-
Notifications
You must be signed in to change notification settings - Fork 72
/
retinaface.py
370 lines (328 loc) · 18.9 KB
/
retinaface.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
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
import time
import cv2
import numpy as np
import torch
import torch.nn as nn
from nets.retinaface import RetinaFace
from utils.anchors import Anchors
from utils.config import cfg_mnet, cfg_re50
from utils.utils import letterbox_image, preprocess_input
from utils.utils_bbox import (decode, decode_landm, non_max_suppression,
retinaface_correct_boxes)
#------------------------------------#
# 请注意主干网络与预训练权重的对应
# 即注意修改model_path和backbone
#------------------------------------#
class Retinaface(object):
_defaults = {
#---------------------------------------------------------------------#
# 使用自己训练好的模型进行预测一定要修改model_path
# model_path指向logs文件夹下的权值文件
# 训练好后logs文件夹下存在多个权值文件，选择损失较低的即可。
#---------------------------------------------------------------------#
"model_path" : 'model_data/Retinaface_mobilenet0.25.pth',
#---------------------------------------------------------------------#
# 所使用的的主干网络：mobilenet、resnet50
#---------------------------------------------------------------------#
"backbone" : 'mobilenet',
#---------------------------------------------------------------------#
# 只有得分大于置信度的预测框会被保留下来
#---------------------------------------------------------------------#
"confidence" : 0.5,
#---------------------------------------------------------------------#
# 非极大抑制所用到的nms_iou大小
#---------------------------------------------------------------------#
"nms_iou" : 0.45,
#---------------------------------------------------------------------#
# 是否需要进行图像大小限制。
# 开启后，会将输入图像的大小限制为input_shape。否则使用原图进行预测。
# 可根据输入图像的大小自行调整input_shape，注意为32的倍数，如[640, 640, 3]
#---------------------------------------------------------------------#
"input_shape" : [1280, 1280, 3],
#---------------------------------------------------------------------#
# 是否需要进行图像大小限制。
#---------------------------------------------------------------------#
"letterbox_image" : True,
#--------------------------------#
# 是否使用Cuda
# 没有GPU可以设置成False
#--------------------------------#
"cuda" : True,
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
#---------------------------------------------------#
# 初始化Retinaface
#---------------------------------------------------#
def __init__(self, **kwargs):
self.__dict__.update(self._defaults)
for name, value in kwargs.items():
setattr(self, name, value)
#---------------------------------------------------#
# 不同主干网络的config信息
#---------------------------------------------------#
if self.backbone == "mobilenet":
self.cfg = cfg_mnet
else:
self.cfg = cfg_re50
#---------------------------------------------------#
# 先验框的生成
#---------------------------------------------------#
if self.letterbox_image:
self.anchors = Anchors(self.cfg, image_size=[self.input_shape[0], self.input_shape[1]]).get_anchors()
self.generate()
#---------------------------------------------------#
# 载入模型
#---------------------------------------------------#
def generate(self):
#-------------------------------#
# 载入模型与权值
#-------------------------------#
self.net = RetinaFace(cfg=self.cfg, mode='eval').eval()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
self.net.load_state_dict(torch.load(self.model_path, map_location=device))
self.net = self.net.eval()
print('{} model, and classes loaded.'.format(self.model_path))
if self.cuda:
self.net = nn.DataParallel(self.net)
self.net = self.net.cuda()
#---------------------------------------------------#
# 检测图片
#---------------------------------------------------#
def detect_image(self, image):
#---------------------------------------------------#
# 对输入图像进行一个备份，后面用于绘图
#---------------------------------------------------#
old_image = image.copy()
#---------------------------------------------------#
# 把图像转换成numpy的形式
#---------------------------------------------------#
image = np.array(image,np.float32)
#---------------------------------------------------#
# 计算输入图片的高和宽
#---------------------------------------------------#
im_height, im_width, _ = np.shape(image)
#---------------------------------------------------#
# 计算scale，用于将获得的预测框转换成原图的高宽
#---------------------------------------------------#
scale = [
np.shape(image)[1], np.shape(image)[0], np.shape(image)[1], np.shape(image)[0]
]
scale_for_landmarks = [
np.shape(image)[1], np.shape(image)[0], np.shape(image)[1], np.shape(image)[0],
np.shape(image)[1], np.shape(image)[0], np.shape(image)[1], np.shape(image)[0],
np.shape(image)[1], np.shape(image)[0]
]
#---------------------------------------------------------#
# letterbox_image可以给图像增加灰条，实现不失真的resize
#---------------------------------------------------------#
if self.letterbox_image:
image = letterbox_image(image, [self.input_shape[1], self.input_shape[0]])
else:
self.anchors = Anchors(self.cfg, image_size=(im_height, im_width)).get_anchors()
with torch.no_grad():
#-----------------------------------------------------------#
# 图片预处理，归一化。
#-----------------------------------------------------------#
image = torch.from_numpy(preprocess_input(image).transpose(2, 0, 1)).unsqueeze(0).type(torch.FloatTensor)
if self.cuda:
self.anchors = self.anchors.cuda()
image = image.cuda()
#---------------------------------------------------------#
# 传入网络进行预测
#---------------------------------------------------------#
loc, conf, landms = self.net(image)
#-----------------------------------------------------------#
# 对预测框进行解码
#-----------------------------------------------------------#
boxes = decode(loc.data.squeeze(0), self.anchors, self.cfg['variance'])
#-----------------------------------------------------------#
# 获得预测结果的置信度
#-----------------------------------------------------------#
conf = conf.data.squeeze(0)[:, 1:2]
#-----------------------------------------------------------#
# 对人脸关键点进行解码
#-----------------------------------------------------------#
landms = decode_landm(landms.data.squeeze(0), self.anchors, self.cfg['variance'])
#-----------------------------------------------------------#
# 对人脸识别结果进行堆叠
#-----------------------------------------------------------#
boxes_conf_landms = torch.cat([boxes, conf, landms], -1)
boxes_conf_landms = non_max_suppression(boxes_conf_landms, self.confidence)
if len(boxes_conf_landms) <= 0:
return old_image
#---------------------------------------------------------#
# 如果使用了letterbox_image的话，要把灰条的部分去除掉。
#---------------------------------------------------------#
if self.letterbox_image:
boxes_conf_landms = retinaface_correct_boxes(boxes_conf_landms, \
np.array([self.input_shape[0], self.input_shape[1]]), np.array([im_height, im_width]))
boxes_conf_landms[:, :4] = boxes_conf_landms[:, :4] * scale
boxes_conf_landms[:, 5:] = boxes_conf_landms[:, 5:] * scale_for_landmarks
for b in boxes_conf_landms:
text = "{:.4f}".format(b[4])
b = list(map(int, b))
#---------------------------------------------------#
# b[0]-b[3]为人脸框的坐标，b[4]为得分
#---------------------------------------------------#
cv2.rectangle(old_image, (b[0], b[1]), (b[2], b[3]), (0, 0, 255), 2)
cx = b[0]
cy = b[1] + 12
cv2.putText(old_image, text, (cx, cy),
cv2.FONT_HERSHEY_DUPLEX, 0.5, (255, 255, 255))
print(b[0], b[1], b[2], b[3], b[4])
#---------------------------------------------------#
# b[5]-b[14]为人脸关键点的坐标
#---------------------------------------------------#
cv2.circle(old_image, (b[5], b[6]), 1, (0, 0, 255), 4)
cv2.circle(old_image, (b[7], b[8]), 1, (0, 255, 255), 4)
cv2.circle(old_image, (b[9], b[10]), 1, (255, 0, 255), 4)
cv2.circle(old_image, (b[11], b[12]), 1, (0, 255, 0), 4)
cv2.circle(old_image, (b[13], b[14]), 1, (255, 0, 0), 4)
return old_image
def get_FPS(self, image, test_interval):
#---------------------------------------------------#
# 把图像转换成numpy的形式
#---------------------------------------------------#
image = np.array(image,np.float32)
#---------------------------------------------------#
# 计算输入图片的高和宽
#---------------------------------------------------#
im_height, im_width, _ = np.shape(image)
#---------------------------------------------------------#
# letterbox_image可以给图像增加灰条，实现不失真的resize
#---------------------------------------------------------#
if self.letterbox_image:
image = letterbox_image(image, [self.input_shape[1], self.input_shape[0]])
else:
self.anchors = Anchors(self.cfg, image_size=(im_height, im_width)).get_anchors()
with torch.no_grad():
#-----------------------------------------------------------#
# 图片预处理，归一化。
#-----------------------------------------------------------#
image = torch.from_numpy(preprocess_input(image).transpose(2, 0, 1)).unsqueeze(0).type(torch.FloatTensor)
if self.cuda:
self.anchors = self.anchors.cuda()
image = image.cuda()
#---------------------------------------------------------#
# 传入网络进行预测
#---------------------------------------------------------#
loc, conf, landms = self.net(image)
#-----------------------------------------------------------#
# 对预测框进行解码
#-----------------------------------------------------------#
boxes = decode(loc.data.squeeze(0), self.anchors, self.cfg['variance'])
#-----------------------------------------------------------#
# 获得预测结果的置信度
#-----------------------------------------------------------#
conf = conf.data.squeeze(0)[:, 1:2]
#-----------------------------------------------------------#
# 对人脸关键点进行解码
#-----------------------------------------------------------#
landms = decode_landm(landms.data.squeeze(0), self.anchors, self.cfg['variance'])
#-----------------------------------------------------------#
# 对人脸识别结果进行堆叠
#-----------------------------------------------------------#
boxes_conf_landms = torch.cat([boxes, conf, landms], -1)
boxes_conf_landms = non_max_suppression(boxes_conf_landms, self.confidence)
t1 = time.time()
for _ in range(test_interval):
with torch.no_grad():
#---------------------------------------------------------#
# 传入网络进行预测
#---------------------------------------------------------#
loc, conf, landms = self.net(image)
#-----------------------------------------------------------#
# 对预测框进行解码
#-----------------------------------------------------------#
boxes = decode(loc.data.squeeze(0), self.anchors, self.cfg['variance'])
#-----------------------------------------------------------#
# 获得预测结果的置信度
#-----------------------------------------------------------#
conf = conf.data.squeeze(0)[:, 1:2]
#-----------------------------------------------------------#
# 对人脸关键点进行解码
#-----------------------------------------------------------#
landms = decode_landm(landms.data.squeeze(0), self.anchors, self.cfg['variance'])
#-----------------------------------------------------------#
# 对人脸识别结果进行堆叠
#-----------------------------------------------------------#
boxes_conf_landms = torch.cat([boxes, conf, landms], -1)
boxes_conf_landms = non_max_suppression(boxes_conf_landms, self.confidence)
t2 = time.time()
tact_time = (t2 - t1) / test_interval
return tact_time
#---------------------------------------------------#
# 检测图片
#---------------------------------------------------#
def get_map_txt(self, image):
#---------------------------------------------------#
# 把图像转换成numpy的形式
#---------------------------------------------------#
image = np.array(image,np.float32)
#---------------------------------------------------#
# 计算输入图片的高和宽
#---------------------------------------------------#
im_height, im_width, _ = np.shape(image)
#---------------------------------------------------#
# 计算scale，用于将获得的预测框转换成原图的高宽
#---------------------------------------------------#
scale = [
np.shape(image)[1], np.shape(image)[0], np.shape(image)[1], np.shape(image)[0]
]
scale_for_landmarks = [
np.shape(image)[1], np.shape(image)[0], np.shape(image)[1], np.shape(image)[0],
np.shape(image)[1], np.shape(image)[0], np.shape(image)[1], np.shape(image)[0],
np.shape(image)[1], np.shape(image)[0]
]
#---------------------------------------------------------#
# letterbox_image可以给图像增加灰条，实现不失真的resize
#---------------------------------------------------------#
if self.letterbox_image:
image = letterbox_image(image, [self.input_shape[1], self.input_shape[0]])
else:
self.anchors = Anchors(self.cfg, image_size=(im_height, im_width)).get_anchors()
with torch.no_grad():
#-----------------------------------------------------------#
# 图片预处理，归一化。
#-----------------------------------------------------------#
image = torch.from_numpy(preprocess_input(image).transpose(2, 0, 1)).unsqueeze(0).type(torch.FloatTensor)
if self.cuda:
self.anchors = self.anchors.cuda()
image = image.cuda()
#---------------------------------------------------------#
# 传入网络进行预测
#---------------------------------------------------------#
loc, conf, landms = self.net(image)
#-----------------------------------------------------------#
# 对预测框进行解码
#-----------------------------------------------------------#
boxes = decode(loc.data.squeeze(0), self.anchors, self.cfg['variance'])
#-----------------------------------------------------------#
# 获得预测结果的置信度
#-----------------------------------------------------------#
conf = conf.data.squeeze(0)[:, 1:2]
#-----------------------------------------------------------#
# 对人脸关键点进行解码
#-----------------------------------------------------------#
landms = decode_landm(landms.data.squeeze(0), self.anchors, self.cfg['variance'])
#-----------------------------------------------------------#
# 对人脸识别结果进行堆叠
#-----------------------------------------------------------#
boxes_conf_landms = torch.cat([boxes, conf, landms], -1)
boxes_conf_landms = non_max_suppression(boxes_conf_landms, self.confidence)
if len(boxes_conf_landms) <= 0:
return np.array([])
#---------------------------------------------------------#
# 如果使用了letterbox_image的话，要把灰条的部分去除掉。
#---------------------------------------------------------#
if self.letterbox_image:
boxes_conf_landms = retinaface_correct_boxes(boxes_conf_landms, \
np.array([self.input_shape[0], self.input_shape[1]]), np.array([im_height, im_width]))
boxes_conf_landms[:, :4] = boxes_conf_landms[:, :4] * scale
boxes_conf_landms[:, 5:] = boxes_conf_landms[:, 5:] * scale_for_landmarks
return boxes_conf_landms