tfa.losses.giou_loss

View source on GitHub

Args:

tfa.losses.giou_loss(
    y_true,
    y_pred,
    mode='giou'
)

y_true: true targets tensor. The coordinates of the each bounding
    box in boxes are encoded as [y_min, x_min, y_max, x_max].
y_pred: predictions tensor. The coordinates of the each bounding
    box in boxes are encoded as [y_min, x_min, y_max, x_max].
mode: one of ['giou', 'iou'], decided to calculate GIoU or IoU loss.

Returns:

GIoU loss float Tensor.