大学生人工智能挑战赛—智慧零售 从目标检测到算法落地

#将所给的数据转为voc数据集格式
import os
import numpy as np
import codecs
import json
from glob import glob
import cv2
import shutil
from sklearn.model_selection import train_test_split
# 1.标签路径
labelme_path = "./2022 年（第 15 届）中国大学生计算机设计大赛人工智能挑战赛-智慧零售赛项数据集/TrainingDataset/"  # 使用labelme打的标签（包含每一张照片和对应json格式的标签）
saved_path = "./VOCdevkit/VOC2007/"  # 保存路径
# 2.voc格式的文件夹，如果没有，就创建一个
if not os.path.exists(saved_path + "Annotations"):
    os.makedirs(saved_path + "Annotations")
if not os.path.exists(saved_path + "JPEGImages/"):
    os.makedirs(saved_path + "JPEGImages/")
if not os.path.exists(saved_path + "ImageSets/Main/"):
    os.makedirs(saved_path + "ImageSets/Main/")
# 3.获取json文件
files = glob(labelme_path + "*.json")
files = [i.split("/")[-1].split(".json")[0] for i in files]  # 获取每一个json文件名
print(len(files))
# 4.读取每一张照片和对应标签，生成xml
for json_file_ in files:
    json_filename = labelme_path + json_file_ + ".json"
    json_file = json.load(open(json_filename, "r", encoding="utf-8"))
    height, width, channels = cv2.imread(labelme_path + json_file_ + ".png").shape
    with codecs.open(saved_path + "Annotations/" + json_file_ + ".xml", "w", "utf-8") as xml:
        xml.write('<annotation>\n')
        xml.write('\t<folder>' + 'UAV_data' + '</folder>\n')
        xml.write('\t<filename>' + json_file_ + ".png" + '</filename>\n')
        xml.write('\t<source>\n')
        xml.write('\t\t<database>The UAV autolanding</database>\n')
        xml.write('\t\t<annotation>UAV AutoLanding</annotation>\n')
        xml.write('\t\t<image>flickr</image>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t</source>\n')
        xml.write('\t<owner>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t\t<name>ChaojieZhu</name>\n')
        xml.write('\t</owner>\n')
        xml.write('\t<size>\n')
        xml.write('\t\t<width>' + str(width) + '</width>\n')
        xml.write('\t\t<height>' + str(height) + '</height>\n')
        xml.write('\t\t<depth>' + str(channels) + '</depth>\n')
        xml.write('\t</size>\n')
        xml.write('\t\t<segmented>0</segmented>\n')
        for multi in json_file["labels"]:
            #print(len(multi))
            xmin=multi['x1']
            xmax=multi['x2']
            ymin=multi['y1']
            ymax=multi['y2']
            label = multi["name"]
            xml.write('\t<object>\n')
            xml.write('\t\t<name>' + label + '</name>\n')
            xml.write('\t\t<pose>Unspecified</pose>\n')
            xml.write('\t\t<truncated>1</truncated>\n')
            xml.write('\t\t<difficult>0</difficult>\n')
            xml.write('\t\t<bndbox>\n')
            xml.write('\t\t\t<xmin>' + str(xmin) + '</xmin>\n')
            xml.write('\t\t\t<ymin>' + str(ymin) + '</ymin>\n')
            xml.write('\t\t\t<xmax>' + str(xmax) + '</xmax>\n')
            xml.write('\t\t\t<ymax>' + str(ymax) + '</ymax>\n')
            xml.write('\t\t</bndbox>\n')
            xml.write('\t</object>\n')
            print(json_filename, xmin, ymin, xmax, ymax, label)
        xml.write('</annotation>')
# 5.复制图片到 VOC2007/JPEGImages/下
image_files = glob(labelme_path + "*.png")
print("copy image files to VOC007/JPEGImages/")
for image in image_files:
    shutil.copy(image, saved_path + "JPEGImages/")
# 6.划分train，test，val格式数据集
txtsavepath = saved_path + "ImageSets/Main/"
ftrainval = open(txtsavepath + '/trainval.txt', 'w')
ftest = open(txtsavepath + '/test.txt', 'w')
ftrain = open(txtsavepath + '/train.txt', 'w')
fval = open(txtsavepath + '/val.txt', 'w')
total_files = glob("./VOCdevkit/VOC2007/Annotations/*.xml")
total_files = [i.split("/")[-1].split(".xml")[0] for i in total_files]
# test_filepath = "/Users/ysj/Desktop/2022 年（第 15 届）中国大学生计算机设计大赛人工智能挑战赛-智慧零售赛项数据集/TestDataset/"
for file in total_files:
    ftrainval.write(file + "\n")
# test
# for file in os.listdir(test_filepath):
#    ftest.write(file.split(".png")[0] + "\n")
# split，根据test_size这个参数来确定test的数量
train_files, val_files = train_test_split(total_files, test_size=0.001, random_state=42)
# train
for file in train_files:
    ftrain.write(file + "\n")
    #ftest.write(file + "\n")
# val
for file in val_files:
    fval.write(file + "\n")
ftrainval.close()
ftrain.close()
fval.close()
#ftest.close()
复制代码