Yolov5目标检测之detect.py部分代码详解

# 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

from numpy import double

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  置信度阈值
        iou_thres=0.45,  # NMS IOU threshold iou阈值
                         # 若预测框和真实框之间的iou值大于iou_threshold，
                         # 就表明此预测框具有和真实框的相同属性（如类别、是否前景）。
                         
        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是否将预测的框坐标以txt文件形式保存
        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')  # save inference images
    #endswith() 方法用于判断字符串是否以指定后缀结尾
    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
    #startswith判断字符串是否以指定字符或子字符串开头
    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
    #isnumeric检测字符串是否只有数字组成
    if is_url and is_file:
        source = check_file(source)  # download

    # 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

    # Load model
    device = select_device(device)
    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
    #选择编译框架，选择。pt
    stride, names, pt = model.stride, model.names, model.pt
    imgsz = check_img_size(imgsz, s=stride)  # check image size
    # 确保输入图片的尺寸imgsz能整除stride=32 如果不能则调整为能被整除并返回

    # Dataloader加载数据
    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:
        # 如果检测视频的时候想显示出来，可以在这里加一行view_img = True
        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:
        t1 = time_sync()
        im = torch.from_numpy(im).to(device)
        im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
        #是否使用半精度
        im /= 255  # 0 - 255 to 0.0 - 1.0
        #归一化转到0-1
        if len(im.shape) == 3:
            im = im[None]  # expand for batch dim
            # 增加一个维度
        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)
        t3 = time_sync()
        dt[1] += t3 - t2

        # NMS
        """
               pred:前向传播的输出
               conf_thres:置信度阈值
               iou_thres:iou阈值
               classes:是否只保留特定的类别
               agnostic:进行nms是否也去除不同类别之间的框
               经过nms之后,预测框格式:xywh-->xyxy(左上角右下角)
               pred是一个列表list[torch.tensor],长度为batch_size
               每一个torch.tensor的shape为(num_boxes, 6),内容为box+conf+cls
               """

        pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
        dt[2] += time_sync() - t3

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

        # Process predictions
        # 对每一张图片作处理
        for i, det in enumerate(pred):  # per image
            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)
            # 但是大部分我们一般都是从LoadImages流读取本都文件中的照片或者视频 所以batch_size=1
            # p: 当前图片/视频的绝对路径 如 F:\yolo_v5\yolov5-U\data\images\bus.jpg
            # s: 输出信息 初始为 ''
            # im0: 原始图片 letterbox + pad 之前的图片
            # frame: 视频流

            p = Path(p)  # to Path
            # 当前路径yolov5/data/images/
            # 设置保存图片/视频的路径
            save_path = str(save_dir / p.name)  # im.jpg
            # 设置保存框坐标txt文件的路径
            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
            # 设置打印信息(图片长宽)
            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
                # 调整预测框的坐标：基于resize+pad的图片的坐标-->基于原size图片的坐标
                # 此时坐标格式为xyxy
                det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()

                # Print results打印检测到的类别数量
                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
                # 保存预测结果
                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()
                    # 将xyxy(左上角+右下角)格式转为xywh(中心点+宽长)格式，
                    # 并除上w，h做归一化，转化为列表再保存
                          # 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')
                     # # 在原图上画框 + 将预测到的目标剪切出来 保存成图片 
                     # 保存在save_dir/crops下 在原图像画图或者保存结果    
                    if save_img or save_crop or view_img:  # Add bbox to image
                        # 在原图上画框
                        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.waitKey(1)  # 1 millisecond
                cv2.imshow(str(p), im0)
                if cv2.waitKey(1) & 0xFF == ord('q'):
                   break
            # 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)


def parse_opt():
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='runs/train/exp7/weights/best.pt', help='model path(s)')
    #parser.add_argument('--source', type=str, default='rtsp://admin:a123456789@192.168.0.35:5035/main/av_stream', help='file/dir/URL/glob, 0 for webcam')
    parser.add_argument('--source', type=str, default='0', 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=[480], help='inference size h,w')
    """
    weights: 训练的权重路径,可以使用自己训练的权重,也可以使用官网提供的权重
    默认官网的权重yolov5s.pt(yolov5n.pt/yolov5s.pt/yolov5m.pt/yolov5l.pt/yolov5x.pt/区别在于网络的宽度和深度以此增加)
    source: 测试数据，可以是图片/视频路径，也可以是'0'(电脑自带摄像头),也可以是rtsp等视频流, 默认data/images
    data: 配置数据文件路径, 包括image/label/classes等信息, 训练自己的文件, 需要作相应更改, 可以不用管
    如果设置了只显示个别类别即使用了--classes = 0 或二者1, 2, 3等, 则需要设置该文件，数字和类别相对应才能只检测某一个类
    imgsz: 网络输入图片大小, 默认的大小是640
    conf-thres: 置信度阈值， 默认为0.25
    iou-thres:  做nms的iou阈值, 默认为0.45
    max-det: 保留的最大检测框数量, 每张图片中检测目标的个数最多为1000类
    device: 设置设备CPU/CUDA, 可以不用设置
    view-img: 是否展示预测之后的图片/视频, 默认False, --view-img 电脑界面出现图片或者视频检测结果
    save-txt: 是否将预测的框坐标以txt文件形式保存, 默认False, 使用--save-txt 在路径runs/detect/exp*/labels/*.txt下生成每张图片预测的txt文件
    save-conf: 是否将置信度conf也保存到txt中, 默认False
    save-crop: 是否保存裁剪预测框图片, 默认为False, 使用--save-crop 在runs/detect/exp*/crop/剪切类别文件夹/ 路径下会保存每个接下来的目标
    nosave: 不保存图片、视频, 要保存图片，不设置--nosave 在runs/detect/exp*/会出现预测的结果
    classes: 设置只保留某一部分类别, 形如0或者0 2 3, 使用--classes = n, 则在路径runs/detect/exp*/下保存的图片为n所对应的类别, 此时需要设置data
    agnostic-nms: 进行NMS去除不同类别之间的框, 默认False
    augment: TTA测试时增强/多尺度预测, 可以提分
    visualize: 是否可视化网络层输出特征
    update: 如果为True,则对所有模型进行strip_optimizer操作,去除pt文件中的优化器等信息,默认为False
    project: 保存测试日志的文件夹路径
    name: 保存测试日志文件夹的名字, 所以最终是保存在project/name中
    exist_ok: 是否重新创建日志文件, False时重新创建文件
    line-thickness: 画框的线条粗细
    hide-labels: 可视化时隐藏预测类别
    hide-conf: 可视化时隐藏置信度
    half: 是否使用F16精度推理, 半进度提高检测速度
    dnn: 用OpenCV DNN预测
    """ 
    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
    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)