将labelme标注的json文件转换为yolo形式
yolo模型的学习是学习深度学习的一个很关键的，在使用yolov5模型进行训练数据集时，必不可少要对文件进行转换，这里是详细说明将labelme标注的json文件转换为yolo形式的过程。
·
最近因为在跑yolov5模型，需要使用数据集进行训练。有时候对数据集进行文件形式转换也是一个很重要的点，所以这里讲一下将labelme标注的json文件转换为yolo形式。个人也刚接触，可能在表述上面会有错误，所以请包含。
这是原先未修改前的代码（会出现一点小问题）：
labelme2yolo.py：
'''
Created on Aug 18, 2021
@author: xiaosonh
'''
import os
import sys
import argparse
import shutil
import math
from collections import OrderedDict
import json
import cv2
import PIL.Image
from sklearn.model_selection import train_test_split
from labelme import utils
class Labelme2YOLO(object):
def __init__(self, json_dir):
self._json_dir = json_dir
self._label_id_map = self._get_label_id_map(self._json_dir)
def _make_train_val_dir(self):
self._label_dir_path = os.path.join(self._json_dir,
'YOLODataset/labels/')
self._image_dir_path = os.path.join(self._json_dir,
'YOLODataset/images/')
for yolo_path in (os.path.join(self._label_dir_path + 'train/'),
os.path.join(self._label_dir_path + 'val/'),
os.path.join(self._image_dir_path + 'train/'),
os.path.join(self._image_dir_path + 'val/')):
if os.path.exists(yolo_path):
shutil.rmtree(yolo_path)
os.makedirs(yolo_path)
def _get_label_id_map(self, json_dir):
label_set = set()
for file_name in os.listdir(json_dir):
if file_name.endswith('json'):
json_path = os.path.join(json_dir, file_name)
data = json.load(open(json_path))
for shape in data['shapes']:
label_set.add(shape['label'])
return OrderedDict([(label, label_id) \
for label_id, label in enumerate(label_set)])
def _train_test_split(self, folders, json_names, val_size):
if len(folders) > 0 and 'train' in folders and 'val' in folders:
train_folder = os.path.join(self._json_dir, 'train/')
train_json_names = [train_sample_name + '.json' \
for train_sample_name in os.listdir(train_folder) \
if os.path.isdir(os.path.join(train_folder, train_sample_name))]
val_folder = os.path.join(self._json_dir, 'val/')
val_json_names = [val_sample_name + '.json' \
for val_sample_name in os.listdir(val_folder) \
if os.path.isdir(os.path.join(val_folder, val_sample_name))]
return train_json_names, val_json_names
train_idxs, val_idxs = train_test_split(range(len(json_names)),
test_size=val_size)
train_json_names = [json_names[train_idx] for train_idx in train_idxs]
val_json_names = [json_names[val_idx] for val_idx in val_idxs]
return train_json_names, val_json_names
def convert(self, val_size):
json_names = [file_name for file_name in os.listdir(self._json_dir) \
if os.path.isfile(os.path.join(self._json_dir, file_name)) and \
file_name.endswith('.json')]
folders = [file_name for file_name in os.listdir(self._json_dir) \
if os.path.isdir(os.path.join(self._json_dir, file_name))]
train_json_names, val_json_names = self._train_test_split(folders, json_names, val_size)
self._make_train_val_dir()
# convert labelme object to yolo format object, and save them to files
# also get image from labelme json file and save them under images folder
for target_dir, json_names in zip(('train/', 'val/'),
(train_json_names, val_json_names)):
for json_name in json_names:
json_path = os.path.join(self._json_dir, json_name)
json_data = json.load(open(json_path))
print('Converting %s for %s ...' % (json_name, target_dir.replace('/', '')))
img_path = self._save_yolo_image(json_data,
json_name,
self._image_dir_path,
target_dir)
yolo_obj_list = self._get_yolo_object_list(json_data, img_path)
self._save_yolo_label(json_name,
self._label_dir_path,
target_dir,
yolo_obj_list)
print('Generating dataset.yaml file ...')
self._save_dataset_yaml()
def convert_one(self, json_name):
json_path = os.path.join(self._json_dir, json_name)
json_data = json.load(open(json_path))
print('Converting %s ...' % json_name)
img_path = self._save_yolo_image(json_data, json_name,
self._json_dir, '')
yolo_obj_list = self._get_yolo_object_list(json_data, img_path)
self._save_yolo_label(json_name, self._json_dir,
'', yolo_obj_list)
def _get_yolo_object_list(self, json_data, img_path):
yolo_obj_list = []
img_h, img_w, _ = cv2.imread(img_path).shape
for shape in json_data['shapes']:
# labelme circle shape is different from others
# it only has 2 points, 1st is circle center, 2nd is drag end point
if shape['shape_type'] == 'circle':
yolo_obj = self._get_circle_shape_yolo_object(shape, img_h, img_w)
else:
yolo_obj = self._get_other_shape_yolo_object(shape, img_h, img_w)
yolo_obj_list.append(yolo_obj)
return yolo_obj_list
def _get_circle_shape_yolo_object(self, shape, img_h, img_w):
obj_center_x, obj_center_y = shape['points'][0]
radius = math.sqrt((obj_center_x - shape['points'][1][0]) ** 2 +
(obj_center_y - shape['points'][1][1]) ** 2)
obj_w = 2 * radius
obj_h = 2 * radius
yolo_center_x= round(float(obj_center_x / img_w), 6)
yolo_center_y = round(float(obj_center_y / img_h), 6)
yolo_w = round(float(obj_w / img_w), 6)
yolo_h = round(float(obj_h / img_h), 6)
label_id = self._label_id_map[shape['label']]
return label_id, yolo_center_x, yolo_center_y, yolo_w, yolo_h
def _get_other_shape_yolo_object(self, shape, img_h, img_w):
def __get_object_desc(obj_port_list):
__get_dist = lambda int_list: max(int_list) - min(int_list)
x_lists = [port[0] for port in obj_port_list]
y_lists = [port[1] for port in obj_port_list]
return min(x_lists), __get_dist(x_lists), min(y_lists), __get_dist(y_lists)
obj_x_min, obj_w, obj_y_min, obj_h = __get_object_desc(shape['points'])
yolo_center_x= round(float((obj_x_min + obj_w / 2.0) / img_w), 6)
yolo_center_y = round(float((obj_y_min + obj_h / 2.0) / img_h), 6)
yolo_w = round(float(obj_w / img_w), 6)
yolo_h = round(float(obj_h / img_h), 6)
label_id = self._label_id_map[shape['label']]
return label_id, yolo_center_x, yolo_center_y, yolo_w, yolo_h
def _save_yolo_label(self, json_name, label_dir_path, target_dir, yolo_obj_list):
txt_path = os.path.join(label_dir_path,
target_dir,
json_name.replace('.json', '.txt'))
with open(txt_path, 'w+') as f:
for yolo_obj_idx, yolo_obj in enumerate(yolo_obj_list):
yolo_obj_line = '%s %s %s %s %s\n' % yolo_obj \
if yolo_obj_idx + 1 != len(yolo_obj_list) else \
'%s %s %s %s %s' % yolo_obj
f.write(yolo_obj_line)
def _save_yolo_image(self, json_data, json_name, image_dir_path, target_dir):
img_name = json_name.replace('.json', '.png')
img_path = os.path.join(image_dir_path, target_dir,img_name)
if not os.path.exists(img_path):
img = utils.img_b64_to_arr(json_data['imageData'])
PIL.Image.fromarray(img).save(img_path)
return img_path
def _save_dataset_yaml(self):
yaml_path = os.path.join(self._json_dir, 'YOLODataset/', 'dataset.yaml')
with open(yaml_path, 'w+') as yaml_file:
yaml_file.write('train: %s\n' % \
os.path.join(self._image_dir_path, 'train/'))
yaml_file.write('val: %s\n\n' % \
os.path.join(self._image_dir_path, 'val/'))
yaml_file.write('nc: %i\n\n' % len(self._label_id_map))
names_str = ''
for label, _ in self._label_id_map.items():
names_str += "'%s', " % label
names_str = names_str.rstrip(', ')
yaml_file.write('names: [%s]' % names_str)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--json_dir',type=str,
help='Please input the path of the labelme json files.')
parser.add_argument('--val_size',type=float, nargs='?', default=None,
help='Please input the validation dataset size, for example 0.1 ')
parser.add_argument('--json_name',type=str, nargs='?', default=None,
help='If you put json name, it would convert only one json file to YOLO.')
args = parser.parse_args(sys.argv[1:])
convertor = Labelme2YOLO(args.json_dir)
if args.json_name is None:
convertor.convert(val_size=args.val_size)
else:
convertor.convert_one(args.json_name)
yaml文件中要填写最后转换出来存放的位置，记得要确保路径是存在的。
首先是将代码直接进行运行，会出现这样的错误：
因为指向这个位置，让我一直纠结在这个地方进行修改，然而一旦修改了ntpath.py文件后，python环境就遭到破坏，出现了一系列问题，查找了很多方法都没能解决。
后面通过查找了解到，可以通过命令行去执行该程序。命令行命令参考labelme2yolo官网：labelme2yolo · PyPI
因为我执行了 labelme2yolo --json_dir + json文件路径 + --val_size0.15 --test_size 0.15出现下面的错误：
后面我使用python命令来对labelme2yolo.py程序进行执行，执行命令为：python labelme2yolo.py --json_dir + json文件路径 + --val_size 0.15 --test_size 0.15
由于我的labelme2yolo.py文件中没有test_size所以这里把它去掉，否则会出现下面的错误：
因此最后我的执行命令为：python labelme2yolo.py --json_dir + json文件路径 + --val_size 0.15
这里又出现了这样的错误：
通过去print这个data的数据知道data是空的，所以导致在这里获取不到shapes的值，所以程序报错误。
错误代码位置：
通过一步步调试知道是在使用json.load()方法读取文件数据的时候出现了问题，读取不到数据，后面通过改变读取文件数据的方法得以解决。则是使用read()方法对该data的数据进行读取，代码如下（将data = json.load(open(json_path))换掉）：
with open(json_path, 'r', encoding='utf-8') as fp:
data = fp.read()
data = json.loads(data) 再次执行程序，这里出现了问题：
后面了解到可能是没有对文件进行解码，所以出现了读取不到的情况，对json_data使用json.loads（）方法进行解码。json.loads()和json.load()方法的区别如下：
再次执行程序可以发现该部分问题解决，然而在下一个地方出现同样获取不到文件数据的情况，所以第一反应就是使用同样的方法进行替换，但并没有得到解决。这时就想着是不是因为不同的方法对使用的文件等某些方面有一定的限制，所以查找了其他的获取方法，最后在使用readline()方法时得以解决。
在这里就把所有的问题解决了，在解决过程中也是很波折，所以想通过写文章的形式记录下来，以供自己后面回顾。最后运行出来的结果是（图片会生成在相应的路径中）：
最终代码：
labelme2yolo.py：
'''
Created on Aug 18, 2021
@author: xiaosonh
'''
import os
import sys
import argparse
import shutil
import math
from collections import OrderedDict
import json
import cv2
import PIL.Image
from sklearn.model_selection import train_test_split
from labelme import utils
class Labelme2YOLO(object):
def __init__(self, json_dir):
self._json_dir = json_dir
self._label_id_map = self._get_label_id_map(self._json_dir)
def _make_train_val_dir(self):
self._label_dir_path = os.path.join(self._json_dir,
'D:/wc/YOLODataset/labels/')
self._image_dir_path = os.path.join(self._json_dir,
'D:/wc/YOLODataset/images/')
for yolo_path in (os.path.join(self._label_dir_path + 'train/'),
os.path.join(self._label_dir_path + 'val/'),
os.path.join(self._image_dir_path + 'train/'),
os.path.join(self._image_dir_path + 'val/')):
if os.path.exists(yolo_path):
shutil.rmtree(yolo_path)
os.makedirs(yolo_path)
def _get_label_id_map(self, json_dir):
label_set = set()
for file_name in os.listdir(json_dir):
# print(file_name)
if file_name.endswith('json'):
json_path = os.path.join(json_dir, file_name)
with open(json_path, 'r', encoding='utf-8') as fp:
# print(type(fp))
data = fp.read()
# print(type(data))
# data = json.load(open(json_path))
# print(data)
# data["shapes"] = json.loads(data["shapes"])
data = json.loads(data)
for shape in data['shapes']:
label_set.add(shape['label'])
return OrderedDict([(label, label_id) \
for label_id, label in enumerate(label_set)])
def _train_test_split(self, folders, json_names, val_size):
if len(folders) > 0 and 'train' in folders and 'val' in folders:
train_folder = os.path.join(self._json_dir, 'train/')
train_json_names = [train_sample_name + '.json' \
for train_sample_name in os.listdir(train_folder) \
if os.path.isdir(os.path.join(train_folder, train_sample_name))]
val_folder = os.path.join(self._json_dir, 'val/')
val_json_names = [val_sample_name + '.json' \
for val_sample_name in os.listdir(val_folder) \
if os.path.isdir(os.path.join(val_folder, val_sample_name))]
return train_json_names, val_json_names
train_idxs, val_idxs = train_test_split(range(len(json_names)),
test_size=val_size)
train_json_names = [json_names[train_idx] for train_idx in train_idxs]
val_json_names = [json_names[val_idx] for val_idx in val_idxs]
return train_json_names, val_json_names
def convert(self, val_size):
json_names = [file_name for file_name in os.listdir(self._json_dir) \
if os.path.isfile(os.path.join(self._json_dir, file_name)) and \
file_name.endswith('.json')]
folders = [file_name for file_name in os.listdir(self._json_dir) \
if os.path.isdir(os.path.join(self._json_dir, file_name))]
train_json_names, val_json_names = self._train_test_split(folders, json_names, val_size)
self._make_train_val_dir()
# convert labelme object to yolo format object, and save them to files
# also get image from labelme json file and save them under images folder
for target_dir, json_names in zip(('train/', 'val/'),
(train_json_names, val_json_names)):
for json_name in json_names:
json_path = os.path.join(self._json_dir, json_name)
# print(json_path)
with open(json_path) as f:
json_data = f.readline()
# print(json_data)
# json_data = json.load(open(json_path))
print('Converting %s for %s ...' % (json_name, target_dir.replace('/', '')))
img_path = self._save_yolo_image(json_data,
json_name,
self._image_dir_path,
target_dir)
yolo_obj_list = self._get_yolo_object_list(json_data, img_path)
self._save_yolo_label(json_name,
self._label_dir_path,
target_dir,
yolo_obj_list)
print('Generating dataset.yaml file ...')
self._save_dataset_yaml()
def convert_one(self, json_name):
json_path = os.path.join(self._json_dir, json_name)
json_data = json.load(open(json_path))
print('Converting %s ...' % json_name)
img_path = self._save_yolo_image(json_data, json_name,
self._json_dir, '')
yolo_obj_list = self._get_yolo_object_list(json_data, img_path)
self._save_yolo_label(json_name, self._json_dir,
'', yolo_obj_list)
def _get_yolo_object_list(self, json_data, img_path):
yolo_obj_list = []
img_h, img_w, _ = cv2.imread(img_path).shape
# print(json_data)
json_data = json.loads(json_data)
# print(json_data)
for shape in json_data['shapes']:
# labelme circle shape is different from others
# it only has 2 points, 1st is circle center, 2nd is drag end point
if shape['shape_type'] == 'circle':
yolo_obj = self._get_circle_shape_yolo_object(shape, img_h, img_w)
else:
yolo_obj = self._get_other_shape_yolo_object(shape, img_h, img_w)
yolo_obj_list.append(yolo_obj)
return yolo_obj_list
def _get_circle_shape_yolo_object(self, shape, img_h, img_w):
obj_center_x, obj_center_y = shape['points'][0]
radius = math.sqrt((obj_center_x - shape['points'][1][0]) ** 2 +
(obj_center_y - shape['points'][1][1]) ** 2)
obj_w = 2 * radius
obj_h = 2 * radius
yolo_center_x= round(float(obj_center_x / img_w), 6)
yolo_center_y = round(float(obj_center_y / img_h), 6)
yolo_w = round(float(obj_w / img_w), 6)
yolo_h = round(float(obj_h / img_h), 6)
label_id = self._label_id_map[shape['label']]
return label_id, yolo_center_x, yolo_center_y, yolo_w, yolo_h
def _get_other_shape_yolo_object(self, shape, img_h, img_w):
def __get_object_desc(obj_port_list):
__get_dist = lambda int_list: max(int_list) - min(int_list)
x_lists = [port[0] for port in obj_port_list]
y_lists = [port[1] for port in obj_port_list]
return min(x_lists), __get_dist(x_lists), min(y_lists), __get_dist(y_lists)
obj_x_min, obj_w, obj_y_min, obj_h = __get_object_desc(shape['points'])
yolo_center_x= round(float((obj_x_min + obj_w / 2.0) / img_w), 6)
yolo_center_y = round(float((obj_y_min + obj_h / 2.0) / img_h), 6)
yolo_w = round(float(obj_w / img_w), 6)
yolo_h = round(float(obj_h / img_h), 6)
label_id = self._label_id_map[shape['label']]
return label_id, yolo_center_x, yolo_center_y, yolo_w, yolo_h
def _save_yolo_label(self, json_name, label_dir_path, target_dir, yolo_obj_list):
txt_path = os.path.join(label_dir_path,
target_dir,
json_name.replace('.json', '.txt'))
with open(txt_path, 'w+') as f:
for yolo_obj_idx, yolo_obj in enumerate(yolo_obj_list):
yolo_obj_line = '%s %s %s %s %s\n' % yolo_obj \
if yolo_obj_idx + 1 != len(yolo_obj_list) else \
'%s %s %s %s %s' % yolo_obj
f.write(yolo_obj_line)
def _save_yolo_image(self, json_data, json_name, image_dir_path, target_dir):
img_name = json_name.replace('.json', '.png')
img_path = os.path.join(image_dir_path, target_dir,img_name)
if not os.path.exists(img_path):
# print(json_data)
json_data = json.loads(json_data)
# print(json_data)
img = utils.img_b64_to_arr(json_data['imageData'])
PIL.Image.fromarray(img).save(img_path)
return img_path
def _save_dataset_yaml(self):
yaml_path = os.path.join(self._json_dir, 'D:/convert/', 'dataset.yaml')
with open(yaml_path, 'w+') as yaml_file:
yaml_file.write('train: %s\n' % \
os.path.join(self._image_dir_path, 'train/'))
yaml_file.write('val: %s\n\n' % \
os.path.join(self._image_dir_path, 'val/'))
yaml_file.write('nc: %i\n\n' % len(self._label_id_map))
names_str = ''
for label, _ in self._label_id_map.items():
names_str += "'%s', " % label
names_str = names_str.rstrip(', ')
yaml_file.write('names: [%s]' % names_str)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--json_dir',type=str,
help='Please input the path of the labelme json files.')
parser.add_argument('--val_size',type=float, nargs='?', default=None,
help='Please input the validation dataset size, for example 0.1 ')
parser.add_argument('--json_name',type=str, nargs='?', default=None,
help='If you put json name, it would convert only one json file to YOLO.')
args = parser.parse_args(sys.argv[1:])
convertor = Labelme2YOLO(args.json_dir)
if args.json_name is None:
convertor.convert(val_size=args.val_size)
else:
convertor.convert_one(args.json_name)
写得比较匆忙，相对也比较潦草，希望可以帮助到大家！！
华为开发者空间，是为全球开发者打造的专属开发空间，汇聚了华为优质开发资源及工具，致力于让每一位开发者拥有一台云主机，基于华为根生态开发、创新。
更多推荐
2
0- 0
已为社区贡献2条内容
所有评论(0)