-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathDetThread.py
199 lines (184 loc) · 9.57 KB
/
DetThread.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
import numpy as np
import torch
import torch.backends.cudnn as cudnn
import time
import cv2
import os
from PyQt5.QtCore import QThread, pyqtSignal
from utils.general import check_img_size, check_requirements, check_imshow, colorstr, non_max_suppression, \
apply_classifier, scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
# from utils.plots import colors, plot_one_box, plot_one_box_PIL
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device
from models.experimental import attempt_load
from utils.datasets import LoadImages, LoadWebcam
class DetThread(QThread):
send_img = pyqtSignal(np.ndarray)
send_raw = pyqtSignal(np.ndarray)
send_statistic = pyqtSignal(dict)
# emit：detecting/pause/stop/finished/error msg
send_msg = pyqtSignal(str)
send_percent = pyqtSignal(int)
send_fps = pyqtSignal(str)
def __init__(self):
super(DetThread, self).__init__()
self.weights = './yolov5s.pt'
self.current_weight = './yolov5s.pt'
self.source = '0'
self.conf_thres = 0.25
self.iou_thres = 0.45
self.jump_out = False # jump out of the loop
self.is_continue = True # continue/pause
self.percent_length = 1000 # progress bar
self.rate_check = True # Whether to enable delay
self.rate = 100
self.save_fold = './result'
@torch.no_grad()
def run(self,
imgsz=640, # inference size (pixels)
max_det=1000, # maximum detections per image
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=True, # show results
save_txt=False, # save results to *.txt
save_conf=False, # save confidences in --save-txt labels
save_crop=False, # save cropped prediction boxes
nosave=False, # do not save images/videos
classes=None, # filter by class: --class 0, or --class 0 2 3
agnostic_nms=False, # class-agnostic NMS
augment=False, # augmented inference
visualize=False, # visualize features
update=False, # update all models
project='runs/detect', # save results to project/name
name='exp', # save results to project/name
exist_ok=False, # existing project/name ok, do not increment
line_thickness=3, # bounding box thickness (pixels)
hide_labels=False, # hide labels
hide_conf=False, # hide confidences
half=False, # use FP16 half-precision inference
):
# Initialize
try:
device = select_device(device)
half &= device.type != 'cpu' # half precision only supported on CUDA
# Load model
model = attempt_load(self.weights, map_location=device) # load FP32 model
num_params = 0
for param in model.parameters():
num_params += param.numel()
stride = int(model.stride.max()) # model stride
imgsz = check_img_size(imgsz, s=stride) # check image size
names = model.module.names if hasattr(model, 'module') else model.names # get class names
if half:
model.half() # to FP16
# Dataloader
if self.source.isnumeric() or self.source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://')):
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadWebcam(self.source, img_size=imgsz, stride=stride)
# bs = len(dataset) # batch_size
else:
dataset = LoadImages(self.source, img_size=imgsz, stride=stride)
# Run inference
if device.type != 'cpu':
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
count = 0
jump_count = 0
start_time = time.time()
dataset = iter(dataset)
while True:
if self.jump_out:
self.vid_cap.release()
self.send_percent.emit(0)
self.send_msg.emit('Stop')
if hasattr(self, 'out'):
self.out.release()
break
# change model
if self.current_weight != self.weights:
# Load model
model = attempt_load(self.weights, map_location=device) # load FP32 model
num_params = 0
for param in model.parameters():
num_params += param.numel()
stride = int(model.stride.max()) # model stride
imgsz = check_img_size(imgsz, s=stride) # check image size
names = model.module.names if hasattr(model, 'module') else model.names # get class names
if half:
model.half() # to FP16
# Run inference
if device.type != 'cpu':
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
self.current_weight = self.weights
if self.is_continue:
path, img, im0s, self.vid_cap = next(dataset)
# jump_count += 1
# if jump_count % 5 != 0:
# continue
count += 1
if count % 30 == 0 and count >= 30:
fps = int(30 / (time.time() - start_time))
self.send_fps.emit('fps：' + str(fps))
start_time = time.time()
if self.vid_cap:
percent = int(count / self.vid_cap.get(cv2.CAP_PROP_FRAME_COUNT) * self.percent_length)
self.send_percent.emit(percent)
else:
percent = self.percent_length
statistic_dic = {name: 0 for name in names}
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
pred = model(img, augment=augment)[0]
# Apply NMS
pred = non_max_suppression(pred, self.conf_thres, self.iou_thres, classes, agnostic_nms,
max_det=max_det)
# Process detections
for i, det in enumerate(pred): # detections per image
im0 = im0s.copy()
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
# Write results
for *xyxy, conf, cls in reversed(det):
c = int(cls) # integer class
statistic_dic[names[c]] += 1
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
annotator.box_label(xyxy, label, color=colors(c, True))
if self.rate_check:
time.sleep(1 / self.rate)
im0 = annotator.result()
self.send_img.emit(im0)
self.send_raw.emit(im0s if isinstance(im0s, np.ndarray) else im0s[0])
self.send_statistic.emit(statistic_dic)
if self.save_fold:
os.makedirs(self.save_fold, exist_ok=True)
if self.vid_cap is None:
save_path = os.path.join(self.save_fold,
time.strftime('%Y_%m_%d_%H_%M_%S',
time.localtime()) + '.jpg')
cv2.imwrite(save_path, im0)
else:
if count == 1:
ori_fps = int(self.vid_cap.get(cv2.CAP_PROP_FPS))
if ori_fps == 0:
ori_fps = 25
# width = int(self.vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
# height = int(self.vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
width, height = im0.shape[1], im0.shape[0]
save_path = os.path.join(self.save_fold,
time.strftime('%Y_%m_%d_%H_%M_%S', time.localtime()) + '.mp4')
self.out = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*"mp4v"), ori_fps,
(width, height))
self.out.write(im0)
if percent == self.percent_length:
print(count)
self.send_percent.emit(0)
self.send_msg.emit('finished')
if hasattr(self, 'out'):
self.out.release()
break
except Exception as e:
self.send_msg.emit('%s' % e)