{    "version": "3.6.16",    "flags": {},    "shapes": [      {        "label": "helmet",        "line_color": null,        "fill_color": null,        "points": [          [            131,            269          ],          [            388,            457          ]        ],        "shape_type": "rectangle"      }    ],    "lineColor": [      0,      255,      0,      128    ],    "fillColor": [      255,      0,      0,      128    ],    "imagePath": "004ffe6f-c3e2-3602-84a1-ecd5f437b113.jpg",    "imageData": ""   # too long ,so not show here    "imageHeight": 1080,    "imageWidth": 1920  }

import os  import glob  import pandas as pd  import xml.etree.ElementTree as ET    ## xml文件的路徑  os.chdir('./data/annotations/scratches')  path = 'C:/Users/Admin/Desktop/data/annotations/scratches' # 絕對路徑  img_path = 'C:/Users/Admin/Desktop/data/images'    def xml_to_csv(path):      xml_list = []      for xml_file in glob.glob(path + '/*.xml'):  #返回所有匹配的文件路徑列表。          tree = ET.parse(xml_file)          root = tree.getroot()            for member in root.findall('object'):  #            value = (root.find('filename').text,  #                     int(root.find('size')[0].text),  #                     int(root.find('size')[1].text),  #                     member[0].text,  #                     int(member[4][0].text),  #                     int(member[4][1].text),  #                     int(member[4][2].text),  #                     int(member[4][3].text)  #                     )              value = (img_path +'/' + root.find('filename').text,                       int(member[4][0].text),                       int(member[4][1].text),                       int(member[4][2].text),                       int(member[4][3].text),                       member[0].text                       )              xml_list.append(value)      #column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']      column_name = ['filename', 'xmin', 'ymin', 'xmax', 'ymax', 'class']      xml_df = pd.DataFrame(xml_list, columns=column_name)      return xml_df    if __name__ == '__main__':      image_path = path      xml_df = xml_to_csv(image_path)      ## 修改文件名稱      xml_df.to_csv('scratches.csv', index=None)      print('Successfully converted xml to csv.')

import os  import json  import numpy as np  import pandas as pd  import glob  import cv2  import shutil  from IPython import embed  from sklearn.model_selection import train_test_split  np.random.seed(41)    # 0為背景  classname_to_id = {"scratches": 1,"inclusion": 2}    class Csv2CoCo:        def __init__(self,image_dir,total_annos):          self.images = []          self.annotations = []          self.categories = []          self.img_id = 0          self.ann_id = 0          self.image_dir = image_dir          self.total_annos = total_annos        def save_coco_json(self, instance, save_path):          json.dump(instance, open(save_path, 'w'), ensure_ascii=False, indent=2)  # indent=2 更加美觀顯示        # 由txt文件構建COCO      def to_coco(self, keys):          self._init_categories()          for key in keys:              self.images.append(self._image(key))              shapes = self.total_annos[key]              for shape in shapes:                  bboxi = []                  for cor in shape[:-1]:                      bboxi.append(int(cor))                  label = shape[-1]                  annotation = self._annotation(bboxi,label)                  self.annotations.append(annotation)                  self.ann_id += 1              self.img_id += 1          instance = {}          instance['info'] = 'spytensor created'          instance['license'] = ['license']          instance['images'] = self.images          instance['annotations'] = self.annotations          instance['categories'] = self.categories          return instance        # 構建類別      def _init_categories(self):          for k, v in classname_to_id.items():              category = {}              category['id'] = v              category['name'] = k              self.categories.append(category)        # 構建COCO的image字段      def _image(self, path):          image = {}          img = cv2.imread(self.image_dir + path)          image['height'] = img.shape[0]          image['width'] = img.shape[1]          image['id'] = self.img_id          image['file_name'] = path          return image        # 構建COCO的annotation字段      def _annotation(self, shape,label):          # label = shape[-1]          points = shape[:4]          annotation = {}          annotation['id'] = self.ann_id          annotation['image_id'] = self.img_id          annotation['category_id'] = int(classname_to_id[label])          annotation['segmentation'] = self._get_seg(points)          annotation['bbox'] = self._get_box(points)          annotation['iscrowd'] = 0          annotation['area'] = 1.0          return annotation        # COCO的格式： [x1,y1,w,h] 對應COCO的bbox格式      def _get_box(self, points):          min_x = points[0]          min_y = points[1]          max_x = points[2]          max_y = points[3]          return [min_x, min_y, max_x - min_x, max_y - min_y]      # segmentation      def _get_seg(self, points):          min_x = points[0]          min_y = points[1]          max_x = points[2]          max_y = points[3]          h = max_y - min_y          w = max_x - min_x          a = []          a.append([min_x,min_y, min_x,min_y+0.5*h, min_x,max_y, min_x+0.5*w,max_y, max_x,max_y, max_x,max_y-0.5*h, max_x,min_y, max_x-0.5*w,min_y])          return a      if __name__ == '__main__':        ## 修改目錄      csv_file = "data/annotations/scratches/scratches.csv"      image_dir = "data/images/"      saved_coco_path = "./"      # 整合csv格式標註文件      total_csv_annotations = {}      annotations = pd.read_csv(csv_file,header=None).values      for annotation in annotations:          key = annotation[0].split(os.sep)[-1]          value = np.array([annotation[1:]])          if key in total_csv_annotations.keys():              total_csv_annotations[key] = np.concatenate((total_csv_annotations[key],value),axis=0)          else:              total_csv_annotations[key] = value      # 按照鍵值劃分數據      total_keys = list(total_csv_annotations.keys())      train_keys, val_keys = train_test_split(total_keys, test_size=0.2)      print("train_n:", len(train_keys), 'val_n:', len(val_keys))      ## 創建必須的文件夾      if not os.path.exists('%ssteel/annotations/'%saved_coco_path):          os.makedirs('%ssteel/annotations/'%saved_coco_path)      if not os.path.exists('%ssteel/images/train/'%saved_coco_path):          os.makedirs('%ssteel/images/train/'%saved_coco_path)      if not os.path.exists('%ssteel/images/val/'%saved_coco_path):          os.makedirs('%ssteel/images/val/'%saved_coco_path)      ## 把訓練集轉化為COCO的json格式      l2c_train = Csv2CoCo(image_dir=image_dir,total_annos=total_csv_annotations)      train_instance = l2c_train.to_coco(train_keys)      l2c_train.save_coco_json(train_instance, '%ssteel/annotations/instances_train.json'%saved_coco_path)      for file in train_keys:          shutil.copy(image_dir+file,"%ssteel/images/train/"%saved_coco_path)      for file in val_keys:          shutil.copy(image_dir+file,"%ssteel/images/val/"%saved_coco_path)      ## 把驗證集轉化為COCO的json格式      l2c_val = Csv2CoCo(image_dir=image_dir,total_annos=total_csv_annotations)      val_instance = l2c_val.to_coco(val_keys)      l2c_val.save_coco_json(val_instance, '%ssteel/annotations/instances_val.json'%saved_coco_path)