图像处理项目2

需求2：检测人体是否在最佳范围内

import argparse
import time
from pathlib import Path
import pandas

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, check_imshow, non_max_suppression, apply_classifier, \
    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, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
    save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
        ('rtsp://', 'rtmp://', 'http://', 'https://'))

    # 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()
    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 = check_imshow()
        cudnn.benchmark = True  # set True to speed up constant image size inference
        dataset = LoadStreams(source, img_size=imgsz, stride=stride)
    else:
        dataset = LoadImages(source, img_size=imgsz, stride=stride)


    # 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()
    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]

        """
        pred: 前向传播的输出
        conf_thresh:置信度
        iou——thres：iou阈值
        agnostic:进行nms是否也去除不同类别之间的框
        xywh -->>xyxy(左上角右下角)
        pred：是一个列表list[torch.tesor],长度为NMS后的目标框的个数
        每个torch.tesor的shape为(num_boxes, 6)内容为box（4个值）+conf+cls
        """
        # Apply NMS
        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
        t2 = time_synchronized()

        # Apply Classifier
        if classify:
            pred = apply_classifier(pred, modelc, img, im0s)
        # Process detections
        for i, det in enumerate(pred):  # detections per image  其中i代表第几个框，det是检测的结果信息
            # 建立一个结果列表和照片名字列表
            imgNameList = []
            result_list = []
            xyxyList = []

            if webcam:  # batch_size >= 1
                p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
            else:
                p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)

            p = Path(p)  # to 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 += '%g x %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
                det[:, :4] = scale_coords(img.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):
                    print("--------------------------")
                    xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()
                    xyxyList.append(xyxy)
                    # print(f'xyxyList内容为{xyxyList}')
                    # print("--------------------------")
                    if save_txt:  # Write to file
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh  将左上角右下角坐标转换为--中心点+宽高
                        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')


                    if save_img or view_img:  # Add bbox to image
                        label = f'{names[int(cls)]} {conf:.2f}'
                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()
                        # c1,c2分别为左上角坐标和右下角坐标
                        c1, c2 = (int(xyxy[0]), int(xyxy[1])), (int(xyxy[2]), int(xyxy[3]))
                        center_xx = (c1[0] + c2[0]) / 2
                        center_yy = (c1[1] + c2[1]) / 2

                        # print(f"xyxy的值为{xyxy}")

                        print(f"左上角坐标为：{c1}, 右下角坐标为：{c2}，中心点坐标为：{(center_xx, center_yy)}")
                        print("++++++++++++++++++++++++++++++++++")

            # print("++++++++++++++++++++++++++++++++++")
            # print(f'xywhList为{xywhList}')

            def find_max():
                return max(xyxyList, key=lambda wh_Tuple:(wh_Tuple[2]-wh_Tuple[0]) * wh_Tuple[3]-wh_Tuple[1])
            maxItem = find_max()
            center_X = (int(maxItem[0])+int(maxItem[2])) / 2
            center_Y = (int(maxItem[1])+int(maxItem[3])) / 2
            center_area_point = (center_X, center_Y)  # 区域面积最大的框的中心点坐标
        # 判断是否在框内
            origin_width = len(im0[0])
            origin_height = len(im0)
            devide_3_width = origin_width // 3
            devide_3_height = origin_height // 3
            # 中心区域左上角坐标
            center_left_top_x = devide_3_width
            center_left_top_y = devide_3_height
            # 中心区域右下角坐标
            center_right_bottom_x = center_left_top_x + devide_3_width
            center_right_bottom_y = center_left_top_y + devide_3_height
            cv2.rectangle(im0, (center_left_top_x, center_left_top_y), (center_right_bottom_x, center_right_bottom_y), color=(220, 232,255) , thickness=1, lineType=cv2.LINE_AA)


            imgName = path.split("/")[-1]
            imgNameList.append(imgName)

            if center_X > center_left_top_x and center_X < center_right_bottom_x and center_Y > center_left_top_y and center_Y < center_right_bottom_y:
                result_list.append("在最佳范围内")

            else:
                result_list.append("不在最佳范围内")

            print(f"长度为{len(result_list)}")


            # print(f"im0的宽度为:{len(im0[0])}, 高度为{len(im0)}")
            #
            # print(f"面积最大区域的左上角坐标为{(int(maxItem[0]), int(maxItem[1])), (int(maxItem[2]), int(maxItem[3]))}"
            #       f"中心点坐标为{center_area_point}")


            # Print time (inference + NMS)
            print(f'{s}Done. ({t2 - t1:.3f}s)')
            print()
            # Stream results
            if view_img:
                cv2.imshow(str(p), im0)
                cv2.waitKey(10000)  # 1 millisecond
                cv2.destroyAllWindows()

            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'image':
                    cv2.imwrite(save_path, im0)
                else:  # 'video' or 'stream'
                    if vid_path != save_path:  # new video
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.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 = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
                    vid_writer.write(im0)

        zipList = zip(imgNameList, result_list)
        resultDict = dict(zipList)
        print(resultDict)

    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='/home/ma/project/yolov5-5.0_fire/weights/yolov5s.pt', help='model.pt path(s)')
    parser.add_argument('--source', type=str, default='/home/ma/project/yolov5-5.0_fire/dataset/202301131344', help='source')  # file/folder, 0 for webcam
    parser.add_argument('--img-size', type=int, default=448, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
    parser.add_argument('--device', default='cpu', 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('--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('--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(exclude=('pycocotools', 'thop'))

    with torch.no_grad():  # 上下文管理器
        if opt.update:  # update all models (to fix SourceChangeWarning)
            for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
                detect()
                strip_optimizer(opt.weights)
        else:
            detect()