yolov5 检测detect.py笔记

FakeOccupational

已于 2022-10-29 21:01:21 修改

阅读量2.6k

点赞数 1

分类专栏：深度学习文章标签：深度学习 python pytorch

于 2022-09-26 16:00:00 首次发布

本文链接：https://blog.csdn.net/ResumeProject/article/details/126855728

版权

深度学习专栏收录该内容

162 篇文章 16 订阅

订阅专栏

参考

试运行

安装环境

在这里插入图片描述

(yolo) ┌──(venv)─(***㉿kali)-[~/myproject/yolov5]
└─$ pip install -qr requirements.txt

尝试运行

使用语句：python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images

(yolo) ┌──(venv)─(***㉿kali)-[~/myproject/yolov5]
└─$ python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images
detect: weights=['yolov5s.pt'], source=data/images, data=data/coco128.yaml, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False
YOLOv5 🚀 2022-5-20 torch 1.12.1+cu102 CPU

Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s.pt to yolov5s.pt...
ERROR: Remote end closed connection without response
Re-attempting https://storage.googleapis.com/ultralytics/yolov5/v6.2/yolov5s.pt to yolov5s.pt...
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100   196  100   196    0     0    265      0 --:--:-- --:--:-- --:--:--   265
ERROR: Downloaded file 'yolov5s.pt' does not exist or size is < min_bytes=100000.0
yolov5s.pt missing, try downloading from https://github.com/ultralytics/yolov5/releases/v6.2 or https://drive.google.com/drive/folders/1EFQTEUeXWSFww0luse2jB9M1QNZQGwNl

Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s.pt to yolov5s.pt...
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 14.1M/14.1M [00:04<00:00, 3.65MB/s]

Fusing layers... 
YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients
image 1/2 /home/***/myproject/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.242s)
image 2/2 /home/***/myproject/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.187s)
Speed: 1.8ms pre-process, 214.5ms inference, 1.0ms NMS per image at shape (1, 3, 640, 640)
Results saved to runs/detect/exp

解释

在这里插入图片描述

导包

import argparse
……
import torch
import torch.backends.cudnn as cudnn

FILE = Path(__file__).resolve() # C:\Users\zkh\Desktop\yolov5\detect.py , __file__:当前路径，.resolve():获取绝对路径
ROOT = FILE.parents[0]  #获取父目录  YOLOv5 root directory, C:\Users\zkh\Desktop\yolov5 
if str(ROOT) not in sys.path: # 模块的查询路径的列表  方便导入自己写的包
    sys.path.append(str(ROOT))  # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative ,绝对路径转换成相对路径

from models.common import DetectMultiBackend

path.resolve()方法可以将多个路径解析为一个规范化的绝对路径。其处理方式类似于对这些路径逐一进行 cd 操作，与 cd 操作不同的是，这引起路径可以是文件，并且可不必实际存在（resolve()方法不会利用底层的文件系统判断路径是否存在，而只是进行路径字符串操作）

主函数

if __name__ == "__main__":
    opt = parse_opt()# 解析参数
    main(opt)# 执行主函数

解析参数

def parse_opt():
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)')
    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=ROOT / 'data/coco128.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')
    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: --classes 0, or --classes 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=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 专门判断一下imgsz是不是1,如果长度为1，自动乘2，从[640]变为[640 640]
    print_args(vars(opt)) # 打印参数信息
    return opt

def main(opt):
    check_requirements(exclude=('tensorboard', 'thop'))# 检查当前环境是否满足 requirements.txt
    run(**vars(opt))

run函数

run函数分为6个部分


source = str(source)	对检测的source处理
increment_path	设置结果保存的文件夹
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)	下载模型，加载模型，确定检测结果的种类，是否半精度，模型步长
img = letterbox(img0，……	daterloder加载数据，设置读取图片的规则，letterbox(padding resize到特定大小)
pred = model(im, augment=augment, visualize=visualize) # torch.Size([1, 18900, 85])	Run inference推断，85是位置4(左上右下)+置信度1+类别80
	im = im[None] # expand for batch dim , torch.Size([1, 3, 640, 480])
	NMS 结果处理（非极大值抑制）[6.72000e+02, 3.95000e+02, 8.10000e+02, 8.78000e+02, 8.96172e-01（置信度）, 0.00000e+00(第一个类别是人)]
	save_path = str(save_dir / p.name) 设置保存路径(整张图像结果,txt文本结果，是否裁剪保存)
	Annotator是专门画检测框的工具
LOGGER.info(f’Speed:……	打印结果

@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 用于设置自己的数据集
        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) # 'python detect.py --source data\\images\\bus.jpg'
    save_img = not nosave and not source.endswith('.txt')  # save inference images
    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
    if is_url and is_file:
        source = check_file(source)  # download

    # Directories 设置结果保存的文件夹
    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  #增量路径 increment run, runs\\detect\\exp3
    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir 指定txt保存

    # Load model
    device = select_device(device)
    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)# 多后端环境检测加载模型
    stride, names, pt = model.stride, model.names, model.pt
    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, auto=pt)
        bs = len(dataset)  # batch_size
    else:
        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
        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
    dt, seen = [0.0, 0.0, 0.0], 0
    for path, im, im0s, vid_cap, s in dataset: # "C:\\Users\\zkh\\Desktop\\yolov5\\data\\images\\bus.jpg"
        t1 = time_sync()
        im = torch.from_numpy(im).to(device) # torch.Size([3, 640, 480])
        im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
        im /= 255  # 0 - 255 to 0.0 - 1.0
        if len(im.shape) == 3:
            im = im[None]  # expand for batch dim , torch.Size([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
        pred = model(im, augment=augment, visualize=visualize) # torch.Size([1, 18900, 85])
        t3 = time_sync()
        dt[1] += t3 - t2

        # NMS
        pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) # 1,5,6 . [6.72000e+02, 3.95000e+02, 8.10000e+02, 8.78000e+02, 8.96172e-01, 0.00000e+00]
        dt[2] += time_sync() - t3

        # Second-stage classifier (optional)
        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)

        # Process predictions
        for i, det in enumerate(pred):  # per image,torch.Size([5, 6])
            seen += 1
            if webcam:  # batch_size >= 1
                p, im0, frame = path[i], im0s[i].copy(), dataset.count
                s += f'{i}: '
            else:
                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)

            p = Path(p)  # to Path
            save_path = str(save_dir / p.name)  # im.jpg, "runs\\detect\\exp3","bus.jpg"
            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
            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()

                # 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}')
                        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)

            # Stream results
            im0 = annotator.result()
            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 = 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
    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:
        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)