Python mmdet.core.bbox_overlaps() Examples

The following are 15 code examples of mmdet.core.bbox_overlaps(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module mmdet.core , or try the search function .
Example #1
Source File: iou_loss.py    From GCNet with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #2
Source File: iou_loss.py    From mmdetection-annotated with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #3
Source File: iou_loss.py    From PolarMask with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #4
Source File: iou_loss.py    From kaggle-kuzushiji-recognition with MIT License 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #5
Source File: iou_loss.py    From RDSNet with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #6
Source File: iou_loss.py    From IoU-Uniform-R-CNN with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #7
Source File: iou_loss.py    From Libra_R-CNN with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #8
Source File: iou_loss.py    From FoveaBox with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #9
Source File: iou_loss.py    From Cascade-RPN with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, linear=False, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    if linear:
        loss = 1 - ious
    else:
        loss = -ious.log()
    return loss
Example #10
Source File: iou_loss.py    From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #11
Source File: iou_loss.py    From CenterNet with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #12
Source File: linear_iou_loss.py    From CenterNet with Apache License 2.0 6 votes vote down vote up 
def linear_iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = 1 - ious
    return loss
Example #13
Source File: iou_loss.py    From ttfnet with Apache License 2.0 6 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #14
Source File: iou_loss.py    From mmdetection with Apache License 2.0 5 votes vote down vote up 
def iou_loss(pred, target, eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (torch.Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (torch.Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        torch.Tensor: Loss tensor.
    """
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    loss = -ious.log()
    return loss
Example #15
Source File: anchor_head.py    From PolarMask with Apache License 2.0 5 votes vote down vote up 
def loss_single(self, cls_score, bbox_pred, labels, label_weights, level,
                    bbox_targets, bbox_weights, num_total_samples, cfg):

        #generate anchors
        anchors = self.anchor_generators[level].grid_anchors(self.featmap_sizes[level], self.anchor_strides[level])
        anchors = anchors.repeat(2,1)

        # classification loss
        labels = labels.reshape(-1)
        label_weights = label_weights.reshape(-1)
        cls_score = cls_score.permute(0, 2, 3,
                                      1).reshape(-1, self.cls_out_channels)

        # regression loss
        bbox_targets = bbox_targets.reshape(-1, 4)
        bbox_weights = bbox_weights.reshape(-1, 4)
        bbox_pred = bbox_pred.permute(0, 2, 3, 1).reshape(-1, 4)
        if 'is_iou' in cfg.keys() and cfg['is_iou'] == True:
            #get IOU
            bbox = delta2bbox(anchors, bbox_pred, self.target_means, self.target_stds)
            ious = bbox_overlaps(bbox, bbox_targets, is_aligned=True)
            loss_cls = self.loss_cls(
                cls_score, labels, label_weights, avg_factor=num_total_samples,ious=ious)
            loss_bbox = self.loss_bbox(
                bbox_pred,
                bbox_targets,
                bbox_weights,
                avg_factor=num_total_samples)
        else:
            loss_cls = self.loss_cls(
                cls_score, labels, label_weights, avg_factor=num_total_samples)
            loss_bbox = self.loss_bbox(
                bbox_pred,
                bbox_targets,
                bbox_weights,
                avg_factor=num_total_samples)
        return loss_cls, loss_bbox