-
Notifications
You must be signed in to change notification settings - Fork 90
/
to_coco_person17.py
284 lines (233 loc) · 9.74 KB
/
to_coco_person17.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
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
import os
import sys
import glob
import json
import shutil
import argparse
import numpy as np
import PIL.Image
import os.path as osp
from tqdm import tqdm
from labelme import utils
from sklearn.model_selection import train_test_split
class Labelme2coco_keypoints():
def __init__(self, args):
"""
Lableme 关键点数据集转 COCO 数据集的构造函数:
Args
args：命令行输入的参数
- class_name 根类名字
"""
self.classname_to_id = {args.class_name: 1}
self.images = []
self.annotations = []
self.categories = []
self.ann_id = 0
self.img_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)
def read_jsonfile(self, path):
with open(path, "r", encoding='utf-8') as f:
return json.load(f)
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]
def _get_keypoints(self, points, keypoints, num_keypoints):
"""
解析 labelme 的原始数据， 生成 coco 标注的 关键点对象
例如：
"keypoints": [
67.06149888292556, # x 的值
122.5043507571318, # y 的值
1, # 相当于 Z 值，如果是2D关键点 0：不可见 1：表示可见。
82.42582269256718,
109.95672933232304,
1,
...,
],
"""
if points[0] == 0 and points[1] == 0:
visable = 0
else:
visable = 1
num_keypoints += 1
keypoints.extend([int(points[0]), int(points[1]), visable])
return keypoints, num_keypoints
def _image(self, obj, path):
"""
解析 labelme 的 obj 对象，生成 coco 的 image 对象
生成包括：id，file_name，height，width 4个属性
示例：
{
"file_name": "training/rgb/00031426.jpg",
"height": 224,
"width": 224,
"id": 31426
}
"""
image = {}
img_x = utils.img_b64_to_arr(obj['imageData']) # 获得原始 labelme 标签的 imageData 属性，并通过 labelme 的工具方法转成 array
image['height'], image['width'] = img_x.shape[:-1] # 获得图片的宽高
# self.img_id = int(os.path.basename(path).split(".json")[0])
self.img_id = self.img_id + 1
image['id'] = self.img_id
image['file_name'] = os.path.basename(path).replace(".json", ".jpg")
return image
def _annotation(self, bboxes_list, keypoints_list, json_path):
"""
生成coco标注
Args：
bboxes_list： 矩形标注框
keypoints_list： 关键点
json_path：json文件路径
"""
if len(keypoints_list) != args.join_num * len(bboxes_list):
print('you loss {} keypoint(s) with file {}'.format(args.join_num * len(bboxes_list) - len(keypoints_list), json_path))
print('Please check ！！！')
sys.exit()
i = 0
for object in bboxes_list:
annotation = {}
keypoints = []
num_keypoints = 0
label = object['label']
bbox = object['points']
annotation['id'] = self.ann_id
annotation['image_id'] = self.img_id
annotation['category_id'] = int(self.classname_to_id[label])
annotation['iscrowd'] = 0
annotation['segmentation'] = [np.asarray(bbox).flatten().tolist()]
annotation['bbox'] = self._get_box(bbox)
annotation['area'] = annotation['bbox'][2]*annotation['bbox'][3]
for keypoint in keypoints_list[i * args.join_num: (i + 1) * args.join_num]:
point = keypoint['points']
annotation['keypoints'], num_keypoints = self._get_keypoints(point[0], keypoints, num_keypoints)
annotation['num_keypoints'] = num_keypoints
i += 1
self.ann_id += 1
self.annotations.append(annotation)
def _init_categories(self):
"""
初始化 COCO 的 标注类别
例如：
"categories": [
{
"supercategory": "hand",
"id": 1,
"name": "hand",
"keypoints": [
"wrist",
"thumb1",
"thumb2",
...,
],
"skeleton": [
]
}
]
"""
for name, id in self.classname_to_id.items():
category = {}
category['supercategory'] = name
category['id'] = id
category['name'] = name
# 17 个关键点数据
category['keypoint'] = [ "nose",
"left_eye",
"right_eye",
"left_ear",
"right_ear",
"left_shoulder",
"right_shoulder",
"left_elbow",
"right_elbow",
"left_wrist",
"right_wrist",
"left_hip",
"right_hip",
"left_knee",
"right_knee",
"left_ankle",
"right_ankle"]
# category['keypoint'] = [str(i + 1) for i in range(args.join_num)]
self.categories.append(category)
def to_coco(self, json_path_list):
"""
Labelme 原始标签转换成 coco 数据集格式，生成的包括标签和图像
Args：
json_path_list：原始数据集的目录
"""
self._init_categories()
for json_path in tqdm(json_path_list):
obj = self.read_jsonfile(json_path) # 解析一个标注文件
self.images.append(self._image(obj, json_path)) # 解析图片
shapes = obj['shapes'] # 读取 labelme shape 标注
bboxes_list, keypoints_list = [], []
keypoints_list = [[] for _ in range(len(self.categories[0]['keypoint']))]
# print(self.categories[0]['keypoint'])
# bb
for shape in shapes:
if shape['shape_type'] == 'rectangle': # bboxs
bboxes_list.append(shape) # keypoints
elif shape['shape_type'] == 'point':
### 按关键点顺序赋值！！！！
kid = self.categories[0]['keypoint'].index(shape['label'])
keypoints_list[kid] = shape
self._annotation(bboxes_list, keypoints_list, json_path)
keypoints = {}
keypoints['info'] = {'description': 'Lableme Dataset', 'version': 1.0, 'year': 2021}
keypoints['license'] = ['BUAA']
keypoints['images'] = self.images
keypoints['annotations'] = self.annotations
keypoints['categories'] = self.categories
return keypoints
def init_dir(base_path):
"""
初始化COCO数据集的文件夹结构；
coco - annotations #标注文件路径
- train #训练数据集
- val #验证数据集
Args：
base_path：数据集放置的根路径
"""
if not os.path.exists(os.path.join(base_path, "coco", "annotations")):
os.makedirs(os.path.join(base_path, "coco", "annotations"))
if not os.path.exists(os.path.join(base_path, "coco", "train2017")):
os.makedirs(os.path.join(base_path, "coco", "train2017"))
if not os.path.exists(os.path.join(base_path, "coco", "val2017")):
os.makedirs(os.path.join(base_path, "coco", "val2017"))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("--class_name", "--n", help="class name", type=str, required=True)
parser.add_argument("--input", "--i", help="json file path (labelme)", type=str, required=True)
parser.add_argument("--output", "--o", help="output file path (coco format)", type=str, required=True)
parser.add_argument("--join_num", "--j", help="number of join", type=int, required=True)
parser.add_argument("--ratio", "--r", help="train and test split ratio", type=float, default=0.12)
args = parser.parse_args()
labelme_path = args.input
saved_coco_path = args.output
init_dir(saved_coco_path) # 初始化COCO数据集的文件夹结构
json_list_path = glob.glob(labelme_path + "/*.json")
train_path, val_path = train_test_split(json_list_path, test_size=args.ratio)
print('{} for training'.format(len(train_path)),
'\n{} for testing'.format(len(val_path)))
print('Start transform please wait ...')
l2c_train = Labelme2coco_keypoints(args) # 构造数据集生成类
# 生成训练集
train_keypoints = l2c_train.to_coco(train_path)
l2c_train.save_coco_json(train_keypoints, os.path.join(saved_coco_path, "coco", "annotations", "person_keypoints_train2017.json"))
# 生成验证集
l2c_val = Labelme2coco_keypoints(args)
val_instance = l2c_val.to_coco(val_path)
l2c_val.save_coco_json(val_instance, os.path.join(saved_coco_path, "coco", "annotations", "person_keypoints_val2017.json"))
# 拷贝 labelme 的原始图片到训练集和验证集里面
for file in train_path:
shutil.copy(file.replace("json", "jpg"), os.path.join(saved_coco_path, "coco", "train2017"))
for file in val_path:
shutil.copy(file.replace("json", "jpg"), os.path.join(saved_coco_path, "coco", "val2017"))