-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathlabelme2COCO.py
180 lines (153 loc) · 6.66 KB
/
labelme2COCO.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
import argparse
import json
import matplotlib.pyplot as plt
import skimage.io as io
import cv2
from labelme import utils
import numpy as np
import glob
import PIL.Image
from sklearn.model_selection import train_test_split
from tqdm import tqdm
import os
class labelme2coco(object):
def __init__(self, labelme_json=[], save_json_path='./new.json', categories=[], label=[]):
'''
:param labelme_json: 所有labelme的json文件路径组成的列表
:param save_json_path: json保存位置
'''
self.labelme_json = labelme_json
self.save_json_path = save_json_path
self.images = []
# = []
self.categories = categories
self.annotations = []
# self.data_coco = {}
self.label = label
self.annID = 1
self.height = 0
self.width = 0
self.save_json()
def data_transfer(self):
for num, json_file in tqdm(enumerate(self.labelme_json)):
with open(json_file, 'r') as fp:
data = json.load(fp) # 加载json文件
self.images.append(self.image(data, num))
for shapes in data['shapes']:
label = shapes['label'].replace('1','').replace('2','').replace('3','').replace('4','')
if label == '_background_': # 检查标定是否异常
continue
print(json_file)
if label not in self.label:
self.categories.append(self.categorie(label))
self.label.append(label)
points = shapes['points']
self.annotations.append(self.annotation(points, label, num))
self.annID += 1
def image(self, data, num):
image = {}
img = utils.img_b64_to_arr(data['imageData']) # 解析原图片数据
# img=io.imread(data['imagePath']) # 通过图片路径打开图片
# img = cv2.imread(data['imagePath'], 0)
height, width = img.shape[:2]
img = None
image['height'] = height
image['width'] = width
image['id'] = num + 1
#image['file_name'] = data['imagePath'].split('/')[-1] # windows会出问题
image['file_name'] = os.path.split(data['imagePath'])[1]
# if image['file_name'] == '229.jpg':
# a=1
self.height = height
self.width = width
return image
def categorie(self, label):
categorie = {}
categorie['supercategory'] = label
categorie['id'] = len(self.label) + 1 # 0 默认为背景
categorie['name'] = label
return categorie
def annotation(self, points, label, num):
annotation = {}
# annotation['segmentation']=[list(np.asarray(points).flatten())]
annotation['segmentation'] = [list(list(map(int, np.asarray(points).flatten())))]
# annotation['segmentation'] = [np.asarray(points).flatten()]
annotation['iscrowd'] = 0
annotation['image_id'] = num + 1
# annotation['bbox'] = str(self.getbbox(points)) # 使用list保存json文件时报错（不知道为什么）
# list(map(int,a[1:-1].split(','))) a=annotation['bbox'] 使用该方式转成list
annotation['bbox'] = list(map(float, self.getbbox(points)))
annotation['area'] = annotation['bbox'][2] * annotation['bbox'][3] #
annotation['category_id'] = self.getcatid(label)
annotation['id'] = self.annID
return annotation
def getcatid(self, label):
for categorie in self.categories:
if label == categorie['name']:
return categorie['id']
return -1
def getbbox(self, points):
# img = np.zeros([self.height,self.width],np.uint8)
# cv2.polylines(img, [np.asarray(points)], True, 1, lineType=cv2.LINE_AA) # 画边界线
# cv2.fillPoly(img, [np.asarray(points)], 1) # 画多边形 内部像素值为1
polygons = points
mask = self.polygons_to_mask([self.height, self.width], polygons)
return self.mask2box(mask)
def mask2box(self, mask):
'''从mask反算出其边框
mask：[h,w] 0、1组成的图片
1对应对象，只需计算1对应的行列号（左上角行列号，右下角行列号，就可以算出其边框）
'''
# np.where(mask==1)
index = np.argwhere(mask == 1)
rows = index[:, 0]
clos = index[:, 1]
# 解析左上角行列号
left_top_r = np.min(rows) # y
left_top_c = np.min(clos) # x
# 解析右下角行列号
right_bottom_r = np.max(rows)
right_bottom_c = np.max(clos)
# return [(left_top_r,left_top_c),(right_bottom_r,right_bottom_c)]
# return [(left_top_c, left_top_r), (right_bottom_c, right_bottom_r)]
# return [left_top_c, left_top_r, right_bottom_c, right_bottom_r] # [x1,y1,x2,y2]
return [left_top_c, left_top_r, right_bottom_c - left_top_c,
right_bottom_r - left_top_r] # [x1,y1,w,h] 对应COCO的bbox格式
def polygons_to_mask(self, img_shape, polygons): # 有用
mask = np.zeros(img_shape, dtype=np.uint8)
mask = PIL.Image.fromarray(mask)
xy = list(map(tuple, polygons))
PIL.ImageDraw.Draw(mask).polygon(xy=xy, outline=1, fill=1)
mask = np.array(mask, dtype=bool)
return mask
def data2coco(self):
data_coco = {}
data_coco['images'] = self.images
data_coco['categories'] = self.categories
data_coco['annotations'] = self.annotations
return data_coco
def save_json(self):
self.data_transfer()
self.data_coco = self.data2coco()
# 保存json文件
json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4) # indent=4 更加美观显示
parser = argparse.ArgumentParser(
description='labelme2coco')
parser.add_argument('--labeled_dir', required=True,
help='path to labeled dir')
parser.add_argument('--output_dir', required=True,
help='path to output dir')
parser.add_argument('--rate', required=False, default=0.3,
help='rate of validation dataset')
args = parser.parse_args()
labelme_json = glob.glob('{}/*.json'.format(args.labeled_dir))
# labelme_json=['./1.json']
labelme_json_train, labelme_json_val = train_test_split(labelme_json)
labelme = labelme2coco(labelme_json_train, '{}/train.json'.format(args.output_dir))
labelme2coco(labelme_json_val, '{}/val.json'.format(args.output_dir), labelme.categories, labelme.label)
#print(labelme.categories)
id2class = dict()
id2class[0] = 'BG'
for info in labelme.categories:
id2class[info['id']] = info['name']
print(id2class)