yolov7-NWD.py

def wasserstein_loss(pred, target, eps=1e-7, constant=12.8):
    r"""`Implementation of paper `Enhancing Geometric Factors into
    Model Learning and Inference for Object Detection and Instance
    Segmentation <https://arxiv.org/abs/2005.03572>`_.
    Code is modified from https://github.com/Zzh-tju/CIoU.
    Args:
        pred (Tensor): Predicted bboxes of format (x_center, y_center, w, h),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).
    Return:
        Tensor: Loss tensor.
    """

    center1 = pred[:, :2]
    center2 = target[:, :2]

    whs = center1[:, :2] - center2[:, :2]

    center_distance = whs[:, 0] * whs[:, 0] + whs[:, 1] * whs[:, 1] + eps #

    w1 = pred[:, 2]  + eps
    h1 = pred[:, 3]  + eps
    w2 = target[:, 2] + eps
    h2 = target[:, 3] + eps

    wh_distance = ((w1 - w2) ** 2 + (h1 - h2) ** 2) / 4

    wasserstein_2 = center_distance + wh_distance
    return torch.exp(-torch.sqrt(wasserstein_2) / constant)

nwd = wasserstein_loss(pbox, tbox[i])
iou_ratio = 0.5
lbox += (1 - iou_ratio) * (1.0 - nwd).mean() + iou_ratio * (1.0 - iou).mean()  # iou loss

# Objectness
iou = (iou.detach() * iou_ratio + nwd.detach() * (1 - iou_ratio)).clamp(0, 1).type(tobj.dtype)