yolov7混淆矩阵

测试部分代码

import argparse
import json
import os
from pathlib import Path
from threading import Thread

import numpy as np
import torch
import yaml
from tqdm import tqdm

from models.experimental import attempt_load
from utils.datasets import create_dataloader
from utils.general import coco80_to_coco91_class, check_dataset, check_file, check_img_size, check_requirements, \
    box_iou, non_max_suppression, scale_coords, xyxy2xywh, xywh2xyxy, set_logging, increment_path, colorstr
from utils.metrics import ap_per_class, ConfusionMatrix
from utils.plots import plot_images, output_to_target, plot_study_txt
from utils.torch_utils import select_device, time_synchronized, TracedModel


def test(data,
         weights=None,
         batch_size=32,
         imgsz=640,
         conf_thres=0.001,
         iou_thres=0.6,  # for NMS
         save_json=False,
         single_cls=False,
         augment=False,
         verbose=False,
         model=None,
         dataloader=None,
         save_dir=Path(''),  # for saving images
         save_txt=False,  # for auto-labelling
         save_hybrid=False,  # for hybrid auto-labelling
         save_conf=False,  # save auto-label confidences
         plots=True,
         wandb_logger=None,
         compute_loss=None,
         half_precision=True,
         trace=False,
         is_coco=False,
         v5_metric=False):
    # Initialize/load model and set device
    training = model is not None
    if training:  # called by train.py
        device = next(model.parameters()).device  # get model device

    else:  # called directly
        set_logging()
        device = select_device(opt.device, batch_size=batch_size)

        # 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

        # Load model
        model = attempt_load(weights, map_location=device)  # load FP32 model
        gs = max(int(model.stride.max()), 32)  # grid size (max stride)
        imgsz = check_img_size(imgsz, s=gs)  # check img_size
        
        if trace:
            model = TracedModel(model, device, imgsz)

    # Half
    half = device.type != 'cpu' and half_precision  # half precision only supported on CUDA
    if half:
        model.half()

    # Configure
    model.eval()
    if isinstance(data, str):
        is_coco = data.endswith('coco.yaml')
        with open(data) as f:
            data = yaml.load(f, Loader=yaml.SafeLoader)
    check_dataset(data)  # check
    nc = 1 if single_cls else int(data['nc'])  # number of classes
    iouv = torch.linspace(0.5, 0.95, 10).to(device)  # iou vector for mAP@0.5:0.95
    niou = iouv.numel()

    # Logging
    log_imgs = 0
    if wandb_logger and wandb_logger.wandb:
        log_imgs = min(wandb_logger.log_imgs, 100)
    # Dataloader
    if not training:
        if device.type != 'cpu':
            model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
        task = opt.task if opt.task in ('train', 'val', 'test') else 'val'  # path to train/val/test images
        dataloader = create_dataloader(data[task], imgsz, batch_size, gs, opt, pad=0.5, rect=True,
                                       prefix=colorstr(f'{task}: '))[0]

    if v5_metric:
        print("Testing with YOLOv5 AP metric...")
    
    seen = 0
    confusion_matrix = ConfusionMatrix(nc=nc)
    names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)}
    coco91class = coco80_to_coco91_class()
    s = ('%20s' + '%12s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', 'mAP@.5', 'mAP@.5:.95')
    p, r, f1, mp, mr, map50, map, t0, t1 = 0., 0., 0., 0., 0., 0., 0., 0., 0.
    loss = torch.zeros(3, device=device)
    jdict, stats, ap, ap_class, wandb_images = [], [], [], [], []
    for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
        img = img.to(device, non_blocking=True)
        img = img.half() if half else img.float()  # uint8 to fp16/32
        img /= 255.0  # 0 - 255 to 0.0 - 1.0
        targets = targets.to(device)
        nb, _, height, width = img.shape  # batch size, channels, height, width

        with torch.no_grad():
            # Run model
            t = time_synchronized()
            out, train_out = model(img, augment=augment)  # inference and training outputs
            t0 += time_synchronized() - t

            # Compute loss
            if compute_loss:
                loss += compute_loss([x.float() for x in train_out], targets)[1][:3]  # box, obj, cls

            # Run NMS
            targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device)  # to pixels
            lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
            t = time_synchronized()
            out = non_max_suppression(out, conf_thres=conf_thres, iou_thres=iou_thres, labels=lb, multi_label=True)
            t1 += time_synchronized() - t

        # Statistics per image
        for si, pred in enumerate(out):
            labels = targets[targets[:, 0] == si, 1:]
            nl = len(labels)
            tcls = labels[:, 0].tolist() if nl else []  # target class
            path = Path(paths[si])
            seen += 1

            if len(pred) == 0:
                if nl:
                    stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls))
                continue

            # Predictions
            predn = pred.clone()
            scale_coords(img[si].shape[1:], predn[:, :4], shapes[si][0], shapes[si][1])  # native-space pred

            # Append to text file
            if save_txt:
                gn = torch.tensor(shapes[si][0])[[1, 0, 1, 0]]  # normalization gain whwh
                for *xyxy, conf, cls in predn.tolist():
                    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(save_dir / 'labels' / (path.stem + '.txt'), 'a') as f:
                        f.write(('%g ' * len(line)).rstrip() % line + '\n')

            # W&B logging - Media Panel Plots
            if len(wandb_images) < log_imgs and wandb_logger.current_epoch > 0:  # Check for test operation
                if wandb_logger.current_epoch % wandb_logger.bbox_interval == 0:
                    box_data = [{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
                                 "class_id": int(cls),
                                 "box_caption": "%s %.3f" % (names[cls], conf),
                                 "scores": {"class_score": conf},
                                 "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()]
                    boxes = {"predictions": {"box_data": box_data, "class_labels": names}}  # inference-space
                    wandb_images.append(wandb_logger.wandb.Image(img[si], boxes=boxes, caption=path.name))
            wandb_logger.log_training_progress(predn, path, names) if wandb_logger and wandb_logger.wandb_run else None

            # Append to pycocotools JSON dictionary
            if save_json:
                # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
                image_id = int(path.stem) if path.stem.isnumeric() else path.stem
                box = xyxy2xywh(predn[:, :4])  # xywh
                box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
                for p, b in zip(pred.tolist(), box.tolist()):
                    jdict.append({'image_id': image_id,
                                  'category_id': coco91class[int(p[5])] if is_coco else int(p[5]),
                                  'bbox': [round(x, 3) for x in b],
                                  'score': round(p[4], 5)})

            # Assign all predictions as incorrect
            correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device)
            if nl:
                """
                predn:  {x1, y1, x2, y2, conf, cls}
                    tensor([[319.32043,  43.82351, 426.80283, 110.60916,   0.90186,  17.00000],
                    [ 84.76453,  36.17760, 120.57571,  67.90933,   0.65967,  19.00000],
                    [3.41989,  57.74736,  94.48680, 110.90230,   0.51758,   8.00000]], device='cuda:0')
                labels: {cls, x, y, w, h}
                    tensor([[ 19.00000, 148.48001,  75.52252,  44.80000,  46.05405],
                    [ 17.00000, 492.80002, 106.86487, 139.51996,  88.27026],
                    [ 17.00000,  79.36000, 124.77477, 124.16000,  52.45045]], device='cuda:0')
                tobx: {x1, y1, x2, y2}
                    tensor([[ 86.04846,  34.00000, 121.06818,  70.00000],
                    [318.17920,  42.00001, 427.24057, 111.00000],
                    [1.00056,  70.00000,  98.05522, 111.00000]], device='cuda:0')
                tcls_tensor: {cls}
                    tensor([19., 17., 17.], device='cuda:0')
                """
                detected = []  # target indices
                tcls_tensor = labels[:, 0]

                # target boxes
                tbox = xywh2xyxy(labels[:, 1:5])
                scale_coords(img[si].shape[1:], tbox, shapes[si][0], shapes[si][1])  # native-space labels
                if plots:
                    confusion_matrix.process_batch(predn, torch.cat((labels[:, 0:1], tbox), 1))

                # Per target class 
                for cls in torch.unique(tcls_tensor):
                    ti = (cls == tcls_tensor).nonzero(as_tuple=False).view(-1)  # prediction indices
                    pi = (cls == pred[:, 5]).nonzero(as_tuple=False).view(-1)  # target indices

                    # Search for detections
                    if pi.shape[0]:
                        # Prediction to target ious
                        ious, i = box_iou(predn[pi, :4], tbox[ti]).max(1)  # best ious, indices

                        # Append detections
                        detected_set = set()
                        for j in (ious > iouv[0]).nonzero(as_tuple=False):
                            d = ti[i[j]]  # detected target
                            if d.item() not in detected_set:
                                detected_set.add(d.item())
                                detected.append(d)
                                correct[pi[j]] = ious[j] > iouv  # iou_thres is 1xn
                                if len(detected) == nl:  # all targets already located in image
                                    break

            # Append statistics (correct, conf, pcls, tcls)
            stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls))

        # Plot images
        if plots and batch_i < 3:
            f = save_dir / f'test_batch{batch_i}_labels.jpg'  # labels
            Thread(target=plot_images, args=(img, targets, paths, f, names), daemon=True).start()
            f = save_dir / f'test_batch{batch_i}_pred.jpg'  # predictions
            Thread(target=plot_images, args=(img, output_to_target(out), paths, f, names), daemon=True).start()
            
    confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
    # Compute statistics
    stats = [np.concatenate(x, 0) for x in zip(*stats)]  # to numpy
    if len(stats) and stats[0].any():
        p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, v5_metric=v5_metric, save_dir=save_dir, names=names)
        ap50, ap = ap[:, 0], ap.mean(1)  # AP@0.5, AP@0.5:0.95
        mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
        nt = np.bincount(stats[3].astype(np.int64), minlength=nc)  # number of targets per class
    else:
        nt = torch.zeros(1)

    # Print results
    pf = '%20s' + '%12i' * 2 + '%12.3g' * 4  # print format
    print(pf % ('all', seen, nt.sum(), mp, mr, map50, map))

    # Print results per class
    if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats):
        for i, c in enumerate(ap_class):
            print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))

    # Print speeds
    t = tuple(x / seen * 1E3 for x in (t0, t1, t0 + t1)) + (imgsz, imgsz, batch_size)  # tuple
    if not training:
        print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t)

    # Plots
    if plots:
        confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
        if wandb_logger and wandb_logger.wandb:
            val_batches = [wandb_logger.wandb.Image(str(f), caption=f.name) for f in sorted(save_dir.glob('test*.jpg'))]
            wandb_logger.log({"Validation": val_batches})
    if wandb_images:
        wandb_logger.log({"Bounding Box Debugger/Images": wandb_images})

    # Save JSON
    if save_json and len(jdict):
        w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else ''  # weights
        anno_json = './coco/annotations/instances_val2017.json'  # annotations json
        pred_json = str(save_dir / f"{w}_predictions.json")  # predictions json
        print('\nEvaluating pycocotools mAP... saving %s...' % pred_json)
        with open(pred_json, 'w') as f:
            json.dump(jdict, f)

        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
            from pycocotools.coco import COCO
            from pycocotools.cocoeval import COCOeval

            anno = COCO(anno_json)  # init annotations api
            pred = anno.loadRes(pred_json)  # init predictions api
            eval = COCOeval(anno, pred, 'bbox')
            if is_coco:
                eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files]  # image IDs to evaluate
            eval.evaluate()
            eval.accumulate()
            eval.summarize()
            map, map50 = eval.stats[:2]  # update results (mAP@0.5:0.95, mAP@0.5)
        except Exception as e:
            print(f'pycocotools unable to run: {e}')

    # Return results
    model.float()  # for training
    if not training:
        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}")
    maps = np.zeros(nc) + map
    for i, c in enumerate(ap_class):
        maps[c] = ap[i]
    return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t


if __name__ == '__main__':
    parser = argparse.ArgumentParser(prog='test.py')
    parser.add_argument('--weights', nargs='+', type=str, default='runs/train/exp10/weights/best.pt', help='model.pt path(s)')
    parser.add_argument('--data', type=str, default='data/voc.yaml', help='*.data path')
    parser.add_argument('--batch-size', type=int, default=1, help='size of each image batch')
    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.5, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.65, help='IOU threshold for NMS')
    parser.add_argument('--task', default='test', help='train, val, test, speed or study')
    parser.add_argument('--device', default='0', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--verbose', action='store_true', help='report mAP by class')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--save-hybrid', action='store_true', help='save label+prediction hybrid results to *.txt')
    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
    parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file')
    parser.add_argument('--project', default='runs/test', help='save to project/name')
    parser.add_argument('--name', default='yolov7_640_val', help='save to project/name')
    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--no-trace', action='store_true', help='don`t trace model')
    parser.add_argument('--v5-metric', action='store_true', help='assume maximum recall as 1.0 in AP calculation')
    opt = parser.parse_args()
    opt.save_json |= opt.data.endswith('coco.yaml')
    opt.data = check_file(opt.data)  # check file
    print(opt)
    #check_requirements()

    if opt.task in ('train', 'val', 'test'):  # run normally
        test(opt.data,
             opt.weights,
             opt.batch_size,
             opt.img_size,
             opt.conf_thres,
             opt.iou_thres,
             opt.save_json,
             opt.single_cls,
             opt.augment,
             opt.verbose,
             save_txt=opt.save_txt | opt.save_hybrid,
             save_hybrid=opt.save_hybrid,
             save_conf=opt.save_conf,
             trace=not opt.no_trace,
             v5_metric=opt.v5_metric
             )

    elif opt.task == 'speed':  # speed benchmarks
        for w in opt.weights:
            test(opt.data, w, opt.batch_size, opt.img_size, 0.25, 0.45, save_json=False, plots=False, v5_metric=opt.v5_metric)

    elif opt.task == 'study':  # run over a range of settings and save/plot
        # python test.py --task study --data coco.yaml --iou 0.65 --weights yolov7.pt
        x = list(range(256, 1536 + 128, 128))  # x axis (image sizes)
        for w in opt.weights:
            f = f'study_{Path(opt.data).stem}_{Path(w).stem}.txt'  # filename to save to
            y = []  # y axis
            for i in x:  # img-size
                print(f'\nRunning {f} point {i}...')
                r, _, t = test(opt.data, w, opt.batch_size, i, opt.conf_thres, opt.iou_thres, opt.save_json,
                               plots=False, v5_metric=opt.v5_metric)
                y.append(r + t)  # results and times
            np.savetxt(f, y, fmt='%10.4g')  # save
        os.system('zip -r study.zip study_*.txt')
        plot_study_txt(x=x)  # plot

混淆矩阵代码：

class ConfusionMatrix:
    # Updated version of https://github.com/kaanakan/object_detection_confusion_matrix
    def __init__(self, nc, conf=0.25, iou_thres=0.45):
        self.matrix = np.zeros((nc + 1, nc + 1))
        self.nc = nc  # number of classes
        self.conf = conf
        self.iou_thres = iou_thres

    def process_batch(self, detections, labels):
        """
        Return intersection-over-union (Jaccard index) of boxes.
        Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
        Arguments:
            detections (Array[N, 6]), x1, y1, x2, y2, conf, class
            labels (Array[M, 5]), class, x1, y1, x2, y2
        Returns:
            None, updates confusion matrix accordingly
        """
        detections = detections[detections[:, 4] > self.conf] 
        gt_classes = labels[:, 0].int()
        detection_classes = detections[:, 5].int()
        iou = general.box_iou(labels[:, 1:], detections[:, :4]) # 第i个gt框和第j个pred的iou
        # iou = tensor([[0.00000, 0.84184, 0.01724],
        # [0.95389, 0.00000, 0.00000],
        # [0.00000, 0.00000, 0.73107]], device='cuda:0')
        # x[0]: gt_index  x[1]:  pred_index     x合起来看就是第x[0]个gt框和第x[1]个pred的iou符合条件
        """
        x : (tensor([0, 1, 2], device='cuda:0'), tensor([1, 0, 2], device='cuda:0'))
        """
        x = torch.where(iou > self.iou_thres)   # 根据IoU匹配结果,返回满足条件的索引 x(dim0), (dim1)
        if x[0].shape[0]:                       # x[0]：存在为True的索引(gt索引), x[1]当前所有下pred的索引(dt索引)
            """
            matches:
                array([[          0,           1,     0.84184],
                [          1,           0,     0.95389],
                [          2,           2,     0.73107]], dtype=float32)
            """
            matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()  # 
            if x[0].shape[0] > 1:
                """
                matches    array([[          1,           0,     0.95389],
                [          0,           1,     0.84184],
                [          2,           2,     0.73107]], dtype=float32)
                """
                matches = matches[matches[:, 2].argsort()[::-1]]  # 按照iou值高低排序 高 ——> 低
                """
                np.unique(matches[:, 1], return_index=True)[1]:
                    (array([          0,           1,           2], dtype=float32), array([0, 1, 2], dtype=int64))
                matches:
                    array([[          1,           0,     0.95389],
                            [          0,           1,     0.84184],
                            [          2,           2,     0.73107]], dtype=float32)
                取第二列中各个框首次出现(不同预测的框)的行  ********(即每一种预测的框中iou最大的那个)********
                """
                matches = matches[np.unique(matches[:, 1], return_index=True)[1]] # 去重(列维度) 若一个dt匹配多个gt,保留IoU最高的gt匹配结果
                """
                matches 再按第三列iou从大到小重排序
                """
                matches = matches[matches[:, 2].argsort()[::-1]] #  按照置信度高低排序 高 ——> 低
                """
                取第一列中各个框首次出现(不同gt的框)的行   ********(即每一种gt框中iou最大的那个)********
                """
                """
                matches:
                    array([[          0,           1,     0.84184],
                    [          1,           0,     0.95389],
                    [          2,           2,     0.73107]], dtype=float32)
                """
                matches = matches[np.unique(matches[:, 0], return_index=True)[1]] # 去重(行维度) 若一个gt匹配多个dt,保留IoU最高的dt匹配结果
                """
                    经过这样的处理 最终得到每一种预测框与所有gt框中iou最大的那个(在大于阈值的前提下)
                    预测框唯一  gt框也唯一  这样得到的matches对应的Pred都是正样本Positive
                """
        else:
            matches = np.zeros((0, 3))

        n = matches.shape[0] > 0 # 是否存在和gt匹配成功的dt
        m0, m1, _ = matches.transpose().astype(np.int16)  # m0:gt索引 m1:dt索引
        for i, gc in enumerate(gt_classes):               # 实际的结果
            j = m0 == i                                   # 预测为该目标的预测结果序号
            """
                如果sum(j)=1 说明gt[i]这个真实框被某个预测框检测到了
                但是detection_classes[m1[j]]并不一定等于gc, 所以此时可能是TP或者是FP
                m1[j]: gt框index=i时, 满足条件的pred框index  detection_classes[m1[j]]: pred_class_index
                gc: gt_class_index    matrix[pred_class_index, gt_class_index] += 1
            """
            if n and sum(j) == 1:                           
                self.matrix[gc, detection_classes[m1[j]]] += 1  #  预测为目标, 且实际为目标
            else:                                         # 该实际结果预测失败
                self.matrix[self.nc, gc] += 1             # 预测为背景,但实际为目标

        if n:                                             # 对预测结果处理
            for i, dc in enumerate(detection_classes):    
                if not any(m1 == i):                      # 若该预测结果没有和实际结果匹配
                    self.matrix[dc, self.nc] += 1         # 预测为目标,但实际为背景

    def matrix(self):
        return self.matrix

    def plot(self, save_dir='', names=()):
        try:
            import seaborn as sn
            print("self.matrix:------------>", self.matrix.shape)
            array = self.matrix / (self.matrix.sum(0).reshape(1, self.nc + 1) + 1E-6)  # normalize
            array[array < 0.005] = np.nan  # don't annotate (would appear as 0.00)

            fig = plt.figure(figsize=(12, 9), tight_layout=True)
            sn.set(font_scale=1.0 if self.nc < 50 else 0.8)  # for label size
            labels = (0 < len(names) < 99) and len(names) == self.nc  # apply names to ticklabels
            sn.heatmap(array, annot=self.nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True,
                       xticklabels=names + ['background FP'] if labels else "auto",
                       yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1))
            fig.axes[0].set_xlabel('True')
            fig.axes[0].set_ylabel('Predicted')
            fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250)
        except Exception as e:
            pass

    def print(self):
        for i in range(self.nc + 1):
            print(' '.join(map(str, self.matrix[i])))

数据集划分代码：

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
f rom os.path import join
import random
from shutil import copyfile
 
classes = ["aeroplane",
"bicycle",
"bird",
"boat",
"bottle",
"bus",
"car",
"cat",
"chair",
"cow",
"diningtable",
"dog",
"horse",
"motorbike",
"person",
"pottedplant",
"sheep",
"sofa",
"train",
"tvmonitor"]

TRAIN_RATIO = 70
 
 
def clear_hidden_files(path):
    dir_list = os.listdir(path)
    for i in dir_list:
        abspath = os.path.join(os.path.abspath(path), i)
        if os.path.isfile(abspath):
            if i.startswith("._"):
                os.remove(abspath)
        else:
            clear_hidden_files(abspath)
 
 
def convert(size, box):
    dw = 1. / size[0]
    dh = 1. / size[1]
    x = (box[0] + box[1]) / 2.0
    y = (box[2] + box[3]) / 2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)
 
 
def convert_annotation(image_id):
    in_file = open('VOCdevkit/VOC2007/Annotations/%s.xml' % image_id)
    out_file = open('VOCdevkit/VOC2007/YOLOLabels/%s.txt' % image_id, 'w')
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)
 
    for obj in root.iter('object'):
        # difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
             float(xmlbox.find('ymax').text))
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
    in_file.close()
    out_file.close()
 
 
wd = os.getcwd()
wd = os.getcwd()
data_base_dir = os.path.join(wd, "VOCdevkit/")
if not os.path.isdir(data_base_dir):
    os.mkdir(data_base_dir)
work_sapce_dir = os.path.join(data_base_dir, "VOC2007/")
if not os.path.isdir(work_sapce_dir):
    os.mkdir(work_sapce_dir)
annotation_dir = os.path.join(work_sapce_dir, "Annotations/")
if not os.path.isdir(annotation_dir):
    os.mkdir(annotation_dir)
clear_hidden_files(annotation_dir)
image_dir = os.path.join(work_sapce_dir, "JPEGImages/")
if not os.path.isdir(image_dir):
    os.mkdir(image_dir)
clear_hidden_files(image_dir)
yolo_labels_dir = os.path.join(work_sapce_dir, "YOLOLabels/")
if not os.path.isdir(yolo_labels_dir):
    os.mkdir(yolo_labels_dir)
clear_hidden_files(yolo_labels_dir)
yolov5_images_dir = os.path.join(data_base_dir, "images/")
if not os.path.isdir(yolov5_images_dir):
    os.mkdir(yolov5_images_dir)
clear_hidden_files(yolov5_images_dir)
yolov5_labels_dir = os.path.join(data_base_dir, "labels/")
if not os.path.isdir(yolov5_labels_dir):
    os.mkdir(yolov5_labels_dir)
clear_hidden_files(yolov5_labels_dir)
yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/")
if not os.path.isdir(yolov5_images_train_dir):
    os.mkdir(yolov5_images_train_dir)
clear_hidden_files(yolov5_images_train_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, "val/")
if not os.path.isdir(yolov5_images_test_dir):
    os.mkdir(yolov5_images_test_dir)
clear_hidden_files(yolov5_images_test_dir)
yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/")
if not os.path.isdir(yolov5_labels_train_dir):
    os.mkdir(yolov5_labels_train_dir)
clear_hidden_files(yolov5_labels_train_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "val/")
if not os.path.isdir(yolov5_labels_test_dir):
    os.mkdir(yolov5_labels_test_dir)
clear_hidden_files(yolov5_labels_test_dir)
 
train_file = open(os.path.join(wd, "yolov7_train.txt"), 'w')
test_file = open(os.path.join(wd, "yolov7_val.txt"), 'w')
train_file.close()
test_file.close()
train_file = open(os.path.join(wd, "yolov7_train.txt"), 'a')
test_file = open(os.path.join(wd, "yolov7_val.txt"), 'a')
list_imgs = os.listdir(image_dir)  # list image files
prob = random.randint(1, 100)
print("Probability: %d" % prob)
for i in range(0, len(list_imgs)):
    path = os.path.join(image_dir, list_imgs[i])
    if os.path.isfile(path):
        image_path = image_dir + list_imgs[i]
        voc_path = list_imgs[i]
        (nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path))
        (voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path))
        annotation_name = nameWithoutExtention + '.xml'
        annotation_path = os.path.join(annotation_dir, annotation_name)
        label_name = nameWithoutExtention + '.txt'
        label_path = os.path.join(yolo_labels_dir, label_name)
    prob = random.randint(1, 100)
    print("Probability: %d" % prob)
    if (prob < TRAIN_RATIO):  # train dataset
        if os.path.exists(annotation_path):
            train_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention)  # convert label
            copyfile(image_path, yolov5_images_train_dir + voc_path)
            copyfile(label_path, yolov5_labels_train_dir + label_name)
    else:  # test dataset
        if os.path.exists(annotation_path):
            test_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention)  # convert label
            copyfile(image_path, yolov5_images_test_dir + voc_path)
            copyfile(label_path, yolov5_labels_test_dir + label_name)
train_file.close()
test_file.close()

yolov7 ap精度

def ap_per_class(tp, conf, pred_cls, target_cls, v5_metric=False, plot=False, save_dir='.', names=()):
    """ Compute the average precision, given the recall and precision curves.
    Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
    # Arguments
        tp:  True positives (nparray, nx1 or nx10).
        conf:  Objectness value from 0-1 (nparray).
        pred_cls:  Predicted object classes (nparray).
        target_cls:  True object classes (nparray).
        plot:  Plot precision-recall curve at mAP@0.5
        save_dir:  Plot save directory
    # Returns
        The average precision as computed in py-faster-rcnn.
    """

    # Sort by objectness
    # 计算mAP 需要将tp按照conf降序排列
    # Sort by objectness  按conf从大到小排序 返回数据对应的索引
    i = np.argsort(-conf)
    tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]

    # Find unique classes
    unique_classes = np.unique(target_cls)
    nc = unique_classes.shape[0]  # number of classes, number of detections

    # Create Precision-Recall curve and compute AP for each class
    px, py = np.linspace(0, 1, 1000), []  # for plotting
    ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000))
    for ci, c in enumerate(unique_classes):
        i = pred_cls == c
        n_l = (target_cls == c).sum()  # number of labels
        n_p = i.sum()  # number of predictions

        if n_p == 0 or n_l == 0:
            continue
        else:
            # Accumulate FPs and TPs
            fpc = (1 - tp[i]).cumsum(0)
            tpc = tp[i].cumsum(0)

            # Recall
            recall = tpc / (n_l + 1e-16)  # recall curve
            r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0)  # negative x, xp because xp decreases

            # Precision
            precision = tpc / (tpc + fpc)  # precision curve
            p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1)  # p at pr_score

            # AP from recall-precision curve
            for j in range(tp.shape[1]):
                ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j], v5_metric=v5_metric)
                if plot and j == 0:
                    py.append(np.interp(px, mrec, mpre))  # precision at mAP@0.5

    # Compute F1 (harmonic mean of precision and recall)
    f1 = 2 * p * r / (p + r + 1e-16)
    if plot:
        plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names)
        plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1')
        plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision')
        plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall')

    i = f1.mean(0).argmax()  # max F1 index
    return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32')

detected.py

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, 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, TracedModel


def detect(save_img=False):
    source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, not opt.no_trace
    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 trace:
        model = TracedModel(model, device, opt.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
    old_img_w = old_img_h = imgsz
    old_img_b = 1

    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)

        # Warmup
        if device.type != 'cpu' and (old_img_b != img.shape[0] or old_img_h != img.shape[2] or old_img_w != img.shape[3]):
            old_img_b = img.shape[0]
            old_img_h = img.shape[2]
            old_img_w = img.shape[3]
            for i in range(3):
                model(img, augment=opt.augment)[0]

        # Inference
        t1 = time_synchronized()
        with torch.no_grad():   # Calculating gradients would cause a GPU memory leak
            pred = model(img, augment=opt.augment)[0]
        t2 = time_synchronized()

        # Apply NMS
        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
        t3 = time_synchronized()

        # Apply Classifier
        if classify:
            pred = apply_classifier(pred, modelc, img, im0s)

        # Process detections
        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:
                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
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
            """
            det  : tensor([[ -0.87500, 171.75000, 261.50000, 352.75000],
                        [361.75000, 187.37500, 494.25000, 300.50000],
                        [203.37500, 173.25000, 348.50000, 312.75000],
                        [304.50000, 184.50000, 378.50000, 282.75000],
                        [ -0.93750, 166.37500, 130.75000, 309.50000]], device='cuda:0')   
            """
            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):
                    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')

                    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=1)

            # Print time (inference + NMS)
            print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS')

            # Stream results
            if view_img:
                cv2.imshow(str(p), im0)
                cv2.waitKey(1)  # 1 millisecond

            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'image':
                    cv2.imwrite(save_path, im0)
                    print(f" The image with the result is saved in: {save_path}")
                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)

    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='runs/train/exp10/weights/best.pt', help='model.pt path(s)')
    parser.add_argument('--source', type=str, default='inference/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')
    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('--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')
    parser.add_argument('--no-trace', action='store_true', help='don`t trace model')
    opt = parser.parse_args()
    print(opt)
    #check_requirements(exclude=('pycocotools', 'thop'))

    with torch.no_grad():
        if opt.update:  # update all models (to fix SourceChangeWarning)
            for opt.weights in ['yolov7.pt']:
                detect()
                strip_optimizer(opt.weights)
        else:
            detect()