yoloV5预测时生成关于图片的重要信息到xml中

版本6.1

半自动化标注可以借鉴一下

# 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        # ImageSets
                                                             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.Annotations                # 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 platform
import sys
from pathlib import Path

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.dataloaders 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
from xml.etree import ElementTree as ET
from xml.dom.minidom import Document

labelsPath = "./data/auto.names"
LABELS = open(labelsPath).read().strip().split("\n")
print(LABELS)
def create_tree(img_name, img_path, img_width, img_height):
    doc = Document()  # 创建DOM文档对象
    item = doc.createElement('annotation')  # 创建根元素
    doc.appendChild(item)
    # 设置一个filename代表图片名字
    filename = doc.createElement('filename')
    filename_text = doc.createTextNode(img_name)  # 图片名字
    filename.appendChild(filename_text)
    item.appendChild(filename)

    width_url = doc.createElement('width')
    width_url_text = doc.createTextNode(str(img_width))  # 图片宽度
    height_urt = doc.createElement('height')
    height_urt_text = doc.createTextNode(str(img_height))  # 图片高度
    size = doc.createElement('img_size')
    item.appendChild(size)
    size.appendChild(width_url)
    size.appendChild(height_urt)
    width_url.appendChild(width_url_text)
    height_urt.appendChild(height_urt_text)

    # 设置一个path代表图片路径
    path = doc.createElement('path')
    path_text = doc.createTextNode(img_path)  # 图片路径
    path.appendChild(path_text)
    item.appendChild(path)
    return doc,item
def create_obgect(doc,item,object_name, box_min_x, box_min_y, box_max_x, box_max_y):



    object = doc.createElement('object')
    item.appendChild(object)
    name_url = doc.createElement('name')
    name_url_text = doc.createTextNode(object_name)  # 检测到的物体类别
    object.appendChild(name_url)
    name_url.appendChild(name_url_text)
    ############################################
    bndbox = doc.createElement('bndbox')
    item.appendChild(bndbox)
    xmin_url = doc.createElement('xmin')
    xmin_url_text = doc.createTextNode(str(box_min_x))  # 检测框框的X最小值
    bndbox.appendChild(xmin_url)
    xmin_url.appendChild(xmin_url_text)

    ymin_url = doc.createElement('ymin')
    ymin_url_text = doc.createTextNode(str(box_min_y))  # 检测框框的Y最小值
    bndbox.appendChild(ymin_url)
    ymin_url.appendChild(ymin_url_text)

    xmax_url = doc.createElement('xmax')
    xmax_url_text = doc.createTextNode(str(box_max_x))  # 检测框框的X最大值
    bndbox.appendChild(xmax_url)
    xmax_url.appendChild(xmax_url_text)

    ymax_url = doc.createElement('ymax')
    ymax_url_text = doc.createTextNode(str(box_max_y))  # 检测框框的Y最大值
    bndbox.appendChild(ymax_url)
    ymax_url.appendChild(ymax_url_text)


def writXML(filename,doc):
    f = open(filename+'.xml', "w")
    doc.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
    f.close()
    print('fine')



@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
        iou_thres=0.45,  # NMS IOU threshold
        max_det=1000,  # maximum detections per ImageSets
        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=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
    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
    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)
    stride, names, pt = model.stride, model.names, model.pt
    imgsz = check_img_size(imgsz, s=stride)  # check ImageSets size

    # Dataloader
    if webcam:
        view_img = check_imshow()
        cudnn.benchmark = True  # set True to speed up constant ImageSets size inference
        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
        bs = len(dataset)  # batch_size
    else:
        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
    seen, windows, dt = 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
        im /= 255  # 0 - 255 to 0.0 - 1.0
        if len(im.shape) == 3:
            im = im[None]  # expand for batch dim
        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 = 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)
########################################################################
        (h, w) = im0s.shape[:2]  # 获取图片的宽和高
        print("source:",source,"path:",path,"h:",h,"w:",w) # path:图片路径 h 图片高度 w图片宽度
        img_name = os.path.split(path)[-1]  # 图片名字
        doc, item = create_tree(img_name=img_name, img_path=path,img_width=w,img_height=h)
########################################################################
        # Process predictions
        for i, det in enumerate(pred):  # per ImageSets
            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)

            p = Path(p)  # to Path
            save_path = str(save_dir / p.name)  # im.jpg
            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'ImageSets' 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
            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
            if len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_coords(im.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):

###########################################################
                    box_ = torch.tensor(xyxy).numpy()
                    x1, y1, x2, y2 = int(box_[0]), int(box_[1]), int(box_[2]), int(box_[3])
                    label = LABELS[int(cls)]
                    print("x1, y1, x2, y2, label:  ", x1, y1, x2, y2, label)
                    create_obgect(doc=doc,item=item,object_name=label,box_min_x=x1,box_min_y=y1,box_max_x=x2,box_max_y=y2)
                    # create_object(annotation, x1, y1, x2, y2, label)
###########################################################

                    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')


                    writXML2 = writXML(filename=img_name,doc=doc)
#########################################################
                    if save_img or save_crop or view_img:  # Add bbox to ImageSets
                        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 (ImageSets with detections)
            if save_img:
                if dataset.mode == 'ImageSets':
                    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 ImageSets
    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per ImageSets 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[0])  # update model (to fix SourceChangeWarning)



def parse_opt():
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default=r'E:\yolov5-master\runs\train\exp5\weights\best.pt', help='model path(s)')
    parser.add_argument('--source', type=str, default=r'E:\yolov5-master\VOCdevkit\VOC2007\images', help='file/dir/URL/glob, 0 for webcam')
    parser.add_argument('--data', type=str, default=ROOT / 'data/VOC.yaml', help='(optional) dataset.yaml path')
    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=0.7, help='confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.5, help='NMS IoU threshold')
    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per ImageSets')
    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)