveto_path, 'val2017', img_name))

    # train data
    print("============train data=========")
    xml_list = xml_labels[split_point:]
    json_file = '/home/zhanglingyun/retinanet/data/coco/annotations/instances_train2017.json'
    convert(xml_list, xml_dir, json_file)
    progress_bar_train = tqdm(xml_list)
    for xml_file in progress_bar_train:
        progress_bar_train.set_description("coping train  data...")
        img_name = xml_file[:-4] + '.jpg'
        shutil.copy(os.path.join(root_path, 'JPEGImages', img_name),
                    os.path.join(saveto_path, 'train2017', img_name))