第一步：YOLOv5介绍

YOLOv5是一种目标检测算法，它是YOLO（You Only Look Once）系列的最新版本。YOLOv5在YOLOv4的基础上进行了改进和优化，以提高检测的准确性和速度。

YOLOv5采用了一些新的技术和方法来改进目标检测的性能。其中包括以下几个方面：

1. 损失函数：YOLOv5使用了CIOU_Loss作为bounding box的损失函数。CIOU_Loss是一种改进的IOU_Loss，可以更好地衡量目标框的位置和大小。

2. 非极大值抑制（NMS）：YOLOv5使用NMS来抑制重叠的边界框，以减少重复检测的问题。

3. 聚类anchors：YOLOv5使用k-means聚类算法来生成anchors，这些anchors用于检测不同尺度的目标。

总的来说，YOLOv5在YOLOv4的基础上进行了一些改进和优化，以提高目标检测的准确性和速度。

标注数据，YOLOv5的训练和测试步骤，各路大神都已经做了很多工作，我就不再写了，这里有几个写的比较好的博客可以参考：

无脑008——yolov5目标检测全流程，训练自己的庞大数据集，半自动标注数据集_python 实现yolov5s 目标检测训练-CSDN博客


基于YOLOV5的数据集标注＆训练，Windows/Linux/Jetson Nano多平台部署全流程-CSDN博客

使用 YOLOv5 训练自建数据集教程 - 知乎

第二步：YOLOv5网络结构

第三步：代码展示

"""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='helmet.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 w = weights[0] if isinstance(weights, list) else weights classify, pt, onnx = False, w.endswith('.pt'), w.endswith('.onnx') # inference type stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults if pt: model = attempt_load(weights, map_location=device) # load FP32 model stride = int(model.stride.max()) # model stride names = model.module.names if hasattr(model, 'module') else model.names # get class names names[0] = "nohat" if half: model.half() # to FP16 if classify: # second-stage classifier modelc = load_classifier(name='resnet50', n=2) # initialize modelc.load_state_dict(torch.load('resnet50.pt', map_location=device)['model']).to(device).eval() elif onnx: check_requirements(('onnx', 'onnxruntime')) import onnxruntime session = onnxruntime.InferenceSession(w, None) imgsz = check_img_size(imgsz, s=stride) # check image size # 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 pt and 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: if pt: img = torch.from_numpy(img).to(device) img = img.half() if half else img.float() # uint8 to fp16/32 elif onnx: img = img.astype('float32') img /= 255.0 # 0 - 255 to 0.0 - 1.0 if len(img.shape) == 3: img = img[None] # expand for batch dim # Inference t1 = time_sync() if pt: visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False pred = model(img, augment=augment, visualize=visualize)[0] elif onnx: pred = torch.tensor(session.run([session.get_outputs()[0].name], {session.get_inputs()[0].name: img})) # NMS pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) t2 = time_sync() # Second-stage classifier (optional) if classify: pred = apply_classifier(pred, modelc, img, im0s) # Process predictions 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 {colorstr('bold', save_dir)}{s}") if update: strip_optimizer(weights) # update model (to fix SourceChangeWarning) print(f'Done. ({time.time() - t0:.3f}s)') return im0 def parse_opt(): parser = argparse.ArgumentParser() parser.add_argument('--weights', nargs='+', type=str, default='helmet.pt', help='model.pt path(s)') parser.add_argument('--source', type=str, default='0', 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)

第四步：运行

图片识别效果：

第五步：整个工程的内容

项目完整文件下载请见演示与介绍视频的简介处给出：➷➷➷

https://www.bilibili.com/video/BV13qUxYsEB7/