# YOLOv5 🚀 by Ultralytics, GPL-3.0 license """ Run inference on images, videos, directories, streams, etc. Usage - sources: $ python path/to/detect.py --weights yolov5s.pt --source 0 # webcam img.jpg # image vid.mp4 # video path/ # directory path/*.jpg # glob 'https://youtu.be/Zgi9g1ksQHc' # YouTube 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream Usage - formats: $ python path/to/detect.py --weights yolov5s.pt # PyTorch yolov5s.torchscript # TorchScript yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn yolov5s.xml # OpenVINO yolov5s.engine # TensorRT yolov5s.mlmodel # CoreML (macOS-only) yolov5s_saved_model # TensorFlow SavedModel yolov5s.pb # TensorFlow GraphDef yolov5s.tflite # TensorFlow Lite yolov5s_edgetpu.tflite # TensorFlow Edge TPU """ import argparse import os import sys from pathlib import Path import torch import torch.backends.cudnn as cudnn FILE = Path(__file__).resolve() ROOT = FILE.parents[0] # YOLOv5 root directory if str(ROOT) not in sys.path: sys.path.append(str(ROOT)) # add ROOT to PATH ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative from models.common import DetectMultiBackend from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2, increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh) from utils.plots import Annotator, colors, save_one_box from utils.torch_utils import select_device, time_sync @torch.no_grad() def run( weights=ROOT / 'yolov5s.pt', # model.pt path(s) source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam data=ROOT / 'data/coco128.yaml', # dataset.yaml path imgsz=(640, 640), # inference size (height, width) 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=ROOT / '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 dnn=False, # use OpenCV DNN for ONNX inference ): source = str(source) save_img = not nosave and not source.endswith('.txt') # 判断nosave 以及source是否为txt文件 is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS) # 是否是图像或者视频文? is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://')) # 是否是网络链? webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file) # 是否启用网络摄像? if is_url and is_file: source = check_file(source) # download 下载文件 # Directories save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run 生成增量文件?run/detect/exp (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir 创建文件? # Load model device = select_device(device) # 选择设备（GPU or CPU? model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half) #检测编译框架，根据不同的编译框架读取不同类型的权重文件 pytorch、tensorflow、tensorrt? stride, names, pt = model.stride, model.names, model.pt imgsz = check_img_size(imgsz, s=stride) # check image size 检查输入图片的尺寸是否能被 stride(32) 整除，如果不能则调整图片大小后返? # Dataloader if webcam: # 如果开启摄像头 view_img = check_imshow() cudnn.benchmark = True # set True to speed up constant image size inference dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt) bs = len(dataset) # batch_size else: dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt) #直接从source文件夹下读取所有图片名? bs = 1 # batch_size vid_path, vid_writer = [None] * bs, [None] * bs # Run inference model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup 模型预热 dt, seen = [0.0, 0.0, 0.0], 0 for path, im, im0s, vid_cap, s in dataset: # path:图片路径 ，im:缩放后的图片，im0s：未缩放的原图， vid_cap：是否为视频，s：输出信? # from collections import Counter # count = Counter(im) t1 = time_sync() im = torch.from_numpy(im).to(device) im = im.half() if model.fp16 else im.float() # uint8 to fp16/32 半精?全精? im /= 255 # 0 - 255 to 0.0 - 1.0 归一? if len(im.shape) == 3: # 增加一个维? im = im[None] # expand for batch dim[1, 3, 640, 480] t2 = time_sync() dt[0] += t2 - t1 # Inference visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False # 是否增量生成文件?run/detect/exp pred = model(im, augment=augment, visualize=visualize) # 图片推理 [1,18900,85]=>([1, 3*(80*80+40*40+20*20), x,y,w,h,c,classes(80)]) t3 = time_sync() dt[1] += t3 - t2 # NMS pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) #NMS非极大抑? dt[2] += time_sync() - t3 # Second-stage classifier (optional) # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) # Process predictions 对每个预测框做处? for i, det in enumerate(pred): # per image seen += 1 if webcam: # batch_size >= 1 如果输入源时webcam则batch_size>=1,取出dataset中的一张图? p, im0, frame = path[i], im0s[i].copy(), dataset.count s += f'{i}: ' else: p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0) # frame：视频流 p = Path(p) # to Path save_path = str(save_dir / p.name) # im.jpg 结果图片路径 txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt 结果坐标信息txt文件路径 s += '%gx%g ' % im.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 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(im.shape[2:], det[:, :4], im0.shape).round() #将预测信息隐射到原图 # Print results for c in det[:, -1].unique(): # 打印检测到的类别数? 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 保存结果到txt文件 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 在图片上画框展示 c = int(cls) # integer class 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 save_crop: save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) #在原图上画框+将预测出来的目标剪切出来，保存成图片 # Stream results im0 = annotator.result() if view_img: # 显示图片 cv2.imshow(str(p), im0) cv2.waitKey(1) # 1 millisecond # Save results (image with detections) if save_img: # 保存图片 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 = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) vid_writer[i].write(im0) # Print time (inference-only) LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)') # Print results t = tuple(x / seen * 1E3 for x in dt) # speeds per image 打印图片检测速度 LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t) if save_txt or save_img: # 保存txt文件或者时保存图片 s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else '' LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}") if update: strip_optimizer(weights) # update model (to fix SourceChangeWarning) def parse_opt(): parser = argparse.ArgumentParser() parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'runs/train/shjd2/weights/best.pt', help='model path(s)') parser.add_argument('--source', type=str, default='/data/fengyang/sunwin/code/yolov5/test1', help='file/dir/URL/glob, 0 for webcam') # parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for webcam') # parser.add_argument('--data', type=str, default='/data2/fengyang/sunwin/data/image/shanghai_jiading/yolo_txt/shanghai_jiading.yaml', help='(optional) dataset.yaml path') parser.add_argument('--data', type=str, default='/data/fengyang/sunwin/data/helmet_fall_phone_delete_work/helmet_fall_phone.yaml', help='(optional) dataset.yaml path') parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w') parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold') # 置信度阈? parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold') # nms的iou阈? parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image') parser.add_argument('--device', default='cpu', 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: --classes 0, or --classes 0 2 3') parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS') # 进行nms是否也去除不同类别之间的框，默认为False parser.add_argument('--augment', action='store_true', help='augmented inference') #推理时进行多尺度、翻转等操作推理 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=ROOT / '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') parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference') opt = parser.parse_args() opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand print_args(vars(opt)) return opt def main(opt): check_requirements(exclude=('tensorboard', 'thop')) run(**vars(opt)) if __name__ == "__main__": opt = parse_opt() main(opt)