yolov8 训练voc数据集

yolov8训练

from ultralytics import YOLO

# 加载模型
# model = YOLO('yolov8n.yaml')  # 从YAML构建新模型
# model = YOLO('yolov8n.pt')    # 加载预训练模型（推荐用于训练）
model = YOLO('yolov8n.yaml').load('yolov8n.pt')  # 从YAML构建并转移权重

# 训练模型
results = model.train(data='VOC.yaml', epochs=100, imgsz=640)

VOC.yaml

# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: D:/Projects/yolo-v7/voc
train: # train images (relative to 'path')  16551 images
  - images/train2007
  - images/val2007
val: # val images (relative to 'path')  4952 images
  - images/test2007
test: # test images (optional)
  - images/test2007

# Classes
names:
  0: aeroplane
  1: bicycle
  2: bird
  3: boat
  4: bottle
  5: bus
  6: car
  7: cat
  8: chair
  9: cow
  10: diningtable
  11: dog
  12: horse
  13: motorbike
  14: person
  15: pottedplant
  16: sheep
  17: sofa
  18: train
  19: tvmonitor

yolov8n.yaml

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80  # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  # s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  # m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  # l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  # x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs

# YOLOv8.0n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
  - [-1, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]]  # 9

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 12

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)

  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)

yolov8 混淆矩阵

class ConfusionMatrix:
    """
    A class for calculating and updating a confusion matrix for object detection and classification tasks.

    Attributes:
        task (str): The type of task, either 'detect' or 'classify'.
        matrix (np.array): The confusion matrix, with dimensions depending on the task.
        nc (int): The number of classes.
        conf (float): The confidence threshold for detections.
        iou_thres (float): The Intersection over Union threshold.
    """

    def __init__(self, nc, conf=0.25, iou_thres=0.45, task='detect'):
        """Initialize attributes for the YOLO model."""
        self.task = task
        self.matrix = np.zeros((nc + 1, nc + 1)) if self.task == 'detect' else np.zeros((nc, nc))
        self.nc = nc  # number of classes
        self.conf = 0.25 if conf in (None, 0.001) else conf  # apply 0.25 if default val conf is passed
        self.iou_thres = iou_thres

    def process_cls_preds(self, preds, targets):
        """
        Update confusion matrix for classification task.

        Args:
            preds (Array[N, min(nc,5)]): Predicted class labels.
            targets (Array[N, 1]): Ground truth class labels.
        """
        preds, targets = torch.cat(preds)[:, 0], torch.cat(targets)
        for p, t in zip(preds.cpu().numpy(), targets.cpu().numpy()):
            self.matrix[p][t] += 1

    def process_batch(self, detections, labels):
        """
        Update confusion matrix for object detection task.

        Args:
            detections (Array[N, 6]): Detected bounding boxes and their associated information.
                                      Each row should contain (x1, y1, x2, y2, conf, class).
            labels (Array[M, 5]): Ground truth bounding boxes and their associated class labels.
                                  Each row should contain (class, x1, y1, x2, y2).
        """
        if labels.size(0) == 0:  # Check if labels is empty
            if detections is not None:
                detections = detections[detections[:, 4] > self.conf]
                detection_classes = detections[:, 5].int()
                for dc in detection_classes:
                    self.matrix[dc, self.nc] += 1  # false positives
            return
        if detections is None:
            gt_classes = labels.int()
            for gc in gt_classes:
                self.matrix[self.nc, gc] += 1  # background FN
            return

        detections = detections[detections[:, 4] > self.conf]
        gt_classes = labels[:, 0].int()
        detection_classes = detections[:, 5].int()
        iou = box_iou(labels[:, 1:], detections[:, :4])

        x = torch.where(iou > self.iou_thres)
        if x[0].shape[0]:
            matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()
            if x[0].shape[0] > 1:
                matches = matches[matches[:, 2].argsort()[::-1]]
                matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
                matches = matches[matches[:, 2].argsort()[::-1]]
                matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
        else:
            matches = np.zeros((0, 3))

        n = matches.shape[0] > 0
        m0, m1, _ = matches.transpose().astype(int)
        for i, gc in enumerate(gt_classes):
            j = m0 == i
            if n and sum(j) == 1:
                self.matrix[detection_classes[m1[j]], gc] += 1  # correct
            else:
                self.matrix[self.nc, gc] += 1  # true background

        if n:
            for i, dc in enumerate(detection_classes):
                if not any(m1 == i):
                    self.matrix[dc, self.nc] += 1  # predicted background

    def matrix(self):
        """Returns the confusion matrix."""
        return self.matrix

    def tp_fp(self):
        """Returns true positives and false positives."""
        tp = self.matrix.diagonal()  # true positives
        fp = self.matrix.sum(1) - tp  # false positives
        # fn = self.matrix.sum(0) - tp  # false negatives (missed detections)
        return (tp[:-1], fp[:-1]) if self.task == 'detect' else (tp, fp)  # remove background class if task=detect

    @TryExcept('WARNING ⚠️ ConfusionMatrix plot failure')
    @plt_settings()
    def plot(self, normalize=True, save_dir='', names=(), on_plot=None):
        """
        Plot the confusion matrix using seaborn and save it to a file.

        Args:
            normalize (bool): Whether to normalize the confusion matrix.
            save_dir (str): Directory where the plot will be saved.
            names (tuple): Names of classes, used as labels on the plot.
            on_plot (func): An optional callback to pass plots path and data when they are rendered.
        """
        import seaborn as sn

        array = self.matrix / ((self.matrix.sum(0).reshape(1, -1) + 1E-9) if normalize else 1)  # normalize columns
        array[array < 0.005] = np.nan  # don't annotate (would appear as 0.00)

        fig, ax = plt.subplots(1, 1, figsize=(12, 9), tight_layout=True)
        nc, nn = self.nc, len(names)  # number of classes, names
        sn.set(font_scale=1.0 if nc < 50 else 0.8)  # for label size
        labels = (0 < nn < 99) and (nn == nc)  # apply names to ticklabels
        ticklabels = (list(names) + ['background']) if labels else 'auto'
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')  # suppress empty matrix RuntimeWarning: All-NaN slice encountered
            sn.heatmap(array,
                       ax=ax,
                       annot=nc < 30,
                       annot_kws={
                           'size': 8},
                       cmap='Blues',
                       fmt='.2f' if normalize else '.0f',
                       square=True,
                       vmin=0.0,
                       xticklabels=ticklabels,
                       yticklabels=ticklabels).set_facecolor((1, 1, 1))
        title = 'Confusion Matrix' + ' Normalized' * normalize
        ax.set_xlabel('True')
        ax.set_ylabel('Predicted')
        ax.set_title(title)
        plot_fname = Path(save_dir) / f'{title.lower().replace(" ", "_")}.png'
        fig.savefig(plot_fname, dpi=250)
        plt.close(fig)
        if on_plot:
            on_plot(plot_fname)

    def print(self):
        """Print the confusion matrix to the console."""
        for i in range(self.nc + 1):
            LOGGER.info(' '.join(map(str, self.matrix[i])))