Detailed explanation of yolov5 detection code

import argparse 
import time 
from pathlib import Path 

import cv2 
import torch 
import torch.backends.cudnn as cudnn 
from numpy import random 

from models.experimental import attempt_load 
from utils.datasets import LoadStreams, 
LoadImages from utils.general import check_img_size, check_requirements, non_max_classifier, apply , scale_coords, \ 
    xyxy2xywh, strip_optimizer, set_logging, increment_path 
from utils.plots import plot_one_box 
from utils.torch_utils import select_device, load_classifier, time_synchronized 


def detect(save_img=False): 
    #source: test data, it can be a picture/video path or it can It is '0' (the computer comes with a camera), or it can be a video stream such as rtsp. 
    #view_img Whether to display the picture/video after prediction, the default is False
    #save_txt Whether the predicted frame coordinates are saved as a txt file, the default is False 
    #imgsz The size of the network input image 
    source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt. img_size 
    # The isnumeric () method detects whether the string is only composed of numbers 
    #lower()Uppercase letters are converted to lowercase letters. Does startswith start with the specified string 
    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith( 
        ('rtsp://','rtmp://','http://')) 
    # Directories 
    save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) # increment run 
    (save_dir /'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir 
    # Initialize 
    set_logging() #Select 
    device 
    device = select_device(opt.device)
    half = device.type != 'cpu'  # half precision only supported on CUDA

    # Load model
    model = attempt_load(weights, map_location=device)  # load FP32 model
    stride = int(model.stride.max())  # model stride
    imgsz = check_img_size(imgsz, s=stride)  # check img_size
    if half:
        model.half()  # to FP16

    # Second-stage classifier
    classify = False
    if classify:
        modelc = load_classifier(name='resnet101', n=2)  # initialize
        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()

    # Set Dataloader
    vid_path, vid_writer = None, None
    # if webcam:
    #     view_img = True
    #     cudnn.benchmark = True  # set True to speed up constant image size inference
    # dataset = LoadStreams(source, img_size=imgsz, stride=stride) 
    # else: 
    save_img = True 
    dataset = LoadImages(source, img_size=imgsz, stride=stride) 
    print(dataset) 
    # Get names and colors 
    names = model.module. names if hasattr(model,'module') else model.names 
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names] 

    # Run inference 
    if device.type != 'cpu':
        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once 
    t0 = time.time() 
    #img0 = cv2.imread(path) 
    #path图片/视频PATH 
    # Picture after img resize + pad 
    # img0原size图片
    # cap is None when reading a picture, and it is a video source when reading a video
    for path, img, im0s, vid_cap in dataset: 
        img = torch.from_numpy(img).to(device) 
        img = img.half() if half else img.float() # uint8 to fp16/32 
        img /= 255.0 # 0-255 to 
        0.0-1.0 if img.ndimension() == 3: 
            img = img.unsqueeze(0) 

        # Inference 
        t1 = time_synchronized() 
        pred = model(img, augment=opt.augment)[0] 

        # Apply NMS 
        # Apply NMS 
        """
        pred: output of forward propagation 
        conf_thres: confidence threshold 
        iou_thres: iou threshold 
        classes: whether to retain only specific categories 
        agnostic: whether to perform nms and remove the boxes between different categories 
        After nms, the prediction box format: xywh- ->xyxy (upper left corner and lower right corner)
        pred is a list list[torch.tensor], the length is batch_size 
        , the shape of each torch.tensor is (num_boxes, 6), and the content is box+conf+cls 
        """ 
        pred = non_max_suppression(pred, opt.conf_thres, opt. iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms) 
        t2 = time_synchronized() 

        # Apply Classifier #Add 
        secondary classification, not used by default 
        if classify: 
            pred = apply_classifier(pred, modelc, img, im0s) 

        # Process detections 
        # Process each picture  
        for i, det in enumerate(pred): # detections per image
            if webcam: # batch_size >= 1 
                p, s, im0, frame = path[i],'%g: '% i, im0s[i].copy(), dataset.count 
            else: 
                #getattr(dataset,'frame', 0) Get the attribute value frame in the dataset, return 0 
                p, s, im0, frame = path,'', im0s, getattr(dataset, 'frame', 0) 

            p = Path(p) # to Path 
            #Image 
            save 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 
            if len(det):
                # Rescale boxes from img_size to im0 size #The 
                coordinate format is xyxy
                det[:, :4] = scale_coords(img.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
                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 opt.save_conf else (cls, *xywh)  # label format
                        with open(txt_path +'.txt','a') as f: 
                            f.write(('%g '* len(line)).rstrip()% line +'\n')im0)
            # Save results (image with detections)

                    if save_img or view_img: # Add bbox to image #Output 
                        label and score value 
                        label = f'{names[int(cls)]} {conf:.2f}' 
                        #Draw 
                        category and score box information plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=5) 

            # Print time (inference + NMS) 
            print(f'{s}Done. ({t2-t1:.3f}s)') 

            # Stream results 
            if view_img: 
                cv2.imshow(str(p), im0) 

            if save_img: 
                if dataset.mode =='image': 
                    cv2.imwrite(save_path, im0) 
                else: #'video'
                    if vid_path != save_path:  # new video
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.release()  # release previous video writer

                        fourcc = 'mp4v'  # output video codec
                        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))
                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h))
                    vid_writer.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 {save_dir}{s}")

    print(f'Done. ({time.time() - t0:.3f}s)')


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    # parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
    parser.add_argument('--weights', nargs='+', type=str, default='./runs/train/exp29/weights/best.pt', help='model.pt path(s)')
    parser.add_argument('--source', type=str, default='data/images', help='source')  # file/folder, 0 for webcam
    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)') 
    parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
    output threshold#Confidence
    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
    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='display 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('--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('--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')
    opt = parser.parse_args()
    print(opt)
    check_requirements()

    with torch.no_grad():
        if opt.update:  # update all models (to fix SourceChangeWarning)
            for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']: 
                opt and other information in the weight
                detect()
                strip_optimizer(opt.weights)
        else:
            detect()