labelme标注文件转coco json+图片也自动分成训练集与验证集，coco json转yolo txt格式，labelme标注文件转分割
参考：https://github.com/wkentaro/labelme
一.labelme标注文件转coco json
1.标注时带图片ImageData信息，将一个文件夹下的照片和labelme的标注文件，分成了train和val的coco json文件和照片
import os
import json
import numpy as np
import glob
import shutil
from sklearn.model_selection import train_test_split
from labelme import utils
np.random.seed(41)
#0为背景
classname_to_id = {"Red": 1}
class Lableme2CoCo:
def __init__(self):
self.images = []
self.annotations = []
self.categories = []
self.img_id = 0
self.ann_id = 0
def save_coco_json(self, instance, save_path):
json.dump(instance, open(save_path, 'w', encoding='utf-8'), ensure_ascii=False, indent=1) # indent=2 更加美观显示
# 由json文件构建COCO
def to_coco(self, json_path_list):
self._init_categories()
for json_path in json_path_list:
obj = self.read_jsonfile(json_path)
self.images.append(self._image(obj, json_path))
shapes = obj['shapes']
for shape in shapes:
annotation = self._annotation(shape)
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
# 构建类别
def _init_categories(self):
for k, v in classname_to_id.items():
category = {}
category['id'] = v
category['name'] = k
self.categories.append(category)
# 构建COCO的image字段
def _image(self, obj, path):
image = {}
img_x = utils.img_b64_to_arr(obj['imageData'])
h, w = img_x.shape[:-1]
image['height'] = h
image['width'] = w
image['id'] = self.img_id
image['file_name'] = os.path.basename(path).replace(".json", ".jpg")
return image
# 构建COCO的annotation字段
def _annotation(self, shape):
label = shape['label']
points = shape['points']
annotation = {}
annotation['id'] = self.ann_id
annotation['image_id'] = self.img_id
annotation['category_id'] = int(classname_to_id[label])
annotation['segmentation'] = [np.asarray(points).flatten().tolist()]
annotation['bbox'] = self._get_box(points)
annotation['iscrowd'] = 0
annotation['area'] = annotation['bbox'][-1]*annotation['bbox'][-2]
return annotation
# 读取json文件，返回一个json对象
def read_jsonfile(self, path):
with open(path, "r", encoding='utf-8') as f:
return json.load(f)
# COCO的格式： [x1,y1,w,h] 对应COCO的bbox格式
def _get_box(self, points):
min_x = min_y = np.inf
max_x = max_y = 0
for x, y in points:
min_x = min(min_x, x)
min_y = min(min_y, y)
max_x = max(max_x, x)
max_y = max(max_y, y)
return [min_x, min_y, max_x - min_x, max_y - min_y]
if __name__ == '__main__':
#将一个文件夹下的照片和labelme的标注文件，分成了train和val的coco json文件和照片
labelme_path = './data/fzh_img_label_example'
train_img_out_path='./train_img'
val_img_out_path = './val_img'
if not (os.path.exists(train_img_out_path) and os.path.exists(val_img_out_path)):
os.mkdir(train_img_out_path)
os.mkdir(val_img_out_path)
# 获取images目录下所有的joson文件列表
json_list_path = glob.glob(labelme_path + "/*.json")
print('json_list_path=', json_list_path)
# 数据划分,这里没有区分val2017和tran2017目录，所有图片都放在images目录下
train_path, val_path = train_test_split(json_list_path, test_size=0.5)
print("train_n:", len(train_path), 'val_n:', len(val_path))
print('train_path=',train_path)
# 把训练集转化为COCO的json格式
l2c_train = Lableme2CoCo()
train_instance = l2c_train.to_coco(train_path)
l2c_train.save_coco_json(train_instance, 'train.json')
# 把验证集转化为COCO的json格式
l2c_val = Lableme2CoCo()
val_instance = l2c_val.to_coco(val_path)
l2c_val.save_coco_json(val_instance, 'val.json')
for file in train_path:
shutil.copy(file.replace("json",'png' or "jpg"),train_img_out_path)
for file in val_path:
shutil.copy(file.replace("json",'png' or "jpg"),val_img_out_path)
labelme标注好的文件和json格式
生成的训练集 生成的验证集
生成的训练集和验证集的json文件
label me标注的json格式 转好的coco json格式
2.标注时图片不带ImageData信息
import os
import json
import numpy as np
import glob
import shutil
from sklearn.model_selection import train_test_split
from labelme import utils
import cv2
np.random.seed(41)
# 0为背景
classname_to_id = {"person": 1,"bus": 6}
class Lableme2CoCo:
def __init__(self):
self.images = []
self.annotations = []
self.categories = []
self.img_id = 0
self.ann_id = 0
def save_coco_json(self, instance, save_path):
json.dump(instance, open(save_path, 'w', encoding='utf-8'), ensure_ascii=False, indent=1) # indent=2 更加美观显示
# 由json文件构建COCO
def to_coco(self, json_path_list):
self._init_categories()
for json_path in json_path_list:
obj = self.read_jsonfile(json_path)
self.images.append(self._image(obj, json_path))
shapes = obj['shapes']
for shape in shapes:
annotation = self._annotation(shape)
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
# 构建类别
def _init_categories(self):
for k, v in classname_to_id.items():
category = {}
category['id'] = v
category['name'] = k
self.categories.append(category)
# 构建COCO的image字段
def _image(self, obj, path):
image = {}
img_path = path.replace(".json", ".jpg")
# img_x = utils.img_b64_to_arr(obj['imageData'])
# h, w = img_x.shape[:-1]
# print("img_path:",img_path)
img_x = cv2.imread(img_path)
h, w = img_x.shape[:-1]
image['height'] = h
image['width'] = w
image['id'] = self.img_id
image['file_name'] = os.path.basename(path).replace(".json", ".jpg")
return image
# 构建COCO的annotation字段
def _annotation(self, shape):
label = shape['label']
points = shape['points']
annotation = {}
annotation['id'] = self.ann_id
annotation['image_id'] = self.img_id
annotation['category_id'] = int(classname_to_id[label])
annotation['segmentation'] = [np.asarray(points).flatten().tolist()]
annotation['bbox'] = self._get_box(points)
annotation['iscrowd'] = 0
annotation['area'] = annotation['bbox'][-1] * annotation['bbox'][-2]
return annotation
# 读取json文件，返回一个json对象
def read_jsonfile(self, path):
with open(path, "r", encoding='utf-8') as f:
return json.load(f)
# COCO的格式： [x1,y1,w,h] 对应COCO的bbox格式
def _get_box(self, points):
min_x = min_y = np.inf
max_x = max_y = 0
for x, y in points:
min_x = min(min_x, x)
min_y = min(min_y, y)
max_x = max(max_x, x)
max_y = max(max_y, y)
return [min_x, min_y, max_x - min_x, max_y - min_y]
if __name__ == '__main__':
# 将一个文件夹下的照片和labelme的标注文件，分成了train和val的coco json文件和照片
labelme_path = './data'
train_img_out_path = './train_img'
val_img_out_path = './val_img'
if not (os.path.exists(train_img_out_path) and os.path.exists(val_img_out_path)):
os.mkdir(train_img_out_path)
os.mkdir(val_img_out_path)
# 获取images目录下所有的joson文件列表
json_list_path = glob.glob(labelme_path + "/*.json")
print('json_list_path=', json_list_path)
# 数据划分,这里没有区分val2017和tran2017目录，所有图片都放在images目录下
train_path, val_path = train_test_split(json_list_path, test_size=0)
print("train_n:", len(train_path), 'val_n:', len(val_path))
print('train_path=', train_path)
# 把训练集转化为COCO的json格式
l2c_train = Lableme2CoCo()
train_instance = l2c_train.to_coco(train_path)
l2c_train.save_coco_json(train_instance, 'train.json')
# 把验证集转化为COCO的json格式
l2c_val = Lableme2CoCo()
val_instance = l2c_val.to_coco(val_path)
l2c_val.save_coco_json(val_instance, 'val.json')
for file in train_path:
shutil.copy(file.replace("json", "jpg"), train_img_out_path)
for file in val_path:
shutil.copy(file.replace("json", "jpg"), val_img_out_path)二.coco josn转yolo txt格式
from __future__ import print_function
import os, sys, zipfile
import json
def convert(size, box):
dw = 1. / (size[0])
dh = 1. / (size[1])
x = box[0] + box[2] / 2.0
y = box[1] + box[3] / 2.0
w = box[2]
h = box[3]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
return (x, y, w, h)
json_file = 'train.json' # # Object Instance 类型的标注
data = json.load(open(json_file, 'r'))
ana_txt_save_path = "./new" # 保存的路径
if not os.path.exists(ana_txt_save_path):
os.makedirs(ana_txt_save_path)
for img in data['images']:
# print(img["file_name"])
filename = img["file_name"]
img_width = img["width"]
img_height = img["height"]
# print(img["height"])
# print(img["width"])
img_id = img["id"]
ana_txt_name = filename.split(".")[0] + ".txt" # 对应的txt名字，与jpg一致
print(ana_txt_name)
f_txt = open(os.path.join(ana_txt_save_path, ana_txt_name), 'w')
for ann in data['annotations']:
if ann['image_id'] == img_id:
# annotation.append(ann)
# print(ann["category_id"], ann["bbox"])
box = convert((img_width, img_height), ann["bbox"])
f_txt.write("%s %s %s %s %s\n" % (ann["category_id"], box[0], box[1], box[2], box[3]))
f_txt.close()
三.labelme标注文件转成分割图片
import json
import os
import os.path as osp
import numpy as np
import PIL.Image
import yaml
from labelme.logger import logger
from labelme import utils
import cv2
def main():
img_path = './002.jpg'
json_file = './002.json'
output_path = './output'
if not os.path.exists(output_path):
os.mkdir(output_path)
json_data = json.load(open(json_file))
img = cv2.imread(img_path)
print('img.shape:',img.shape)
label_name_to_value = {'_background_': 0}
for shape in sorted(json_data['shapes'], key=lambda x: x['label']):
label_name = shape['label']
print('label_name:',label_name)
if label_name in label_name_to_value:
label_value = label_name_to_value[label_name]
else:
label_value = len(label_name_to_value)
print('label_value:',label_value)
label_name_to_value[label_name] = label_value
lbl = utils.shapes_to_label(img.shape, json_data['shapes'], label_name_to_value)
cv2.imwrite(output_path+'/'+img_path.split('/')[-1], lbl * 255)