执行方法:

代码

# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
"""
Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc.

Usage - sources:
    $ python detect.py --weights yolov5s.pt --source 0                               # webcam
                                                     img.jpg                         # image
                                                     vid.mp4                         # video
                                                     screen                          # screenshot
                                                     path/                           # directory
                                                     list.txt                        # list of images
                                                     list.streams                    # list of streams
                                                     'path/*.jpg'                    # glob
                                                     'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                                                     'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream

Usage - formats:
    $ python detect.py --weights yolov5s.pt                 # PyTorch
                                 yolov5s.torchscript        # TorchScript
                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
                                 yolov5s_openvino_model     # 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
                                 yolov5s_paddle_model       # PaddlePaddle
"""

import argparse
import os
import platform
import sys
from pathlib import Path

import torch

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.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
                           increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, smart_inference_mode


@smart_inference_mode()
def run(
        weights=ROOT / 'yolov5s.pt',  # model path or triton URL
        source=ROOT / 'data/images',  # file/dir/URL/glob/screen/0(webcam)
        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
        imgsz=(640, 640),  # inference size (height, width)
        conf_thres=0.70,  # confidence threshold
        # iou_thres=0.45,  # NMS IOU threshold
        iou_thres=0.50,  # NMS IOU threshold
        max_det=1000,  # maximum detections per image
        device='0',  # 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 label
        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 label
        hide_conf=False,  # hide confidences
        half=False,  # use FP16 half-precision inference
        dnn=False,  # use OpenCV DNN for ONNX inference
        vid_stride=1,  # video frame-rate stride
):
    '''第一部分: 对source进行额外的判断'''
    source = str(source) # 路径转为字符串，防止非字符串路径
    # 如果nosave为false,source不是以txt结尾，则save_img=true 即结果需要保存
    save_img = not nosave and not source.endswith('.txt')  # save inference images
    # 判断传入的路径是不是文件地址 suffix表示后缀, suffix[1:]即此处的jpg, IMG_FORMATS + VID_FORMATS表示图片和视频的格式
    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
    # 判断是不是网络流地址并转换为小写字母
    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
    # isnumeric() 好像是判断是不是数字 本地是0
    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
    screenshot = source.lower().startswith('screen')
    # 判断是不是网络流 和 是不是网络流里面的文件，如果是则进入进行 下载网络流中的图片和视频
    if is_url and is_file:
        source = check_file(source)  # download

    '''第二部分: 新建保存结果的文件夹'''
    # Directories
    # 检测文件夹下的数字到几了，把每一次的结果增量保存
    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
    (save_dir / 'label' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir

    '''第三部分：加载模型的权重'''
    # Load model
    # 选择加载模型的设备，如果是GPU则选择GPU
    device = select_device(device)
    # 选择模型的后端框架, dnn默认是false，data是训练和测试的文件，如果是pytorch就用pytorch的加载方式，其他的用其他的方式
    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
    # nodel.names 表示默认的类别 此处是初始值 后面会变的
    stride, names, pt = model.stride, model.names, model.pt
    # 输入待推理的图片 检查根据640*640和32步长，判断是否是32的倍数 不是的话就再计算一个倍数
    imgsz = check_img_size(imgsz, s=stride)  # check image size

    '''第四部分：加载待预测的图片'''
    # Dataloader
    bs = 1  # batch_size
    if webcam:
        view_img = check_imshow(warn=True)
        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
        bs = len(dataset)
    elif screenshot:
        dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt)
    else:
        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
    vid_path, vid_writer = [None] * bs, [None] * bs

    '''第五部分：执行模型的推理，产生预测结果，画出预测框'''
    # Run inference
    # warmup是热身的意思 初始化一张空白图片 让模型跑一下
    model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmup
    seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
    # 遍历之后，得到图片路径，im是resize后的图片，im0 shi yuantu
    for path, im, im0s, vid_cap, s in dataset:
        # 对图片预处理
        with dt[0]:
            # 图片是numpy格式，必须把它转为Pytorch支持的格式，并把他放到 device (GPU)上
            im = torch.from_numpy(im).to(model.device)
            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
            # 归一化 确保像素在0-255之间
            im /= 255  # 0 - 255 to 0.0 - 1.0
            # 图片是 (长，宽，通道)，现在给他扩展一下，给出batch的位置
            if len(im.shape) == 3:
                im = im[None]  # expand for batch dim

        # Inference: 对图片进行预测
        with dt[1]:
            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
            # augment是看是否对图片进行增强 得到所有的检测框 一个图片上万个， (1,18900,85),4个坐标信息，1个置信度信息和80个类别的概率值
            pred = model(im, augment=augment, visualize=visualize)

        # NMS: 对预测的18900个框进行过滤，使用的是置信度阈值，Iou阈值，max_det是最大能检测的目标，run函数默认1000个，如果超出1000个自动过滤掉剩下的目标
        with dt[2]:
            '''
                最终得到[1,5,6,[类别]]
                1：是一个batch
                5：是将上万个检测框降低到5个检测框
                6: 目标的 x_left_up,y_left_up,x_right_down,y_right_down,置信度,目标所属类别()
            '''
            pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)

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

        '''
           遍历pred，遍历一个batch中的每个图片 
        '''
        # Process predictions
        for i, det in enumerate(pred):  # per image
            seen += 1 #计数，每处理一个图片则+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)  # 图片保存路径 im.jpg
            # txt路径
            txt_path = str(save_dir / 'label' / 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
            # 定义一个专门绘图的工具 line_thickness是线条粗细 str(names)标签名
            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
            if len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()

                # Print results
                for c in det[:, 5].unique():
                    n = (det[:, 5] == 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(f'{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:
                if platform.system() == 'Linux' and p not in windows:
                    windows.append(p)
                    cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)  # allow window resize (Linux)
                    cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
                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)

        '''第六部分：打印输出信息'''
        # Print time (inference-only)
        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")

    # Print results
    t = tuple(x.t / 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('label/*.txt')))} label saved to {save_dir / 'label'}" if save_txt else ''
        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
    if update:
        strip_optimizer(weights[0])  # update model (to fix SourceChangeWarning)


def parse_opt():
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path or triton URL')
    parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob/screen/0(webcam)')
    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
    # 模型预测的图片大小 默认是[640]
    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=0.60, help='confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.55, 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 label')
    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 label')
    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')
    parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride')
    opt = parser.parse_args()

    # 检查图片大小：如果opt.imgsz的长度为1，即默认值[640]，则变成640的平方即 640*640，否则就不动了
    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand

    # 打印所有信息
    print_args(vars(opt))

    # 返回所有变量信息
    return opt


def main(opt):
    # 检测 requirements的包有没有成功安装
    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
    # 检测完成，传递参数
    run(**vars(opt))

if __name__ == '__main__':
    opt = parse_opt()
    main(opt)