-
Notifications
You must be signed in to change notification settings - Fork 0
/
yolo.py
182 lines (154 loc) · 7.07 KB
/
yolo.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
# -------------------------------------#
# 创建YOLO类
# -------------------------------------#
import colorsys
import os
import numpy as np
import torch
import torch.nn as nn
from PIL import ImageFont, ImageDraw
from nets.yolo3 import YoloBody
from utils.config import Config
from utils.utils import non_max_suppression, DecodeBox, letterbox_image, yolo_correct_boxes
class YOLO(object):
_defaults = {
"model_path": 'model_data/yolov3_final.pth',
"classes_path": 'model_data/classes.txt',
"model_image_size": (416, 416, 3),
"confidence": 0.5,
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
# ---------------------------------------------------#
# 初始化YOLO
# ---------------------------------------------------#
def __init__(self, **kwargs):
self.__dict__.update(self._defaults)
self.class_names = self._get_class()
self.config = Config
self.generate()
# ---------------------------------------------------#
# 获得所有的分类
# ---------------------------------------------------#
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
# ---------------------------------------------------#
# 获得所有的分类
# ---------------------------------------------------#
def generate(self):
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
self.config["yolo"]["classes"] = len(self.class_names)
self.net = YoloBody(self.config)
state_dict = torch.load(self.model_path)
self.net.load_state_dict(state_dict)
self.net = nn.DataParallel(self.net)
self.net = self.net.cuda()
self.yolo_decodes = []
for i in range(3):
self.yolo_decodes.append(DecodeBox(self.config["yolo"]["anchors"][i], self.config["yolo"]["classes"],
(self.config["img_w"], self.config["img_h"])))
print('{} model, anchors, and classes loaded.'.format(self.model_path))
# 画框设置不同的颜色
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
# ---------------------------------------------------#
# 检测图片
# ---------------------------------------------------#
def detect_image(self, image):
image_shape = np.array(np.shape(image)[0:2])
crop_img = np.array(letterbox_image(image, (self.model_image_size[0], self.model_image_size[1])))
photo = np.array(crop_img, dtype=np.float32)
photo /= 255.0
photo = np.transpose(photo, (2, 0, 1))
photo = photo.astype(np.float32)
images = []
images.append(photo)
images = np.asarray(images)
images = torch.from_numpy(images).cuda()
with torch.no_grad():
outputs = self.net(images)
output_list = []
for i in range(3):
output_list.append(self.yolo_decodes[i](outputs[i]))
output = torch.cat(output_list, 1)
batch_detections = non_max_suppression(output, self.config["yolo"]["classes"],
conf_thres=self.confidence,
nms_thres=0.3)
try:
batch_detections = batch_detections[0].cpu().numpy()
except:
with open("num.txt", mode='w') as f:
f.write("0" + '\n' + "0" + '\n' + "0")
return image
top_index = batch_detections[:, 4] * batch_detections[:, 5] > self.confidence
top_conf = batch_detections[top_index, 4] * batch_detections[top_index, 5]
top_label = np.array(batch_detections[top_index, -1], np.int32)
top_bboxes = np.array(batch_detections[top_index, :4])
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(top_bboxes[:, 0], -1), np.expand_dims(top_bboxes[:, 1],
-1), np.expand_dims(
top_bboxes[:, 2], -1), np.expand_dims(top_bboxes[:, 3], -1)
# 去掉灰条
boxes = yolo_correct_boxes(top_ymin, top_xmin, top_ymax, top_xmax,
np.array([self.model_image_size[0], self.model_image_size[1]]), image_shape)
font = ImageFont.truetype(font='model_data/simhei.ttf',
size=np.floor(3e-2 * np.shape(image)[1] + 0.5).astype('int32'))
thickness = (np.shape(image)[0] + np.shape(image)[1]) // self.model_image_size[0]
self.num_all = 0
self.num_hat = 0
self.num_person = 0
m = 'hat'
for i, c in enumerate(top_label):
self.num_all = self.num_all + 1
predicted_class = self.class_names[c]
if predicted_class == m:
self.num_hat = self.num_hat + 1
score = top_conf[i]
top, left, bottom, right = boxes[i]
top = top - 5
left = left - 5
bottom = bottom + 5
right = right + 5
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(np.shape(image)[0], np.floor(bottom + 0.5).astype('int32'))
right = min(np.shape(image)[1], np.floor(right + 0.5).astype('int32'))
# 画框框
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
print(label)
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
for i in range(thickness):
draw.rectangle(
[left + i, top + i, right - i, bottom - i],
outline=self.colors[self.class_names.index(predicted_class)])
draw.rectangle(
[tuple(text_origin), tuple(text_origin + label_size)],
fill=self.colors[self.class_names.index(predicted_class)])
draw.text(text_origin, str(label, 'UTF-8'), fill=(0, 0, 0), font=font)
del draw
self.num_person = self.num_all - self.num_hat
print(self.num_all)
print(self.num_hat)
print(self.num_person)
Num = [self.num_all, self.num_hat, self.num_person]
with open("num.txt", mode='w') as f:
f.write(str(self.num_hat) + '\n')
f.write(str(self.num_person))
return image