detect.py

"""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_synchronized


@torch.no_grad()
def run(weights='yolov5s.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
        ):
    # 是否保存图片
    save_img = not nosave and not source.endswith('.txt')  # save inference images
    # 判断预测源是否为视频流
    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
        ('rtsp://', 'rtmp://', 'http://', 'https://'))

    # Directories
    # 获取保存预测路径
    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
    # 初始化logging
    set_logging()
    # 获取设备
    device = select_device(device)
    # 如果设备为gpu且opt.half=True，使用Float16
    half &= device.type != 'cpu'  # half precision only supported on CUDA

    # Load model
    # 加载Float32模型，确保用户设定的输入图片分辨率能整除32(如不能则调整为能整除并返回)
    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 image size
    # 获取类别名字
    names = model.module.names if hasattr(model, 'module') else model.names  # get class names
    # 设置Float16
    if half:
        model.half()  # to FP16

    # Second-stage classifier
    # 设置第二次分类，默认不使用
    classify = False
    if classify:
        modelc = load_classifier(name='resnet50', n=2)  # initialize
        modelc.load_state_dict(torch.load('resnet50.pt', map_location=device)['model']).to(device).eval()

    # Dataloader
    # 通过不同的输入源来设置不同的数据加载方式
    if webcam:
        # 检查当前环境是否能够正常imshow
        view_img = check_imshow()
        cudnn.benchmark = True  # set True to speed up constant image size inference
        dataset = LoadStreams(source, img_size=imgsz, stride=stride)
        # batch-size
        bs = len(dataset)  # batch_size
    else:
        dataset = LoadImages(source, img_size=imgsz, stride=stride)
        # batch-size
        bs = 1  # batch_size
    vid_path, vid_writer = [None] * bs, [None] * bs

    # Run inference
    # 进行一次前向推理,测试程序是否正常
    if device.type != 'cpu':
        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
    t0 = time.time()
    """
    path 图片/视频路径
    img 进行resize+pad之后的图片
    img0 原size图片
    cap 当读取图片时为None，读取视频时为视频源
    """
    for path, img, im0s, vid_cap in dataset:
        img = torch.from_numpy(img).to(device)
        # 图片也设置为Float16
        img = img.half() if half else img.float()  # uint8 to fp16/32
        img /= 255.0  # 0 - 255 to 0.0 - 1.0
        # 没有batch_size的话则在最前面添加一个轴
        if img.ndimension() == 3:
            img = img.unsqueeze(0)

        # Inference
        t1 = time_synchronized()
        """
        前向传播 返回pred的shape是(1, num_boxes, 5+num_class)
        h,w为传入网络图片的长和宽，注意dataset在检测时使用了矩形推理，所以这里h不一定等于w
        num_boxes = h/32 * w/32 + h/16 * w/16 + h/8 * w/8
        pred[..., 0:4]为预测框坐标
        预测框坐标为xywh(中心点+宽长)格式
        pred[..., 4]为objectness置信度
        pred[..., 5:-1]为分类结果
        """
        pred = model(img,
                     augment=augment,
                     visualize=increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False)[0]

        # Apply 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_nms:进行nms是否也去除不同类别之间的框
        max-det:保留的最大检测框数量
        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)
        t2 = time_synchronized()

        # Apply Classifier
        # 添加二次分类，默认不使用
        if classify:
            pred = apply_classifier(pred, modelc, img, im0s)

        # Process detections
        # 对每一张图片作处理
        for i, det in enumerate(pred):  # detections per image
            # 如果输入源是webcam，则batch_size不为1，取出dataset中的一张图片
            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
            # 设置保存图片/视频的路径
            save_path = str(save_dir / p.name)  # img.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}')  # img.txt
            # 设置打印信息(图片长宽)
            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
                # 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(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
                # 保存预测结果
                for *xyxy, conf, cls in reversed(det):
                    if save_txt:  # Write to file
                        # 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
                        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')

                    # 在原图上画框
                    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:
                            # 保存crop
                            save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)

            # Print time (inference + NMS)
            # 打印前向传播+nms时间
            print(f'{s}Done. ({t2 - t1:.3f}s)')

            # Stream results
            # 如果设置展示，则show图片/视频
            if view_img:
                cv2.imshow(str(p), im0)
                cv2.waitKey(1)  # 1 millisecond

            # Save results (image with detections)
            # 设置保存图片/视频
            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)

    # 显示保存信息
    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}")

    # strip_optimizer函数将pt文件中除了模型model或者ema之外的所有东西去除；
    if update:
        strip_optimizer(weights)  # update model (to fix SourceChangeWarning)

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


def parse_opt():
    """
    weights:训练的权重
    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
    imgsz:网络输入图片大小
    conf-thres:置信度阈值
    iou-thres:做nms的iou阈值
    max-det:保留的最大检测框数量
    device:设置设备
    view-img:是否展示预测之后的图片/视频，默认False
    save-txt:是否将预测的框坐标以txt文件形式保存，默认False
    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
    nosave:不保存图片、视频
    classes:设置只保留某一部分类别，形如0或者0 2 3
    agnostic-nms:进行nms是否也去除不同类别之间的框，默认False
    augment:推理的时候进行多尺度，翻转等操作(TTA)推理
    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
    """
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
    parser.add_argument('--source', type=str, default='data/images', 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()))
    # 检查环境
    check_requirements(exclude=('tensorboard', 'thop'))
    run(**vars(opt))


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