Saltar al contenido

Referencia para ultralytics/utils/loss.py

Nota

Este archivo est√° disponible en https://github.com/ultralytics/ ultralytics/blob/main/ ultralytics/utils/loss .py. Si detectas alg√ļn problema, por favor, ayuda a solucionarlo contribuyendo con una Pull Request ūüõ†ÔłŹ. ¬°Gracias ūüôŹ!



ultralytics.utils.loss.VarifocalLoss

Bases: Module

Pérdida varifocal por Zhang et al.

https://arxiv.org/abs/2008.13367.

Código fuente en ultralytics/utils/loss.py
class VarifocalLoss(nn.Module):
    """
    Varifocal loss by Zhang et al.

    https://arxiv.org/abs/2008.13367.
    """

    def __init__(self):
        """Initialize the VarifocalLoss class."""
        super().__init__()

    @staticmethod
    def forward(pred_score, gt_score, label, alpha=0.75, gamma=2.0):
        """Computes varfocal loss."""
        weight = alpha * pred_score.sigmoid().pow(gamma) * (1 - label) + gt_score * label
        with torch.cuda.amp.autocast(enabled=False):
            loss = (
                (F.binary_cross_entropy_with_logits(pred_score.float(), gt_score.float(), reduction="none") * weight)
                .mean(1)
                .sum()
            )
        return loss

__init__()

Inicializa la clase VarifocalLoss.

Código fuente en ultralytics/utils/loss.py
def __init__(self):
    """Initialize the VarifocalLoss class."""
    super().__init__()

forward(pred_score, gt_score, label, alpha=0.75, gamma=2.0) staticmethod

Calcula la pérdida varfocal.

Código fuente en ultralytics/utils/loss.py
@staticmethod
def forward(pred_score, gt_score, label, alpha=0.75, gamma=2.0):
    """Computes varfocal loss."""
    weight = alpha * pred_score.sigmoid().pow(gamma) * (1 - label) + gt_score * label
    with torch.cuda.amp.autocast(enabled=False):
        loss = (
            (F.binary_cross_entropy_with_logits(pred_score.float(), gt_score.float(), reduction="none") * weight)
            .mean(1)
            .sum()
        )
    return loss



ultralytics.utils.loss.FocalLoss

Bases: Module

Envuelve la pérdida focal alrededor de loss_fcn() existente, es decir, criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1,5).

Código fuente en ultralytics/utils/loss.py
class FocalLoss(nn.Module):
    """Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)."""

    def __init__(self):
        """Initializer for FocalLoss class with no parameters."""
        super().__init__()

    @staticmethod
    def forward(pred, label, gamma=1.5, alpha=0.25):
        """Calculates and updates confusion matrix for object detection/classification tasks."""
        loss = F.binary_cross_entropy_with_logits(pred, label, reduction="none")
        # p_t = torch.exp(-loss)
        # loss *= self.alpha * (1.000001 - p_t) ** self.gamma  # non-zero power for gradient stability

        # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
        pred_prob = pred.sigmoid()  # prob from logits
        p_t = label * pred_prob + (1 - label) * (1 - pred_prob)
        modulating_factor = (1.0 - p_t) ** gamma
        loss *= modulating_factor
        if alpha > 0:
            alpha_factor = label * alpha + (1 - label) * (1 - alpha)
            loss *= alpha_factor
        return loss.mean(1).sum()

__init__()

Inicializador de la clase FocalLoss sin par√°metros.

Código fuente en ultralytics/utils/loss.py
def __init__(self):
    """Initializer for FocalLoss class with no parameters."""
    super().__init__()

forward(pred, label, gamma=1.5, alpha=0.25) staticmethod

Calcula y actualiza la matriz de confusión para tareas de detección/clasificación de objetos.

Código fuente en ultralytics/utils/loss.py
@staticmethod
def forward(pred, label, gamma=1.5, alpha=0.25):
    """Calculates and updates confusion matrix for object detection/classification tasks."""
    loss = F.binary_cross_entropy_with_logits(pred, label, reduction="none")
    # p_t = torch.exp(-loss)
    # loss *= self.alpha * (1.000001 - p_t) ** self.gamma  # non-zero power for gradient stability

    # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
    pred_prob = pred.sigmoid()  # prob from logits
    p_t = label * pred_prob + (1 - label) * (1 - pred_prob)
    modulating_factor = (1.0 - p_t) ** gamma
    loss *= modulating_factor
    if alpha > 0:
        alpha_factor = label * alpha + (1 - label) * (1 - alpha)
        loss *= alpha_factor
    return loss.mean(1).sum()



ultralytics.utils.loss.BboxLoss

Bases: Module

Clase de criterio para calcular las pérdidas durante el entrenamiento.

Código fuente en ultralytics/utils/loss.py
class BboxLoss(nn.Module):
    """Criterion class for computing training losses during training."""

    def __init__(self, reg_max, use_dfl=False):
        """Initialize the BboxLoss module with regularization maximum and DFL settings."""
        super().__init__()
        self.reg_max = reg_max
        self.use_dfl = use_dfl

    def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
        """IoU loss."""
        weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1)
        iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, CIoU=True)
        loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum

        # DFL loss
        if self.use_dfl:
            target_ltrb = bbox2dist(anchor_points, target_bboxes, self.reg_max)
            loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight
            loss_dfl = loss_dfl.sum() / target_scores_sum
        else:
            loss_dfl = torch.tensor(0.0).to(pred_dist.device)

        return loss_iou, loss_dfl

    @staticmethod
    def _df_loss(pred_dist, target):
        """
        Return sum of left and right DFL losses.

        Distribution Focal Loss (DFL) proposed in Generalized Focal Loss
        https://ieeexplore.ieee.org/document/9792391
        """
        tl = target.long()  # target left
        tr = tl + 1  # target right
        wl = tr - target  # weight left
        wr = 1 - wl  # weight right
        return (
            F.cross_entropy(pred_dist, tl.view(-1), reduction="none").view(tl.shape) * wl
            + F.cross_entropy(pred_dist, tr.view(-1), reduction="none").view(tl.shape) * wr
        ).mean(-1, keepdim=True)

__init__(reg_max, use_dfl=False)

Inicializa el módulo BboxLoss con los ajustes de regularización máxima y DFL.

Código fuente en ultralytics/utils/loss.py
def __init__(self, reg_max, use_dfl=False):
    """Initialize the BboxLoss module with regularization maximum and DFL settings."""
    super().__init__()
    self.reg_max = reg_max
    self.use_dfl = use_dfl

forward(pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask)

Pérdida de IoU.

Código fuente en ultralytics/utils/loss.py
def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
    """IoU loss."""
    weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1)
    iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, CIoU=True)
    loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum

    # DFL loss
    if self.use_dfl:
        target_ltrb = bbox2dist(anchor_points, target_bboxes, self.reg_max)
        loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight
        loss_dfl = loss_dfl.sum() / target_scores_sum
    else:
        loss_dfl = torch.tensor(0.0).to(pred_dist.device)

    return loss_iou, loss_dfl



ultralytics.utils.loss.RotatedBboxLoss

Bases: BboxLoss

Clase de criterio para calcular las pérdidas durante el entrenamiento.

Código fuente en ultralytics/utils/loss.py
class RotatedBboxLoss(BboxLoss):
    """Criterion class for computing training losses during training."""

    def __init__(self, reg_max, use_dfl=False):
        """Initialize the BboxLoss module with regularization maximum and DFL settings."""
        super().__init__(reg_max, use_dfl)

    def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
        """IoU loss."""
        weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1)
        iou = probiou(pred_bboxes[fg_mask], target_bboxes[fg_mask])
        loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum

        # DFL loss
        if self.use_dfl:
            target_ltrb = bbox2dist(anchor_points, xywh2xyxy(target_bboxes[..., :4]), self.reg_max)
            loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight
            loss_dfl = loss_dfl.sum() / target_scores_sum
        else:
            loss_dfl = torch.tensor(0.0).to(pred_dist.device)

        return loss_iou, loss_dfl

__init__(reg_max, use_dfl=False)

Inicializa el módulo BboxLoss con los ajustes de regularización máxima y DFL.

Código fuente en ultralytics/utils/loss.py
def __init__(self, reg_max, use_dfl=False):
    """Initialize the BboxLoss module with regularization maximum and DFL settings."""
    super().__init__(reg_max, use_dfl)

forward(pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask)

Pérdida de IoU.

Código fuente en ultralytics/utils/loss.py
def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
    """IoU loss."""
    weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1)
    iou = probiou(pred_bboxes[fg_mask], target_bboxes[fg_mask])
    loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum

    # DFL loss
    if self.use_dfl:
        target_ltrb = bbox2dist(anchor_points, xywh2xyxy(target_bboxes[..., :4]), self.reg_max)
        loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight
        loss_dfl = loss_dfl.sum() / target_scores_sum
    else:
        loss_dfl = torch.tensor(0.0).to(pred_dist.device)

    return loss_iou, loss_dfl



ultralytics.utils.loss.KeypointLoss

Bases: Module

Clase de criterio para calcular las pérdidas de entrenamiento.

Código fuente en ultralytics/utils/loss.py
class KeypointLoss(nn.Module):
    """Criterion class for computing training losses."""

    def __init__(self, sigmas) -> None:
        """Initialize the KeypointLoss class."""
        super().__init__()
        self.sigmas = sigmas

    def forward(self, pred_kpts, gt_kpts, kpt_mask, area):
        """Calculates keypoint loss factor and Euclidean distance loss for predicted and actual keypoints."""
        d = (pred_kpts[..., 0] - gt_kpts[..., 0]).pow(2) + (pred_kpts[..., 1] - gt_kpts[..., 1]).pow(2)
        kpt_loss_factor = kpt_mask.shape[1] / (torch.sum(kpt_mask != 0, dim=1) + 1e-9)
        # e = d / (2 * (area * self.sigmas) ** 2 + 1e-9)  # from formula
        e = d / ((2 * self.sigmas).pow(2) * (area + 1e-9) * 2)  # from cocoeval
        return (kpt_loss_factor.view(-1, 1) * ((1 - torch.exp(-e)) * kpt_mask)).mean()

__init__(sigmas)

Inicializa la clase KeypointLoss.

Código fuente en ultralytics/utils/loss.py
def __init__(self, sigmas) -> None:
    """Initialize the KeypointLoss class."""
    super().__init__()
    self.sigmas = sigmas

forward(pred_kpts, gt_kpts, kpt_mask, area)

Calcula el factor de pérdida de puntos clave y la pérdida de distancia euclidiana para los puntos clave previstos y reales.

Código fuente en ultralytics/utils/loss.py
def forward(self, pred_kpts, gt_kpts, kpt_mask, area):
    """Calculates keypoint loss factor and Euclidean distance loss for predicted and actual keypoints."""
    d = (pred_kpts[..., 0] - gt_kpts[..., 0]).pow(2) + (pred_kpts[..., 1] - gt_kpts[..., 1]).pow(2)
    kpt_loss_factor = kpt_mask.shape[1] / (torch.sum(kpt_mask != 0, dim=1) + 1e-9)
    # e = d / (2 * (area * self.sigmas) ** 2 + 1e-9)  # from formula
    e = d / ((2 * self.sigmas).pow(2) * (area + 1e-9) * 2)  # from cocoeval
    return (kpt_loss_factor.view(-1, 1) * ((1 - torch.exp(-e)) * kpt_mask)).mean()



ultralytics.utils.loss.v8DetectionLoss

Clase de criterio para calcular las pérdidas de entrenamiento.

Código fuente en ultralytics/utils/loss.py
class v8DetectionLoss:
    """Criterion class for computing training losses."""

    def __init__(self, model):  # model must be de-paralleled
        """Initializes v8DetectionLoss with the model, defining model-related properties and BCE loss function."""
        device = next(model.parameters()).device  # get model device
        h = model.args  # hyperparameters

        m = model.model[-1]  # Detect() module
        self.bce = nn.BCEWithLogitsLoss(reduction="none")
        self.hyp = h
        self.stride = m.stride  # model strides
        self.nc = m.nc  # number of classes
        self.no = m.nc + m.reg_max * 4
        self.reg_max = m.reg_max
        self.device = device

        self.use_dfl = m.reg_max > 1

        self.assigner = TaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0)
        self.bbox_loss = BboxLoss(m.reg_max - 1, use_dfl=self.use_dfl).to(device)
        self.proj = torch.arange(m.reg_max, dtype=torch.float, device=device)

    def preprocess(self, targets, batch_size, scale_tensor):
        """Preprocesses the target counts and matches with the input batch size to output a tensor."""
        if targets.shape[0] == 0:
            out = torch.zeros(batch_size, 0, 5, device=self.device)
        else:
            i = targets[:, 0]  # image index
            _, counts = i.unique(return_counts=True)
            counts = counts.to(dtype=torch.int32)
            out = torch.zeros(batch_size, counts.max(), 5, device=self.device)
            for j in range(batch_size):
                matches = i == j
                n = matches.sum()
                if n:
                    out[j, :n] = targets[matches, 1:]
            out[..., 1:5] = xywh2xyxy(out[..., 1:5].mul_(scale_tensor))
        return out

    def bbox_decode(self, anchor_points, pred_dist):
        """Decode predicted object bounding box coordinates from anchor points and distribution."""
        if self.use_dfl:
            b, a, c = pred_dist.shape  # batch, anchors, channels
            pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype))
            # pred_dist = pred_dist.view(b, a, c // 4, 4).transpose(2,3).softmax(3).matmul(self.proj.type(pred_dist.dtype))
            # pred_dist = (pred_dist.view(b, a, c // 4, 4).softmax(2) * self.proj.type(pred_dist.dtype).view(1, 1, -1, 1)).sum(2)
        return dist2bbox(pred_dist, anchor_points, xywh=False)

    def __call__(self, preds, batch):
        """Calculate the sum of the loss for box, cls and dfl multiplied by batch size."""
        loss = torch.zeros(3, device=self.device)  # box, cls, dfl
        feats = preds[1] if isinstance(preds, tuple) else preds
        pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
            (self.reg_max * 4, self.nc), 1
        )

        pred_scores = pred_scores.permute(0, 2, 1).contiguous()
        pred_distri = pred_distri.permute(0, 2, 1).contiguous()

        dtype = pred_scores.dtype
        batch_size = pred_scores.shape[0]
        imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0]  # image size (h,w)
        anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)

        # Targets
        targets = torch.cat((batch["batch_idx"].view(-1, 1), batch["cls"].view(-1, 1), batch["bboxes"]), 1)
        targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
        gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
        mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)

        # Pboxes
        pred_bboxes = self.bbox_decode(anchor_points, pred_distri)  # xyxy, (b, h*w, 4)

        _, target_bboxes, target_scores, fg_mask, _ = self.assigner(
            pred_scores.detach().sigmoid(),
            (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
            anchor_points * stride_tensor,
            gt_labels,
            gt_bboxes,
            mask_gt,
        )

        target_scores_sum = max(target_scores.sum(), 1)

        # Cls loss
        # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way
        loss[1] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum  # BCE

        # Bbox loss
        if fg_mask.sum():
            target_bboxes /= stride_tensor
            loss[0], loss[2] = self.bbox_loss(
                pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask
            )

        loss[0] *= self.hyp.box  # box gain
        loss[1] *= self.hyp.cls  # cls gain
        loss[2] *= self.hyp.dfl  # dfl gain

        return loss.sum() * batch_size, loss.detach()  # loss(box, cls, dfl)

__call__(preds, batch)

Calcula la suma de la p√©rdida por caja, cls y dfl multiplicada por el tama√Īo del lote.

Código fuente en ultralytics/utils/loss.py
def __call__(self, preds, batch):
    """Calculate the sum of the loss for box, cls and dfl multiplied by batch size."""
    loss = torch.zeros(3, device=self.device)  # box, cls, dfl
    feats = preds[1] if isinstance(preds, tuple) else preds
    pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
        (self.reg_max * 4, self.nc), 1
    )

    pred_scores = pred_scores.permute(0, 2, 1).contiguous()
    pred_distri = pred_distri.permute(0, 2, 1).contiguous()

    dtype = pred_scores.dtype
    batch_size = pred_scores.shape[0]
    imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0]  # image size (h,w)
    anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)

    # Targets
    targets = torch.cat((batch["batch_idx"].view(-1, 1), batch["cls"].view(-1, 1), batch["bboxes"]), 1)
    targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
    gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
    mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)

    # Pboxes
    pred_bboxes = self.bbox_decode(anchor_points, pred_distri)  # xyxy, (b, h*w, 4)

    _, target_bboxes, target_scores, fg_mask, _ = self.assigner(
        pred_scores.detach().sigmoid(),
        (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
        anchor_points * stride_tensor,
        gt_labels,
        gt_bboxes,
        mask_gt,
    )

    target_scores_sum = max(target_scores.sum(), 1)

    # Cls loss
    # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way
    loss[1] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum  # BCE

    # Bbox loss
    if fg_mask.sum():
        target_bboxes /= stride_tensor
        loss[0], loss[2] = self.bbox_loss(
            pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask
        )

    loss[0] *= self.hyp.box  # box gain
    loss[1] *= self.hyp.cls  # cls gain
    loss[2] *= self.hyp.dfl  # dfl gain

    return loss.sum() * batch_size, loss.detach()  # loss(box, cls, dfl)

__init__(model)

Inicializa v8DetectionLoss con el modelo, definiendo las propiedades relacionadas con el modelo y la función de pérdida BCE.

Código fuente en ultralytics/utils/loss.py
def __init__(self, model):  # model must be de-paralleled
    """Initializes v8DetectionLoss with the model, defining model-related properties and BCE loss function."""
    device = next(model.parameters()).device  # get model device
    h = model.args  # hyperparameters

    m = model.model[-1]  # Detect() module
    self.bce = nn.BCEWithLogitsLoss(reduction="none")
    self.hyp = h
    self.stride = m.stride  # model strides
    self.nc = m.nc  # number of classes
    self.no = m.nc + m.reg_max * 4
    self.reg_max = m.reg_max
    self.device = device

    self.use_dfl = m.reg_max > 1

    self.assigner = TaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0)
    self.bbox_loss = BboxLoss(m.reg_max - 1, use_dfl=self.use_dfl).to(device)
    self.proj = torch.arange(m.reg_max, dtype=torch.float, device=device)

bbox_decode(anchor_points, pred_dist)

Decodifica las coordenadas del cuadro delimitador del objeto predicho a partir de los puntos de anclaje y la distribución.

Código fuente en ultralytics/utils/loss.py
def bbox_decode(self, anchor_points, pred_dist):
    """Decode predicted object bounding box coordinates from anchor points and distribution."""
    if self.use_dfl:
        b, a, c = pred_dist.shape  # batch, anchors, channels
        pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype))
        # pred_dist = pred_dist.view(b, a, c // 4, 4).transpose(2,3).softmax(3).matmul(self.proj.type(pred_dist.dtype))
        # pred_dist = (pred_dist.view(b, a, c // 4, 4).softmax(2) * self.proj.type(pred_dist.dtype).view(1, 1, -1, 1)).sum(2)
    return dist2bbox(pred_dist, anchor_points, xywh=False)

preprocess(targets, batch_size, scale_tensor)

Preprocesa los recuentos objetivo y los compara con el tama√Īo del lote de entrada para obtener una salida tensor.

Código fuente en ultralytics/utils/loss.py
def preprocess(self, targets, batch_size, scale_tensor):
    """Preprocesses the target counts and matches with the input batch size to output a tensor."""
    if targets.shape[0] == 0:
        out = torch.zeros(batch_size, 0, 5, device=self.device)
    else:
        i = targets[:, 0]  # image index
        _, counts = i.unique(return_counts=True)
        counts = counts.to(dtype=torch.int32)
        out = torch.zeros(batch_size, counts.max(), 5, device=self.device)
        for j in range(batch_size):
            matches = i == j
            n = matches.sum()
            if n:
                out[j, :n] = targets[matches, 1:]
        out[..., 1:5] = xywh2xyxy(out[..., 1:5].mul_(scale_tensor))
    return out



ultralytics.utils.loss.v8SegmentationLoss

Bases: v8DetectionLoss

Clase de criterio para calcular las pérdidas de entrenamiento.

Código fuente en ultralytics/utils/loss.py
class v8SegmentationLoss(v8DetectionLoss):
    """Criterion class for computing training losses."""

    def __init__(self, model):  # model must be de-paralleled
        """Initializes the v8SegmentationLoss class, taking a de-paralleled model as argument."""
        super().__init__(model)
        self.overlap = model.args.overlap_mask

    def __call__(self, preds, batch):
        """Calculate and return the loss for the YOLO model."""
        loss = torch.zeros(4, device=self.device)  # box, cls, dfl
        feats, pred_masks, proto = preds if len(preds) == 3 else preds[1]
        batch_size, _, mask_h, mask_w = proto.shape  # batch size, number of masks, mask height, mask width
        pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
            (self.reg_max * 4, self.nc), 1
        )

        # B, grids, ..
        pred_scores = pred_scores.permute(0, 2, 1).contiguous()
        pred_distri = pred_distri.permute(0, 2, 1).contiguous()
        pred_masks = pred_masks.permute(0, 2, 1).contiguous()

        dtype = pred_scores.dtype
        imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0]  # image size (h,w)
        anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)

        # Targets
        try:
            batch_idx = batch["batch_idx"].view(-1, 1)
            targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1)
            targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
            gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
            mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
        except RuntimeError as e:
            raise TypeError(
                "ERROR ‚ĚĆ segment dataset incorrectly formatted or not a segment dataset.\n"
                "This error can occur when incorrectly training a 'segment' model on a 'detect' dataset, "
                "i.e. 'yolo train model=yolov8n-seg.pt data=coco8.yaml'.\nVerify your dataset is a "
                "correctly formatted 'segment' dataset using 'data=coco8-seg.yaml' "
                "as an example.\nSee https://docs.ultralytics.com/datasets/segment/ for help."
            ) from e

        # Pboxes
        pred_bboxes = self.bbox_decode(anchor_points, pred_distri)  # xyxy, (b, h*w, 4)

        _, target_bboxes, target_scores, fg_mask, target_gt_idx = self.assigner(
            pred_scores.detach().sigmoid(),
            (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
            anchor_points * stride_tensor,
            gt_labels,
            gt_bboxes,
            mask_gt,
        )

        target_scores_sum = max(target_scores.sum(), 1)

        # Cls loss
        # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way
        loss[2] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum  # BCE

        if fg_mask.sum():
            # Bbox loss
            loss[0], loss[3] = self.bbox_loss(
                pred_distri,
                pred_bboxes,
                anchor_points,
                target_bboxes / stride_tensor,
                target_scores,
                target_scores_sum,
                fg_mask,
            )
            # Masks loss
            masks = batch["masks"].to(self.device).float()
            if tuple(masks.shape[-2:]) != (mask_h, mask_w):  # downsample
                masks = F.interpolate(masks[None], (mask_h, mask_w), mode="nearest")[0]

            loss[1] = self.calculate_segmentation_loss(
                fg_mask, masks, target_gt_idx, target_bboxes, batch_idx, proto, pred_masks, imgsz, self.overlap
            )

        # WARNING: lines below prevent Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove
        else:
            loss[1] += (proto * 0).sum() + (pred_masks * 0).sum()  # inf sums may lead to nan loss

        loss[0] *= self.hyp.box  # box gain
        loss[1] *= self.hyp.box  # seg gain
        loss[2] *= self.hyp.cls  # cls gain
        loss[3] *= self.hyp.dfl  # dfl gain

        return loss.sum() * batch_size, loss.detach()  # loss(box, cls, dfl)

    @staticmethod
    def single_mask_loss(
        gt_mask: torch.Tensor, pred: torch.Tensor, proto: torch.Tensor, xyxy: torch.Tensor, area: torch.Tensor
    ) -> torch.Tensor:
        """
        Compute the instance segmentation loss for a single image.

        Args:
            gt_mask (torch.Tensor): Ground truth mask of shape (n, H, W), where n is the number of objects.
            pred (torch.Tensor): Predicted mask coefficients of shape (n, 32).
            proto (torch.Tensor): Prototype masks of shape (32, H, W).
            xyxy (torch.Tensor): Ground truth bounding boxes in xyxy format, normalized to [0, 1], of shape (n, 4).
            area (torch.Tensor): Area of each ground truth bounding box of shape (n,).

        Returns:
            (torch.Tensor): The calculated mask loss for a single image.

        Notes:
            The function uses the equation pred_mask = torch.einsum('in,nhw->ihw', pred, proto) to produce the
            predicted masks from the prototype masks and predicted mask coefficients.
        """
        pred_mask = torch.einsum("in,nhw->ihw", pred, proto)  # (n, 32) @ (32, 80, 80) -> (n, 80, 80)
        loss = F.binary_cross_entropy_with_logits(pred_mask, gt_mask, reduction="none")
        return (crop_mask(loss, xyxy).mean(dim=(1, 2)) / area).sum()

    def calculate_segmentation_loss(
        self,
        fg_mask: torch.Tensor,
        masks: torch.Tensor,
        target_gt_idx: torch.Tensor,
        target_bboxes: torch.Tensor,
        batch_idx: torch.Tensor,
        proto: torch.Tensor,
        pred_masks: torch.Tensor,
        imgsz: torch.Tensor,
        overlap: bool,
    ) -> torch.Tensor:
        """
        Calculate the loss for instance segmentation.

        Args:
            fg_mask (torch.Tensor): A binary tensor of shape (BS, N_anchors) indicating which anchors are positive.
            masks (torch.Tensor): Ground truth masks of shape (BS, H, W) if `overlap` is False, otherwise (BS, ?, H, W).
            target_gt_idx (torch.Tensor): Indexes of ground truth objects for each anchor of shape (BS, N_anchors).
            target_bboxes (torch.Tensor): Ground truth bounding boxes for each anchor of shape (BS, N_anchors, 4).
            batch_idx (torch.Tensor): Batch indices of shape (N_labels_in_batch, 1).
            proto (torch.Tensor): Prototype masks of shape (BS, 32, H, W).
            pred_masks (torch.Tensor): Predicted masks for each anchor of shape (BS, N_anchors, 32).
            imgsz (torch.Tensor): Size of the input image as a tensor of shape (2), i.e., (H, W).
            overlap (bool): Whether the masks in `masks` tensor overlap.

        Returns:
            (torch.Tensor): The calculated loss for instance segmentation.

        Notes:
            The batch loss can be computed for improved speed at higher memory usage.
            For example, pred_mask can be computed as follows:
                pred_mask = torch.einsum('in,nhw->ihw', pred, proto)  # (i, 32) @ (32, 160, 160) -> (i, 160, 160)
        """
        _, _, mask_h, mask_w = proto.shape
        loss = 0

        # Normalize to 0-1
        target_bboxes_normalized = target_bboxes / imgsz[[1, 0, 1, 0]]

        # Areas of target bboxes
        marea = xyxy2xywh(target_bboxes_normalized)[..., 2:].prod(2)

        # Normalize to mask size
        mxyxy = target_bboxes_normalized * torch.tensor([mask_w, mask_h, mask_w, mask_h], device=proto.device)

        for i, single_i in enumerate(zip(fg_mask, target_gt_idx, pred_masks, proto, mxyxy, marea, masks)):
            fg_mask_i, target_gt_idx_i, pred_masks_i, proto_i, mxyxy_i, marea_i, masks_i = single_i
            if fg_mask_i.any():
                mask_idx = target_gt_idx_i[fg_mask_i]
                if overlap:
                    gt_mask = masks_i == (mask_idx + 1).view(-1, 1, 1)
                    gt_mask = gt_mask.float()
                else:
                    gt_mask = masks[batch_idx.view(-1) == i][mask_idx]

                loss += self.single_mask_loss(
                    gt_mask, pred_masks_i[fg_mask_i], proto_i, mxyxy_i[fg_mask_i], marea_i[fg_mask_i]
                )

            # WARNING: lines below prevents Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove
            else:
                loss += (proto * 0).sum() + (pred_masks * 0).sum()  # inf sums may lead to nan loss

        return loss / fg_mask.sum()

__call__(preds, batch)

Calcula y devuelve la pérdida del modelo YOLO .

Código fuente en ultralytics/utils/loss.py
def __call__(self, preds, batch):
    """Calculate and return the loss for the YOLO model."""
    loss = torch.zeros(4, device=self.device)  # box, cls, dfl
    feats, pred_masks, proto = preds if len(preds) == 3 else preds[1]
    batch_size, _, mask_h, mask_w = proto.shape  # batch size, number of masks, mask height, mask width
    pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
        (self.reg_max * 4, self.nc), 1
    )

    # B, grids, ..
    pred_scores = pred_scores.permute(0, 2, 1).contiguous()
    pred_distri = pred_distri.permute(0, 2, 1).contiguous()
    pred_masks = pred_masks.permute(0, 2, 1).contiguous()

    dtype = pred_scores.dtype
    imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0]  # image size (h,w)
    anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)

    # Targets
    try:
        batch_idx = batch["batch_idx"].view(-1, 1)
        targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1)
        targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
        gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
        mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
    except RuntimeError as e:
        raise TypeError(
            "ERROR ‚ĚĆ segment dataset incorrectly formatted or not a segment dataset.\n"
            "This error can occur when incorrectly training a 'segment' model on a 'detect' dataset, "
            "i.e. 'yolo train model=yolov8n-seg.pt data=coco8.yaml'.\nVerify your dataset is a "
            "correctly formatted 'segment' dataset using 'data=coco8-seg.yaml' "
            "as an example.\nSee https://docs.ultralytics.com/datasets/segment/ for help."
        ) from e

    # Pboxes
    pred_bboxes = self.bbox_decode(anchor_points, pred_distri)  # xyxy, (b, h*w, 4)

    _, target_bboxes, target_scores, fg_mask, target_gt_idx = self.assigner(
        pred_scores.detach().sigmoid(),
        (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
        anchor_points * stride_tensor,
        gt_labels,
        gt_bboxes,
        mask_gt,
    )

    target_scores_sum = max(target_scores.sum(), 1)

    # Cls loss
    # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way
    loss[2] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum  # BCE

    if fg_mask.sum():
        # Bbox loss
        loss[0], loss[3] = self.bbox_loss(
            pred_distri,
            pred_bboxes,
            anchor_points,
            target_bboxes / stride_tensor,
            target_scores,
            target_scores_sum,
            fg_mask,
        )
        # Masks loss
        masks = batch["masks"].to(self.device).float()
        if tuple(masks.shape[-2:]) != (mask_h, mask_w):  # downsample
            masks = F.interpolate(masks[None], (mask_h, mask_w), mode="nearest")[0]

        loss[1] = self.calculate_segmentation_loss(
            fg_mask, masks, target_gt_idx, target_bboxes, batch_idx, proto, pred_masks, imgsz, self.overlap
        )

    # WARNING: lines below prevent Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove
    else:
        loss[1] += (proto * 0).sum() + (pred_masks * 0).sum()  # inf sums may lead to nan loss

    loss[0] *= self.hyp.box  # box gain
    loss[1] *= self.hyp.box  # seg gain
    loss[2] *= self.hyp.cls  # cls gain
    loss[3] *= self.hyp.dfl  # dfl gain

    return loss.sum() * batch_size, loss.detach()  # loss(box, cls, dfl)

__init__(model)

Inicializa la clase v8SegmentationLoss, tomando como argumento un modelo desparalizado.

Código fuente en ultralytics/utils/loss.py
def __init__(self, model):  # model must be de-paralleled
    """Initializes the v8SegmentationLoss class, taking a de-paralleled model as argument."""
    super().__init__(model)
    self.overlap = model.args.overlap_mask

calculate_segmentation_loss(fg_mask, masks, target_gt_idx, target_bboxes, batch_idx, proto, pred_masks, imgsz, overlap)

Calcula la pérdida por segmentación de instancia.

Par√°metros:

Nombre Tipo Descripción Por defecto
fg_mask Tensor

Un tensor binario de forma (BS, N_anclas) que indica qué anclas son positivas.

necesario
masks Tensor

M√°scaras de la verdad sobre el terreno de forma (BS, H, W) si overlap es Falso, en caso contrario (BS, ?, H, W).

necesario
target_gt_idx Tensor

√ćndices de objetos verdaderos para cada ancla de forma (BS, N_anclas).

necesario
target_bboxes Tensor

Cajas delimitadoras de la verdad sobre el terreno para cada ancla de la forma (BS, N_anclas, 4).

necesario
batch_idx Tensor

√ćndices de lote de forma (N_etiquetas_en_lote, 1).

necesario
proto Tensor

Prototipos de m√°scaras de forma (BS, 32, H, W).

necesario
pred_masks Tensor

M√°scaras previstas para cada ancla de forma (BS, N_anclas, 32).

necesario
imgsz Tensor

Tama√Īo de la imagen de entrada como tensor de la forma (2), es decir, (H, W).

necesario
overlap bool

Si las m√°scaras de masks tensor solapamiento.

necesario

Devuelve:

Tipo Descripción
Tensor

La pérdida calculada para la segmentación por ejemplo.

Notas

La pérdida por lotes puede calcularse para mejorar la velocidad con un mayor uso de memoria. Por ejemplo, pred_mask se puede calcular de la siguiente manera: pred_mask = torch.einsum('in,nhw->ihw', pred, proto) # (i, 32) @ (32, 160, 160) -> (i, 160, 160)

Código fuente en ultralytics/utils/loss.py
def calculate_segmentation_loss(
    self,
    fg_mask: torch.Tensor,
    masks: torch.Tensor,
    target_gt_idx: torch.Tensor,
    target_bboxes: torch.Tensor,
    batch_idx: torch.Tensor,
    proto: torch.Tensor,
    pred_masks: torch.Tensor,
    imgsz: torch.Tensor,
    overlap: bool,
) -> torch.Tensor:
    """
    Calculate the loss for instance segmentation.

    Args:
        fg_mask (torch.Tensor): A binary tensor of shape (BS, N_anchors) indicating which anchors are positive.
        masks (torch.Tensor): Ground truth masks of shape (BS, H, W) if `overlap` is False, otherwise (BS, ?, H, W).
        target_gt_idx (torch.Tensor): Indexes of ground truth objects for each anchor of shape (BS, N_anchors).
        target_bboxes (torch.Tensor): Ground truth bounding boxes for each anchor of shape (BS, N_anchors, 4).
        batch_idx (torch.Tensor): Batch indices of shape (N_labels_in_batch, 1).
        proto (torch.Tensor): Prototype masks of shape (BS, 32, H, W).
        pred_masks (torch.Tensor): Predicted masks for each anchor of shape (BS, N_anchors, 32).
        imgsz (torch.Tensor): Size of the input image as a tensor of shape (2), i.e., (H, W).
        overlap (bool): Whether the masks in `masks` tensor overlap.

    Returns:
        (torch.Tensor): The calculated loss for instance segmentation.

    Notes:
        The batch loss can be computed for improved speed at higher memory usage.
        For example, pred_mask can be computed as follows:
            pred_mask = torch.einsum('in,nhw->ihw', pred, proto)  # (i, 32) @ (32, 160, 160) -> (i, 160, 160)
    """
    _, _, mask_h, mask_w = proto.shape
    loss = 0

    # Normalize to 0-1
    target_bboxes_normalized = target_bboxes / imgsz[[1, 0, 1, 0]]

    # Areas of target bboxes
    marea = xyxy2xywh(target_bboxes_normalized)[..., 2:].prod(2)

    # Normalize to mask size
    mxyxy = target_bboxes_normalized * torch.tensor([mask_w, mask_h, mask_w, mask_h], device=proto.device)

    for i, single_i in enumerate(zip(fg_mask, target_gt_idx, pred_masks, proto, mxyxy, marea, masks)):
        fg_mask_i, target_gt_idx_i, pred_masks_i, proto_i, mxyxy_i, marea_i, masks_i = single_i
        if fg_mask_i.any():
            mask_idx = target_gt_idx_i[fg_mask_i]
            if overlap:
                gt_mask = masks_i == (mask_idx + 1).view(-1, 1, 1)
                gt_mask = gt_mask.float()
            else:
                gt_mask = masks[batch_idx.view(-1) == i][mask_idx]

            loss += self.single_mask_loss(
                gt_mask, pred_masks_i[fg_mask_i], proto_i, mxyxy_i[fg_mask_i], marea_i[fg_mask_i]
            )

        # WARNING: lines below prevents Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove
        else:
            loss += (proto * 0).sum() + (pred_masks * 0).sum()  # inf sums may lead to nan loss

    return loss / fg_mask.sum()

single_mask_loss(gt_mask, pred, proto, xyxy, area) staticmethod

Calcula la pérdida de segmentación de la instancia para una sola imagen.

Par√°metros:

Nombre Tipo Descripción Por defecto
gt_mask Tensor

M√°scara de la verdad sobre el terreno de forma (n, H, W), donde n es el n√ļmero de objetos.

necesario
pred Tensor

Coeficientes predichos de la m√°scara de forma (n, 32).

necesario
proto Tensor

Prototipos de m√°scaras de forma (32, H, A).

necesario
xyxy Tensor

Cuadros delimitadores de la verdad sobre el terreno en formato xyxy, normalizados a [0, 1], de forma (n, 4).

necesario
area Tensor

√Ārea de cada cuadro delimitador de la verdad sobre el terreno de la forma (n,).

necesario

Devuelve:

Tipo Descripción
Tensor

La pérdida de máscara calculada para una sola imagen.

Notas

La función utiliza la ecuación pred_mask = torch.einsum('in,nhw->ihw', pred, proto) para producir las máscaras predichas a partir de las máscaras prototipo y los coeficientes de máscara predichos.

Código fuente en ultralytics/utils/loss.py
@staticmethod
def single_mask_loss(
    gt_mask: torch.Tensor, pred: torch.Tensor, proto: torch.Tensor, xyxy: torch.Tensor, area: torch.Tensor
) -> torch.Tensor:
    """
    Compute the instance segmentation loss for a single image.

    Args:
        gt_mask (torch.Tensor): Ground truth mask of shape (n, H, W), where n is the number of objects.
        pred (torch.Tensor): Predicted mask coefficients of shape (n, 32).
        proto (torch.Tensor): Prototype masks of shape (32, H, W).
        xyxy (torch.Tensor): Ground truth bounding boxes in xyxy format, normalized to [0, 1], of shape (n, 4).
        area (torch.Tensor): Area of each ground truth bounding box of shape (n,).

    Returns:
        (torch.Tensor): The calculated mask loss for a single image.

    Notes:
        The function uses the equation pred_mask = torch.einsum('in,nhw->ihw', pred, proto) to produce the
        predicted masks from the prototype masks and predicted mask coefficients.
    """
    pred_mask = torch.einsum("in,nhw->ihw", pred, proto)  # (n, 32) @ (32, 80, 80) -> (n, 80, 80)
    loss = F.binary_cross_entropy_with_logits(pred_mask, gt_mask, reduction="none")
    return (crop_mask(loss, xyxy).mean(dim=(1, 2)) / area).sum()



ultralytics.utils.loss.v8PoseLoss

Bases: v8DetectionLoss

Clase de criterio para calcular las pérdidas de entrenamiento.

Código fuente en ultralytics/utils/loss.py
class v8PoseLoss(v8DetectionLoss):
    """Criterion class for computing training losses."""

    def __init__(self, model):  # model must be de-paralleled
        """Initializes v8PoseLoss with model, sets keypoint variables and declares a keypoint loss instance."""
        super().__init__(model)
        self.kpt_shape = model.model[-1].kpt_shape
        self.bce_pose = nn.BCEWithLogitsLoss()
        is_pose = self.kpt_shape == [17, 3]
        nkpt = self.kpt_shape[0]  # number of keypoints
        sigmas = torch.from_numpy(OKS_SIGMA).to(self.device) if is_pose else torch.ones(nkpt, device=self.device) / nkpt
        self.keypoint_loss = KeypointLoss(sigmas=sigmas)

    def __call__(self, preds, batch):
        """Calculate the total loss and detach it."""
        loss = torch.zeros(5, device=self.device)  # box, cls, dfl, kpt_location, kpt_visibility
        feats, pred_kpts = preds if isinstance(preds[0], list) else preds[1]
        pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
            (self.reg_max * 4, self.nc), 1
        )

        # B, grids, ..
        pred_scores = pred_scores.permute(0, 2, 1).contiguous()
        pred_distri = pred_distri.permute(0, 2, 1).contiguous()
        pred_kpts = pred_kpts.permute(0, 2, 1).contiguous()

        dtype = pred_scores.dtype
        imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0]  # image size (h,w)
        anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)

        # Targets
        batch_size = pred_scores.shape[0]
        batch_idx = batch["batch_idx"].view(-1, 1)
        targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1)
        targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
        gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
        mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)

        # Pboxes
        pred_bboxes = self.bbox_decode(anchor_points, pred_distri)  # xyxy, (b, h*w, 4)
        pred_kpts = self.kpts_decode(anchor_points, pred_kpts.view(batch_size, -1, *self.kpt_shape))  # (b, h*w, 17, 3)

        _, target_bboxes, target_scores, fg_mask, target_gt_idx = self.assigner(
            pred_scores.detach().sigmoid(),
            (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
            anchor_points * stride_tensor,
            gt_labels,
            gt_bboxes,
            mask_gt,
        )

        target_scores_sum = max(target_scores.sum(), 1)

        # Cls loss
        # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way
        loss[3] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum  # BCE

        # Bbox loss
        if fg_mask.sum():
            target_bboxes /= stride_tensor
            loss[0], loss[4] = self.bbox_loss(
                pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask
            )
            keypoints = batch["keypoints"].to(self.device).float().clone()
            keypoints[..., 0] *= imgsz[1]
            keypoints[..., 1] *= imgsz[0]

            loss[1], loss[2] = self.calculate_keypoints_loss(
                fg_mask, target_gt_idx, keypoints, batch_idx, stride_tensor, target_bboxes, pred_kpts
            )

        loss[0] *= self.hyp.box  # box gain
        loss[1] *= self.hyp.pose  # pose gain
        loss[2] *= self.hyp.kobj  # kobj gain
        loss[3] *= self.hyp.cls  # cls gain
        loss[4] *= self.hyp.dfl  # dfl gain

        return loss.sum() * batch_size, loss.detach()  # loss(box, cls, dfl)

    @staticmethod
    def kpts_decode(anchor_points, pred_kpts):
        """Decodes predicted keypoints to image coordinates."""
        y = pred_kpts.clone()
        y[..., :2] *= 2.0
        y[..., 0] += anchor_points[:, [0]] - 0.5
        y[..., 1] += anchor_points[:, [1]] - 0.5
        return y

    def calculate_keypoints_loss(
        self, masks, target_gt_idx, keypoints, batch_idx, stride_tensor, target_bboxes, pred_kpts
    ):
        """
        Calculate the keypoints loss for the model.

        This function calculates the keypoints loss and keypoints object loss for a given batch. The keypoints loss is
        based on the difference between the predicted keypoints and ground truth keypoints. The keypoints object loss is
        a binary classification loss that classifies whether a keypoint is present or not.

        Args:
            masks (torch.Tensor): Binary mask tensor indicating object presence, shape (BS, N_anchors).
            target_gt_idx (torch.Tensor): Index tensor mapping anchors to ground truth objects, shape (BS, N_anchors).
            keypoints (torch.Tensor): Ground truth keypoints, shape (N_kpts_in_batch, N_kpts_per_object, kpts_dim).
            batch_idx (torch.Tensor): Batch index tensor for keypoints, shape (N_kpts_in_batch, 1).
            stride_tensor (torch.Tensor): Stride tensor for anchors, shape (N_anchors, 1).
            target_bboxes (torch.Tensor): Ground truth boxes in (x1, y1, x2, y2) format, shape (BS, N_anchors, 4).
            pred_kpts (torch.Tensor): Predicted keypoints, shape (BS, N_anchors, N_kpts_per_object, kpts_dim).

        Returns:
            (tuple): Returns a tuple containing:
                - kpts_loss (torch.Tensor): The keypoints loss.
                - kpts_obj_loss (torch.Tensor): The keypoints object loss.
        """
        batch_idx = batch_idx.flatten()
        batch_size = len(masks)

        # Find the maximum number of keypoints in a single image
        max_kpts = torch.unique(batch_idx, return_counts=True)[1].max()

        # Create a tensor to hold batched keypoints
        batched_keypoints = torch.zeros(
            (batch_size, max_kpts, keypoints.shape[1], keypoints.shape[2]), device=keypoints.device
        )

        # TODO: any idea how to vectorize this?
        # Fill batched_keypoints with keypoints based on batch_idx
        for i in range(batch_size):
            keypoints_i = keypoints[batch_idx == i]
            batched_keypoints[i, : keypoints_i.shape[0]] = keypoints_i

        # Expand dimensions of target_gt_idx to match the shape of batched_keypoints
        target_gt_idx_expanded = target_gt_idx.unsqueeze(-1).unsqueeze(-1)

        # Use target_gt_idx_expanded to select keypoints from batched_keypoints
        selected_keypoints = batched_keypoints.gather(
            1, target_gt_idx_expanded.expand(-1, -1, keypoints.shape[1], keypoints.shape[2])
        )

        # Divide coordinates by stride
        selected_keypoints /= stride_tensor.view(1, -1, 1, 1)

        kpts_loss = 0
        kpts_obj_loss = 0

        if masks.any():
            gt_kpt = selected_keypoints[masks]
            area = xyxy2xywh(target_bboxes[masks])[:, 2:].prod(1, keepdim=True)
            pred_kpt = pred_kpts[masks]
            kpt_mask = gt_kpt[..., 2] != 0 if gt_kpt.shape[-1] == 3 else torch.full_like(gt_kpt[..., 0], True)
            kpts_loss = self.keypoint_loss(pred_kpt, gt_kpt, kpt_mask, area)  # pose loss

            if pred_kpt.shape[-1] == 3:
                kpts_obj_loss = self.bce_pose(pred_kpt[..., 2], kpt_mask.float())  # keypoint obj loss

        return kpts_loss, kpts_obj_loss

__call__(preds, batch)

Calcula la pérdida total y sepárala.

Código fuente en ultralytics/utils/loss.py
def __call__(self, preds, batch):
    """Calculate the total loss and detach it."""
    loss = torch.zeros(5, device=self.device)  # box, cls, dfl, kpt_location, kpt_visibility
    feats, pred_kpts = preds if isinstance(preds[0], list) else preds[1]
    pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
        (self.reg_max * 4, self.nc), 1
    )

    # B, grids, ..
    pred_scores = pred_scores.permute(0, 2, 1).contiguous()
    pred_distri = pred_distri.permute(0, 2, 1).contiguous()
    pred_kpts = pred_kpts.permute(0, 2, 1).contiguous()

    dtype = pred_scores.dtype
    imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0]  # image size (h,w)
    anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)

    # Targets
    batch_size = pred_scores.shape[0]
    batch_idx = batch["batch_idx"].view(-1, 1)
    targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1)
    targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
    gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
    mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)

    # Pboxes
    pred_bboxes = self.bbox_decode(anchor_points, pred_distri)  # xyxy, (b, h*w, 4)
    pred_kpts = self.kpts_decode(anchor_points, pred_kpts.view(batch_size, -1, *self.kpt_shape))  # (b, h*w, 17, 3)

    _, target_bboxes, target_scores, fg_mask, target_gt_idx = self.assigner(
        pred_scores.detach().sigmoid(),
        (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
        anchor_points * stride_tensor,
        gt_labels,
        gt_bboxes,
        mask_gt,
    )

    target_scores_sum = max(target_scores.sum(), 1)

    # Cls loss
    # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way
    loss[3] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum  # BCE

    # Bbox loss
    if fg_mask.sum():
        target_bboxes /= stride_tensor
        loss[0], loss[4] = self.bbox_loss(
            pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask
        )
        keypoints = batch["keypoints"].to(self.device).float().clone()
        keypoints[..., 0] *= imgsz[1]
        keypoints[..., 1] *= imgsz[0]

        loss[1], loss[2] = self.calculate_keypoints_loss(
            fg_mask, target_gt_idx, keypoints, batch_idx, stride_tensor, target_bboxes, pred_kpts
        )

    loss[0] *= self.hyp.box  # box gain
    loss[1] *= self.hyp.pose  # pose gain
    loss[2] *= self.hyp.kobj  # kobj gain
    loss[3] *= self.hyp.cls  # cls gain
    loss[4] *= self.hyp.dfl  # dfl gain

    return loss.sum() * batch_size, loss.detach()  # loss(box, cls, dfl)

__init__(model)

Inicializa v8PoseLoss con el modelo, establece variables de punto clave y declara una instancia de pérdida de punto clave.

Código fuente en ultralytics/utils/loss.py
def __init__(self, model):  # model must be de-paralleled
    """Initializes v8PoseLoss with model, sets keypoint variables and declares a keypoint loss instance."""
    super().__init__(model)
    self.kpt_shape = model.model[-1].kpt_shape
    self.bce_pose = nn.BCEWithLogitsLoss()
    is_pose = self.kpt_shape == [17, 3]
    nkpt = self.kpt_shape[0]  # number of keypoints
    sigmas = torch.from_numpy(OKS_SIGMA).to(self.device) if is_pose else torch.ones(nkpt, device=self.device) / nkpt
    self.keypoint_loss = KeypointLoss(sigmas=sigmas)

calculate_keypoints_loss(masks, target_gt_idx, keypoints, batch_idx, stride_tensor, target_bboxes, pred_kpts)

Calcula la pérdida de puntos clave del modelo.

Esta función calcula la pérdida de puntos clave y la pérdida de objetos de puntos clave de un lote determinado. La pérdida de puntos clave basada en la diferencia entre los puntos clave predichos y los puntos clave reales. La pérdida por objeto de los puntos clave es una pérdida de clasificación binaria que clasifica si un punto clave está presente o no.

Par√°metros:

Nombre Tipo Descripción Por defecto
masks Tensor

M√°scara binaria tensor que indica la presencia del objeto, forma (BS, N_anclajes).

necesario
target_gt_idx Tensor

√ćndice tensor que asigna anclas a objetos de la verdad sobre el terreno, forma (BS, N_anclas).

necesario
keypoints Tensor

Puntos clave de la verdad sobre el terreno, forma (N_kpts_en_lote, N_kpts_por_objeto, kpts_dim).

necesario
batch_idx Tensor

√ćndice de lote tensor para puntos clave, forma (N_kpts_en_lote, 1).

necesario
stride_tensor Tensor

Zancada tensor para anclas, forma (N_anclas, 1).

necesario
target_bboxes Tensor

Cajas de verdad sobre el terreno en formato (x1, y1, x2, y2), forma (BS, N_anclajes, 4).

necesario
pred_kpts Tensor

Puntos clave previstos, forma (BS, N_anclajes, N_kpts_por_objeto, kpts_dim).

necesario

Devuelve:

Tipo Descripción
tuple

Devuelve una tupla que contiene: - kpts_loss (torch.Tensor): La pérdida de puntos clave. - kpts_obj_loss (torch.Tensor): La pérdida de los puntos clave del objeto.

Código fuente en ultralytics/utils/loss.py
def calculate_keypoints_loss(
    self, masks, target_gt_idx, keypoints, batch_idx, stride_tensor, target_bboxes, pred_kpts
):
    """
    Calculate the keypoints loss for the model.

    This function calculates the keypoints loss and keypoints object loss for a given batch. The keypoints loss is
    based on the difference between the predicted keypoints and ground truth keypoints. The keypoints object loss is
    a binary classification loss that classifies whether a keypoint is present or not.

    Args:
        masks (torch.Tensor): Binary mask tensor indicating object presence, shape (BS, N_anchors).
        target_gt_idx (torch.Tensor): Index tensor mapping anchors to ground truth objects, shape (BS, N_anchors).
        keypoints (torch.Tensor): Ground truth keypoints, shape (N_kpts_in_batch, N_kpts_per_object, kpts_dim).
        batch_idx (torch.Tensor): Batch index tensor for keypoints, shape (N_kpts_in_batch, 1).
        stride_tensor (torch.Tensor): Stride tensor for anchors, shape (N_anchors, 1).
        target_bboxes (torch.Tensor): Ground truth boxes in (x1, y1, x2, y2) format, shape (BS, N_anchors, 4).
        pred_kpts (torch.Tensor): Predicted keypoints, shape (BS, N_anchors, N_kpts_per_object, kpts_dim).

    Returns:
        (tuple): Returns a tuple containing:
            - kpts_loss (torch.Tensor): The keypoints loss.
            - kpts_obj_loss (torch.Tensor): The keypoints object loss.
    """
    batch_idx = batch_idx.flatten()
    batch_size = len(masks)

    # Find the maximum number of keypoints in a single image
    max_kpts = torch.unique(batch_idx, return_counts=True)[1].max()

    # Create a tensor to hold batched keypoints
    batched_keypoints = torch.zeros(
        (batch_size, max_kpts, keypoints.shape[1], keypoints.shape[2]), device=keypoints.device
    )

    # TODO: any idea how to vectorize this?
    # Fill batched_keypoints with keypoints based on batch_idx
    for i in range(batch_size):
        keypoints_i = keypoints[batch_idx == i]
        batched_keypoints[i, : keypoints_i.shape[0]] = keypoints_i

    # Expand dimensions of target_gt_idx to match the shape of batched_keypoints
    target_gt_idx_expanded = target_gt_idx.unsqueeze(-1).unsqueeze(-1)

    # Use target_gt_idx_expanded to select keypoints from batched_keypoints
    selected_keypoints = batched_keypoints.gather(
        1, target_gt_idx_expanded.expand(-1, -1, keypoints.shape[1], keypoints.shape[2])
    )

    # Divide coordinates by stride
    selected_keypoints /= stride_tensor.view(1, -1, 1, 1)

    kpts_loss = 0
    kpts_obj_loss = 0

    if masks.any():
        gt_kpt = selected_keypoints[masks]
        area = xyxy2xywh(target_bboxes[masks])[:, 2:].prod(1, keepdim=True)
        pred_kpt = pred_kpts[masks]
        kpt_mask = gt_kpt[..., 2] != 0 if gt_kpt.shape[-1] == 3 else torch.full_like(gt_kpt[..., 0], True)
        kpts_loss = self.keypoint_loss(pred_kpt, gt_kpt, kpt_mask, area)  # pose loss

        if pred_kpt.shape[-1] == 3:
            kpts_obj_loss = self.bce_pose(pred_kpt[..., 2], kpt_mask.float())  # keypoint obj loss

    return kpts_loss, kpts_obj_loss

kpts_decode(anchor_points, pred_kpts) staticmethod

Decodifica los puntos clave previstos en coordenadas de imagen.

Código fuente en ultralytics/utils/loss.py
@staticmethod
def kpts_decode(anchor_points, pred_kpts):
    """Decodes predicted keypoints to image coordinates."""
    y = pred_kpts.clone()
    y[..., :2] *= 2.0
    y[..., 0] += anchor_points[:, [0]] - 0.5
    y[..., 1] += anchor_points[:, [1]] - 0.5
    return y



ultralytics.utils.loss.v8ClassificationLoss

Clase de criterio para calcular las pérdidas de entrenamiento.

Código fuente en ultralytics/utils/loss.py
class v8ClassificationLoss:
    """Criterion class for computing training losses."""

    def __call__(self, preds, batch):
        """Compute the classification loss between predictions and true labels."""
        loss = torch.nn.functional.cross_entropy(preds, batch["cls"], reduction="mean")
        loss_items = loss.detach()
        return loss, loss_items

__call__(preds, batch)

Calcula la pérdida de clasificación entre las predicciones y las etiquetas verdaderas.

Código fuente en ultralytics/utils/loss.py
def __call__(self, preds, batch):
    """Compute the classification loss between predictions and true labels."""
    loss = torch.nn.functional.cross_entropy(preds, batch["cls"], reduction="mean")
    loss_items = loss.detach()
    return loss, loss_items



ultralytics.utils.loss.v8OBBLoss

Bases: v8DetectionLoss

Código fuente en ultralytics/utils/loss.py
class v8OBBLoss(v8DetectionLoss):
    def __init__(self, model):
        """
        Initializes v8OBBLoss with model, assigner, and rotated bbox loss.

        Note model must be de-paralleled.
        """
        super().__init__(model)
        self.assigner = RotatedTaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0)
        self.bbox_loss = RotatedBboxLoss(self.reg_max - 1, use_dfl=self.use_dfl).to(self.device)

    def preprocess(self, targets, batch_size, scale_tensor):
        """Preprocesses the target counts and matches with the input batch size to output a tensor."""
        if targets.shape[0] == 0:
            out = torch.zeros(batch_size, 0, 6, device=self.device)
        else:
            i = targets[:, 0]  # image index
            _, counts = i.unique(return_counts=True)
            counts = counts.to(dtype=torch.int32)
            out = torch.zeros(batch_size, counts.max(), 6, device=self.device)
            for j in range(batch_size):
                matches = i == j
                n = matches.sum()
                if n:
                    bboxes = targets[matches, 2:]
                    bboxes[..., :4].mul_(scale_tensor)
                    out[j, :n] = torch.cat([targets[matches, 1:2], bboxes], dim=-1)
        return out

    def __call__(self, preds, batch):
        """Calculate and return the loss for the YOLO model."""
        loss = torch.zeros(3, device=self.device)  # box, cls, dfl
        feats, pred_angle = preds if isinstance(preds[0], list) else preds[1]
        batch_size = pred_angle.shape[0]  # batch size, number of masks, mask height, mask width
        pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
            (self.reg_max * 4, self.nc), 1
        )

        # b, grids, ..
        pred_scores = pred_scores.permute(0, 2, 1).contiguous()
        pred_distri = pred_distri.permute(0, 2, 1).contiguous()
        pred_angle = pred_angle.permute(0, 2, 1).contiguous()

        dtype = pred_scores.dtype
        imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0]  # image size (h,w)
        anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)

        # targets
        try:
            batch_idx = batch["batch_idx"].view(-1, 1)
            targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"].view(-1, 5)), 1)
            rw, rh = targets[:, 4] * imgsz[0].item(), targets[:, 5] * imgsz[1].item()
            targets = targets[(rw >= 2) & (rh >= 2)]  # filter rboxes of tiny size to stabilize training
            targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
            gt_labels, gt_bboxes = targets.split((1, 5), 2)  # cls, xywhr
            mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
        except RuntimeError as e:
            raise TypeError(
                "ERROR ‚ĚĆ OBB dataset incorrectly formatted or not a OBB dataset.\n"
                "This error can occur when incorrectly training a 'OBB' model on a 'detect' dataset, "
                "i.e. 'yolo train model=yolov8n-obb.pt data=dota8.yaml'.\nVerify your dataset is a "
                "correctly formatted 'OBB' dataset using 'data=dota8.yaml' "
                "as an example.\nSee https://docs.ultralytics.com/datasets/obb/ for help."
            ) from e

        # Pboxes
        pred_bboxes = self.bbox_decode(anchor_points, pred_distri, pred_angle)  # xyxy, (b, h*w, 4)

        bboxes_for_assigner = pred_bboxes.clone().detach()
        # Only the first four elements need to be scaled
        bboxes_for_assigner[..., :4] *= stride_tensor
        _, target_bboxes, target_scores, fg_mask, _ = self.assigner(
            pred_scores.detach().sigmoid(),
            bboxes_for_assigner.type(gt_bboxes.dtype),
            anchor_points * stride_tensor,
            gt_labels,
            gt_bboxes,
            mask_gt,
        )

        target_scores_sum = max(target_scores.sum(), 1)

        # Cls loss
        # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way
        loss[1] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum  # BCE

        # Bbox loss
        if fg_mask.sum():
            target_bboxes[..., :4] /= stride_tensor
            loss[0], loss[2] = self.bbox_loss(
                pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask
            )
        else:
            loss[0] += (pred_angle * 0).sum()

        loss[0] *= self.hyp.box  # box gain
        loss[1] *= self.hyp.cls  # cls gain
        loss[2] *= self.hyp.dfl  # dfl gain

        return loss.sum() * batch_size, loss.detach()  # loss(box, cls, dfl)

    def bbox_decode(self, anchor_points, pred_dist, pred_angle):
        """
        Decode predicted object bounding box coordinates from anchor points and distribution.

        Args:
            anchor_points (torch.Tensor): Anchor points, (h*w, 2).
            pred_dist (torch.Tensor): Predicted rotated distance, (bs, h*w, 4).
            pred_angle (torch.Tensor): Predicted angle, (bs, h*w, 1).

        Returns:
            (torch.Tensor): Predicted rotated bounding boxes with angles, (bs, h*w, 5).
        """
        if self.use_dfl:
            b, a, c = pred_dist.shape  # batch, anchors, channels
            pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype))
        return torch.cat((dist2rbox(pred_dist, pred_angle, anchor_points), pred_angle), dim=-1)

__call__(preds, batch)

Calcula y devuelve la pérdida del modelo YOLO .

Código fuente en ultralytics/utils/loss.py
def __call__(self, preds, batch):
    """Calculate and return the loss for the YOLO model."""
    loss = torch.zeros(3, device=self.device)  # box, cls, dfl
    feats, pred_angle = preds if isinstance(preds[0], list) else preds[1]
    batch_size = pred_angle.shape[0]  # batch size, number of masks, mask height, mask width
    pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
        (self.reg_max * 4, self.nc), 1
    )

    # b, grids, ..
    pred_scores = pred_scores.permute(0, 2, 1).contiguous()
    pred_distri = pred_distri.permute(0, 2, 1).contiguous()
    pred_angle = pred_angle.permute(0, 2, 1).contiguous()

    dtype = pred_scores.dtype
    imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0]  # image size (h,w)
    anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)

    # targets
    try:
        batch_idx = batch["batch_idx"].view(-1, 1)
        targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"].view(-1, 5)), 1)
        rw, rh = targets[:, 4] * imgsz[0].item(), targets[:, 5] * imgsz[1].item()
        targets = targets[(rw >= 2) & (rh >= 2)]  # filter rboxes of tiny size to stabilize training
        targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
        gt_labels, gt_bboxes = targets.split((1, 5), 2)  # cls, xywhr
        mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
    except RuntimeError as e:
        raise TypeError(
            "ERROR ‚ĚĆ OBB dataset incorrectly formatted or not a OBB dataset.\n"
            "This error can occur when incorrectly training a 'OBB' model on a 'detect' dataset, "
            "i.e. 'yolo train model=yolov8n-obb.pt data=dota8.yaml'.\nVerify your dataset is a "
            "correctly formatted 'OBB' dataset using 'data=dota8.yaml' "
            "as an example.\nSee https://docs.ultralytics.com/datasets/obb/ for help."
        ) from e

    # Pboxes
    pred_bboxes = self.bbox_decode(anchor_points, pred_distri, pred_angle)  # xyxy, (b, h*w, 4)

    bboxes_for_assigner = pred_bboxes.clone().detach()
    # Only the first four elements need to be scaled
    bboxes_for_assigner[..., :4] *= stride_tensor
    _, target_bboxes, target_scores, fg_mask, _ = self.assigner(
        pred_scores.detach().sigmoid(),
        bboxes_for_assigner.type(gt_bboxes.dtype),
        anchor_points * stride_tensor,
        gt_labels,
        gt_bboxes,
        mask_gt,
    )

    target_scores_sum = max(target_scores.sum(), 1)

    # Cls loss
    # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way
    loss[1] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum  # BCE

    # Bbox loss
    if fg_mask.sum():
        target_bboxes[..., :4] /= stride_tensor
        loss[0], loss[2] = self.bbox_loss(
            pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask
        )
    else:
        loss[0] += (pred_angle * 0).sum()

    loss[0] *= self.hyp.box  # box gain
    loss[1] *= self.hyp.cls  # cls gain
    loss[2] *= self.hyp.dfl  # dfl gain

    return loss.sum() * batch_size, loss.detach()  # loss(box, cls, dfl)

__init__(model)

Inicializa v8OBBLoss con el modelo, el asignador y la pérdida bbox rotada.

Ten en cuenta que el modelo debe estar desparalizado.

Código fuente en ultralytics/utils/loss.py
def __init__(self, model):
    """
    Initializes v8OBBLoss with model, assigner, and rotated bbox loss.

    Note model must be de-paralleled.
    """
    super().__init__(model)
    self.assigner = RotatedTaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0)
    self.bbox_loss = RotatedBboxLoss(self.reg_max - 1, use_dfl=self.use_dfl).to(self.device)

bbox_decode(anchor_points, pred_dist, pred_angle)

Decodifica las coordenadas del cuadro delimitador del objeto predicho a partir de los puntos de anclaje y la distribución.

Par√°metros:

Nombre Tipo Descripción Por defecto
anchor_points Tensor

Puntos de anclaje, (h*w, 2).

necesario
pred_dist Tensor

Distancia rotada prevista, (bs, h*w, 4).

necesario
pred_angle Tensor

√Āngulo previsto, (bs, h*w, 1).

necesario

Devuelve:

Tipo Descripción
Tensor

Cajas delimitadoras rotadas predichas con √°ngulos, (bs, h*w, 5).

Código fuente en ultralytics/utils/loss.py
def bbox_decode(self, anchor_points, pred_dist, pred_angle):
    """
    Decode predicted object bounding box coordinates from anchor points and distribution.

    Args:
        anchor_points (torch.Tensor): Anchor points, (h*w, 2).
        pred_dist (torch.Tensor): Predicted rotated distance, (bs, h*w, 4).
        pred_angle (torch.Tensor): Predicted angle, (bs, h*w, 1).

    Returns:
        (torch.Tensor): Predicted rotated bounding boxes with angles, (bs, h*w, 5).
    """
    if self.use_dfl:
        b, a, c = pred_dist.shape  # batch, anchors, channels
        pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype))
    return torch.cat((dist2rbox(pred_dist, pred_angle, anchor_points), pred_angle), dim=-1)

preprocess(targets, batch_size, scale_tensor)

Preprocesa los recuentos objetivo y los compara con el tama√Īo del lote de entrada para obtener una salida tensor.

Código fuente en ultralytics/utils/loss.py
def preprocess(self, targets, batch_size, scale_tensor):
    """Preprocesses the target counts and matches with the input batch size to output a tensor."""
    if targets.shape[0] == 0:
        out = torch.zeros(batch_size, 0, 6, device=self.device)
    else:
        i = targets[:, 0]  # image index
        _, counts = i.unique(return_counts=True)
        counts = counts.to(dtype=torch.int32)
        out = torch.zeros(batch_size, counts.max(), 6, device=self.device)
        for j in range(batch_size):
            matches = i == j
            n = matches.sum()
            if n:
                bboxes = targets[matches, 2:]
                bboxes[..., :4].mul_(scale_tensor)
                out[j, :n] = torch.cat([targets[matches, 1:2], bboxes], dim=-1)
    return out





Creado 2023-11-12, Actualizado 2024-05-18
Autores: glenn-jocher (5), Burhan-Q (1), Laughing-q (1)