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
|
- """Run inference with a YOLOv5 model on images, videos, directories, streams
- Usage:
- $ python path/to/detect.py --source path/to/img.jpg --weights yolov5s.pt --img 640
- """
- import argparse
- import sys
- import time
- from pathlib import Path
- import cv2
- import torch
- import torch.backends.cudnn as cudnn
- FILE = Path(__file__).absolute()
- sys.path.append(FILE.parents[0].as_posix()) # add yolov5/ to path
- from models.experimental import attempt_load
- from utils.datasets import LoadStreams, LoadImages
- 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, save_one_box
- from utils.plots import colors, plot_one_box
- from utils.torch_utils import select_device, load_classifier, time_sync
- @torch.no_grad()
- def run(weights='yolov5s.pt', # model.pt path(s)
- source='data/images', # file/dir/URL/glob, 0 for webcam
- imgsz=640, # inference size (pixels)
- conf_thres=0.25, # confidence threshold
- iou_thres=0.45, # NMS IOU threshold
- max_det=1000, # maximum detections per image
- device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
- view_img=False, # 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
- ):
- save_img = not nosave and not source.endswith('.txt') # save inference images
- webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
- ('rtsp://', 'rtmp://', 'http://', 'https://'))
- # Directories
- save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
- (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
- # Initialize
- set_logging()
- device = select_device(device)
- half &= device.type != 'cpu' # half precision only supported on CUDA
- # Load model
- model = attempt_load(weights, map_location=device) # load FP32 model
- 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
- # Second-stage classifier
- classify = False
- if classify:
- modelc = load_classifier(name='resnet50', n=2) # initialize
- modelc.load_state_dict(torch.load('resnet50.pt', map_location=device)['model']).to(device).eval()
- # Dataloader
- if webcam:
- view_img = check_imshow()
- cudnn.benchmark = True # set True to speed up constant image size inference
- dataset = LoadStreams(source, img_size=imgsz, stride=stride)
- bs = len(dataset) # batch_size
- else:
- dataset = LoadImages(source, img_size=imgsz, stride=stride)
- bs = 1 # batch_size
- vid_path, vid_writer = [None] * bs, [None] * bs
- # Run inference
- if device.type != 'cpu':
- model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
- t0 = time.time()
- for path, img, im0s, vid_cap in dataset:
- 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)
- # Inference
- t1 = time_sync()
- pred = model(img,
- augment=augment,
- visualize=increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False)[0]
- # Apply NMS
- pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
- t2 = time_sync()
- # Apply Classifier
- if classify:
- pred = apply_classifier(pred, modelc, img, im0s)
- # Process detections
- for i, det in enumerate(pred): # detections per image
- if webcam: # batch_size >= 1
- p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
- else:
- p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0)
- p = Path(p) # to Path
- save_path = str(save_dir / p.name) # img.jpg
- txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
- s += '%gx%g ' % img.shape[2:] # print string
- gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
- imc = im0.copy() if save_crop else im0 # for save_crop
- if len(det):
- # Rescale boxes from img_size to im0 size
- det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
- # Print results
- for c in det[:, -1].unique():
- n = (det[:, -1] == c).sum() # detections per class
- s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
- # Write results
- for *xyxy, conf, cls in reversed(det):
- if save_txt: # Write to file
- xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
- line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
- with open(txt_path + '.txt', 'a') as f:
- f.write(('%g ' * len(line)).rstrip() % line + '\n')
- if save_img or save_crop or view_img: # Add bbox to image
- c = int(cls) # integer class
- label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
- plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=line_thickness)
- if save_crop:
- save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
- # Print time (inference + NMS)
- print(f'{s}Done. ({t2 - t1:.3f}s)')
- # Stream results
- if view_img:
- cv2.imshow(str(p), im0)
- cv2.waitKey(1) # 1 millisecond
- # Save results (image with detections)
- if save_img:
- if dataset.mode == 'image':
- cv2.imwrite(save_path, im0)
- else: # 'video' or 'stream'
- if vid_path[i] != save_path: # new video
- vid_path[i] = save_path
- if isinstance(vid_writer[i], cv2.VideoWriter):
- vid_writer[i].release() # release previous video writer
- if vid_cap: # video
- fps = vid_cap.get(cv2.CAP_PROP_FPS)
- w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
- h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
- else: # stream
- fps, w, h = 30, im0.shape[1], im0.shape[0]
- save_path += '.mp4'
- vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
- vid_writer[i].write(im0)
- if save_txt or save_img:
- s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
- print(f"Results saved to {save_dir}{s}")
- if update:
- strip_optimizer(weights) # update model (to fix SourceChangeWarning)
- print(f'Done. ({time.time() - t0:.3f}s)')
- def parse_opt():
- parser = argparse.ArgumentParser()
- parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
- parser.add_argument('--source', type=str, default='data/images', help='file/dir/URL/glob, 0 for webcam')
- parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)')
- parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
- parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
- parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
- parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
- parser.add_argument('--view-img', action='store_true', help='show results')
- parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
- parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
- parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
- parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
- parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
- parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
- parser.add_argument('--augment', action='store_true', help='augmented inference')
- parser.add_argument('--visualize', action='store_true', help='visualize features')
- parser.add_argument('--update', action='store_true', help='update all models')
- parser.add_argument('--project', default='runs/detect', help='save results to project/name')
- parser.add_argument('--name', default='exp', help='save results to project/name')
- parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
- parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
- parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
- parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
- parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
- opt = parser.parse_args()
- return opt
- def main(opt):
- print(colorstr('detect: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))
- check_requirements(exclude=('tensorboard', 'thop'))
- run(**vars(opt))
- if __name__ == "__main__":
- opt = parse_opt()
- main(opt)
|