將數(shù)據(jù)集制作成VOC數(shù)據(jù)集格式的實例

#coding='utf-8'
import os
import numpy as np
 
def imgs_rename(imgs_path):
  imgs_labels_name = np.array(os.listdir(imgs_path)).reshape(-1,2)
  # 從 000001開始
  i = 1
  for img_label_name in imgs_labels_name:
    if img_label_name[0].endswith('.jpg'):
      # 修改圖片名稱
      img_old_name = os.path.join(os.path.abspath(imgs_path), img_label_name[0])
      # 類別+圖片編號  format(str(i),'0>3s') 填充對齊
      img_new_name = os.path.join(os.path.abspath(imgs_path), '00' + format(str(i),'0>4s') + '.jpg')
      os.rename(img_old_name, img_new_name)
      # 修改json文件名稱
      label_old_name = os.path.join(os.path.abspath(imgs_path), img_label_name[1])
      label_new_name = os.path.join(os.path.abspath(imgs_path), '00' + format(str(i), '0>4s') + '.json')
      os.rename(label_old_name, label_new_name)
      i = i + 1
 
if __name__=='__main__':
  # 讀取json文件的路徑
  root = "read_file_path"
 
  imgs_rename(root)

import json
import os
import numpy as np
import cv2
 
#讀取json格式文件，返回坐標
def read_json(file_name):
  file = open(file_name,'r',encoding='utf-8')
  set = json.load(file)
  # print("讀取完整信息：",set)
  coord = set['objects'][0]['seg'] # 只讀取第一個標注的車牌
  return coord
 
def save_imgs(imgs_jsons_files, imgs_path):
  # 提取圖片文件夾中的jpg文件名稱
  for idx in range(len(imgs_jsons_list)):
    if imgs_jsons_list[idx][-3:]=='jpg':
      img_name = imgs_jsons_list[idx]
      read_img_path = os.path.join(imgs_jsons_files, img_name)
      img = cv2.imread(read_img_path)
      save_img_path = os.path.join(imgs_path, img_name)
      cv2.imwrite(save_img_path, img)
 
def save_labels(imgs_jsons_files, labels_path):
  # 提取圖片文件夾中的json文件名稱
  for idx in range(len(imgs_jsons_list)):
    if imgs_jsons_list[idx][-4:] == 'json':
      json_name = imgs_jsons_list[idx]
 
      # 操作每一個json文件，讀取并保存坐標
      json_path = os.path.join(imgs_jsons_files, json_name)
      json_coord = read_json(json_path)
      if len(json_coord) > 8:
        print("標注坐標多于四個點的文件名稱：", json_name)
 
      # 提取左上和右下坐標
      roi_coord = []
      for idx in range(len(json_coord)):
        if idx == 0 or idx == 1 or idx == 4 or idx == 5:
          roi_coord.extend([json_coord[idx]])
      # 保存roi坐標到txt文件中
      label_path = labels_path + json_name[:6] + '.txt'
      np.savetxt(label_path, roi_coord)
 
if __name__=='__main__':
  print("loading......")
  # 讀取jpg json文件的路徑
  imgs_jsons_files = "Jpg_json_file_path"
 
  # 保存讀取的真實標簽路徑
  labels_path = "save_labels_path"
  if not os.path.exists(labels_path):
    os.mkdir(labels_path)
  # 保存讀取的圖片
  imgs_path = "sabe_imgs_path"
  if not os.path.exists(imgs_path):
    os.mkdir(imgs_path)
 
  imgs_jsons_list = os.listdir(imgs_jsons_files)
 
  save_imgs(imgs_jsons_files, imgs_path)
  save_labels(imgs_jsons_files, labels_path)
  print("done!!!")

# encoding = utf-8
import os
import numpy as np
import codecs
import cv2
 
def read_txt(label_path):
  file = open(label_path,'r',encoding='utf-8')
  label_lines = file.readlines()
  label = []
  for line in label_lines:
    one_line = float(line.strip().split('\n')[0])
    label.extend([one_line])
  return np.array(label,dtype=np.float64)
 
def covert_xml(label,xml_path, img_name, img_path):
  # 獲得圖片信息
  img = cv2.imread(img_path)
  height, width, depth = img.shape
  x_min,y_min,x_max,y_max = label
 
  xml = codecs.open(xml_path, 'w', encoding='utf-8')
  xml.write('<annotation>\n')
  xml.write('\t<folder>' + 'VOC2007' + '</folder>\n')
  xml.write('\t<filename>' + img_name + '</filename>\n')
  xml.write('\t<source>\n')
  xml.write('\t\t<database>The VOC 2007 Database</database>\n')
  xml.write('\t\t<annotation>Pascal VOC2007</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>faster</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(depth) + '</depth>\n')
  xml.write('\t</size>\n')
  xml.write('\t\t<segmented>0</segmented>\n')
  xml.write('\t<object>\n')
  xml.write('\t\t<name>plate</name>\n')
  xml.write('\t\t<pose>Unspecified</pose>\n')
  xml.write('\t\t<truncated>0</truncated>\n')
  xml.write('\t\t<difficult>0</difficult>\n')
  xml.write('\t\t<bndbox>\n')
  xml.write('\t\t\t<xmin>' + str(x_min) + '</xmin>\n')
  xml.write('\t\t\t<ymin>' + str(y_min) + '</ymin>\n')
  xml.write('\t\t\t<xmax>' + str(x_max) + '</xmax>\n')
  xml.write('\t\t\t<ymax>' + str(y_max) + '</ymax>\n')
  xml.write('\t\t</bndbox>\n')
  xml.write('\t</object>\n')
  xml.write('</annotation>')
 
if __name__=='__main__':
  labels_file_path = "D:/Code_py/VOC2007/labels/"
  imgs_file_path = "D:/Code_Py/VOC2007/imgs/"
 
  xmls_file_path = "D:/Code_py/VOC2007/xmls/"
  if not os.path.exists(xmls_file_path):
    os.mkdir(xmls_file_path)
 
  labels_name = os.listdir(labels_file_path)
  for label_name in labels_name:
    label_path = os.path.join(labels_file_path, label_name)
    label = read_txt(label_path)
 
    xml_name = label_name[:6]+'.xml'
    xml_path = os.path.join(xmls_file_path, xml_name)
 
    img_name = label_name[:6]+'.jpg'
    img_path = os.path.join(imgs_file_path, img_name)
 
    covert_xml(label, xml_path, img_name, img_path)

import os
import numpy as np
 
if __name__=='__main__':
  root = "save_path"
  train = open(root+"train.txt", 'w', encoding='utf-8')
  train_val = open(root+"trainval.txt", 'w', encoding='utf-8')
  test = open(root+"test.txt", 'w', encoding='utf-8')
  val = open(root+"val.txt", 'w', encoding='utf-8')
 
  imgs_path = os.path.join(root, "imgs")
 
  imgs_name = os.listdir(imgs_path)
 
  # 首先切分訓練驗證集和測試集
  train_val_img_info = []
  for img_name in imgs_name:
    x = np.random.uniform(0,1)
    img_info = str(img_name).strip().split('.')[0]
    # 隨機選取1/2比例的數(shù)據(jù)為測試集
    if x>0.5:
      train_val_img_info.append(img_info)
      train_val.writelines(img_info)
    else:
      test.writelines(img_info+'\n')
 
  # 然后切分訓練驗證集為訓練集和驗證集
  for img_name in train_val_img_info:
    x = np.random.uniform(0,1)
    if x>0.5:
      train.writelines(img_name+'\n')
    else:
      val.writelines(img_name+'\n')