YOLOv11改进 | 损失函数改进篇 | 2024最新高质量的目标检测边界框回归损失Unified-IoU、FocalUIoU、FocalInvUIoU（设置动态epoch参数）

import numpy as np
import torch, math
 
 
class WIoU_Scale:
    ''' monotonous: {
            None: origin v1
            True: monotonic FM v2
            False: non-monotonic FM v3
        }
        momentum: The momentum of running mean'''
 
    iou_mean = 1.
    monotonous = False
    _momentum = 1 - 0.5 ** (1 / 7000)
    _is_train = True
 
    def __init__(self, iou):
        self.iou = iou
        self._update(self)
 
    @classmethod
    def _update(cls, self):
        if cls._is_train: cls.iou_mean = (1 - cls._momentum) * cls.iou_mean + \
                                         cls._momentum * self.iou.detach().mean().item()
 
    @classmethod
    def _scaled_loss(cls, self, gamma=1.9, delta=3):
        if isinstance(self.monotonous, bool):
            if self.monotonous:
                return (self.iou.detach() / self.iou_mean).sqrt()
            else:
                beta = self.iou.detach() / self.iou_mean
                alpha = delta * torch.pow(gamma, beta - delta)
                return beta / alpha
        return 1
 
 
def bbox_iou(box1, box2, epoch=1, xywh=True, GIoU=False, DIoU=False, CIoU=False, SIoU=False, EIoU=False, WIoU=False,
             UIoU=False, Focal=False, alpha=1, gamma=0.5, scale=False, eps=1e-7):
    # Returns Intersection over Union (IoU) of box1(1,4) to box2(n,4)
 
    # Get the coordinates of bounding boxes
    if xywh:  # transform from xywh to xyxy
        (x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, -1), box2.chunk(4, -1)
        w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2
        b1_x1, b1_x2, b1_y1, b1_y2 = x1 - w1_, x1 + w1_, y1 - h1_, y1 + h1_
        b2_x1, b2_x2, b2_y1, b2_y2 = x2 - w2_, x2 + w2_, y2 - h2_, y2 + h2_
    else:  # x1, y1, x2, y2 = box1
        b1_x1, b1_y1, b1_x2, b1_y2 = box1.chunk(4, -1)
        b2_x1, b2_y1, b2_x2, b2_y2 = box2.chunk(4, -1)
        w1, h1 = b1_x2 - b1_x1, (b1_y2 - b1_y1).clamp(eps)
        w2, h2 = b2_x2 - b2_x1, (b2_y2 - b2_y1).clamp(eps)
 
    # ----------------------------------------------------------------------------------------------------------------
    # UIoU
    if UIoU:
        # define the center point for scaling
        epoch = epoch + 1
        bb1_xc = x1
        bb1_yc = y1
        bb2_xc = x2
        bb2_yc = y2
        # attenuation mode of hyperparameter "ratio"
        linear = True
        cosine = False
        fraction = False
        # assuming that the total training epochs are 300, the "ratio" changes from 2 to 0.5
        if linear:
            ratio = -0.005 * epoch + 2
        elif cosine:
            ratio = 0.75 * math.cos(math.pi * epoch / 300) + 1.25
        elif fraction:
            ratio = 200 / (epoch + 100)
        else:
            ratio = 0.5
        ww1, hh1, ww2, hh2 = w1 * ratio, h1 * ratio, w2 * ratio, h2 * ratio
        bb1_x1, bb1_x2, bb1_y1, bb1_y2 = bb1_xc - (ww1 / 2), bb1_xc + (ww1 / 2), bb1_yc - (hh1 / 2), bb1_yc + (hh1 / 2)
        bb2_x1, bb2_x2, bb2_y1, bb2_y2 = bb2_xc - (ww2 / 2), bb2_xc + (ww2 / 2), bb2_yc - (hh2 / 2), bb2_yc + (hh2 / 2)
        # assign the value back to facilitate subsequent calls
        w1, h1, w2, h2 = ww1, hh1, ww2, hh2
        b1_x1, b1_x2, b1_y1, b1_y2 = bb1_x1, bb1_x2, bb1_y1, bb1_y2
        b2_x1, b2_x2, b2_y1, b2_y2 = bb2_x1, bb2_x2, bb2_y1, bb2_y2
        # print(epoch)
        CIoU = True
    # ---------------------------------------------------------------------------------------------------------------
 
    # Intersection area
    inter = (b1_x2.minimum(b2_x2) - b1_x1.maximum(b2_x1)).clamp(0) * \
            (b1_y2.minimum(b2_y2) - b1_y1.maximum(b2_y1)).clamp(0)
 
    # Union Area
    union = w1 * h1 + w2 * h2 - inter + eps
 
    # WIoU needs to set scale to "True"
    if scale:
        self = WIoU_Scale(1 - (inter / union))
 
    # IoU
    # iou = inter / union # ori iou
    iou = torch.pow(inter / (union + eps), alpha)  # alpha iou
    if CIoU or DIoU or GIoU or EIoU or SIoU or WIoU:
        cw = b1_x2.maximum(b2_x2) - b1_x1.minimum(b2_x1)  # convex (smallest enclosing box) width
        ch = b1_y2.maximum(b2_y2) - b1_y1.minimum(b2_y1)  # convex height
        if CIoU or DIoU or EIoU or SIoU or WIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
            c2 = (cw ** 2 + ch ** 2) ** alpha + eps  # convex diagonal squared
            rho2 = (((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (
                    b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4) ** alpha  # center dist ** 2
            if CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
                v = (4 / math.pi ** 2) * (torch.atan(w2 / h2) - torch.atan(w1 / h1)).pow(2)
                with torch.no_grad():
                    alpha_ciou = v / (v - iou + (1 + eps))
                if Focal:
                    return iou - (rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha)), torch.pow(inter / (union + eps),
                                                                                                 gamma)  # Focal_CIoU
                else:
                    return iou - (rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha))  # CIoU
            elif EIoU:
                rho_w2 = ((b2_x2 - b2_x1) - (b1_x2 - b1_x1)) ** 2
                rho_h2 = ((b2_y2 - b2_y1) - (b1_y2 - b1_y1)) ** 2
                cw2 = torch.pow(cw ** 2 + eps, alpha)
                ch2 = torch.pow(ch ** 2 + eps, alpha)
                if Focal:
                    return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2), torch.pow(inter / (union + eps),
                                                                                      gamma)  # Focal_EIou
                else:
                    return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2)  # EIou
            elif SIoU:
                # SIoU Loss https://arxiv.org/pdf/2205.12740.pdf
                s_cw = (b2_x1 + b2_x2 - b1_x1 - b1_x2) * 0.5 + eps
                s_ch = (b2_y1 + b2_y2 - b1_y1 - b1_y2) * 0.5 + eps
                sigma = torch.pow(s_cw ** 2 + s_ch ** 2, 0.5)
                sin_alpha_1 = torch.abs(s_cw) / sigma
                sin_alpha_2 = torch.abs(s_ch) / sigma
                threshold = pow(2, 0.5) / 2
                sin_alpha = torch.where(sin_alpha_1 > threshold, sin_alpha_2, sin_alpha_1)
                angle_cost = torch.cos(torch.arcsin(sin_alpha) * 2 - math.pi / 2)
                rho_x = (s_cw / cw) ** 2
                rho_y = (s_ch / ch) ** 2
                gamma = angle_cost - 2
                distance_cost = 2 - torch.exp(gamma * rho_x) - torch.exp(gamma * rho_y)
                omiga_w = torch.abs(w1 - w2) / torch.max(w1, w2)
                omiga_h = torch.abs(h1 - h2) / torch.max(h1, h2)
                shape_cost = torch.pow(1 - torch.exp(-1 * omiga_w), 4) + torch.pow(1 - torch.exp(-1 * omiga_h), 4)
                if Focal:
                    return iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha), torch.pow(
                        inter / (union + eps), gamma)  # Focal_SIou
                else:
                    return iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha)  # SIou
            elif WIoU:
                if Focal:
                    raise RuntimeError("WIoU do not support Focal.")
                elif scale:
                    return getattr(WIoU_Scale, '_scaled_loss')(self), (1 - iou) * torch.exp(
                        (rho2 / c2)), iou  # WIoU https://arxiv.org/abs/2301.10051
                else:
                    return iou, torch.exp((rho2 / c2))  # WIoU v1
            if Focal:
                return iou - rho2 / c2, torch.pow(inter / (union + eps), gamma)  # Focal_DIoU
            else:
                return iou - rho2 / c2  # DIoU
        c_area = cw * ch + eps  # convex area
        if Focal:
            return iou - torch.pow((c_area - union) / c_area + eps, alpha), torch.pow(inter / (union + eps),
                                                                                      gamma)  # Focal_GIoU https://arxiv.org/pdf/1902.09630.pdf
        else:
            return iou - torch.pow((c_area - union) / c_area + eps, alpha)  # GIoU https://arxiv.org/pdf/1902.09630.pdf
    if Focal:
        return iou, torch.pow(inter / (union + eps), gamma)  # Focal_IoU
    else:
        return iou  # IoU

    def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask, epoch):
        """IoU loss."""
        weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1)
        iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=True, epoch=epoch, CIoU=False, UIoU=True, Focal=False)
        # UIoU设置为True则代码使用UIoU, Focal同时设置为True 则设置的是FocalUIoU
        if type(iou) is tuple:
            if len(iou) == 2:
                # increased the weight of low/high IoU
                loss_iou = ((1 - iou[1].detach().squeeze()) * (1 - iou[0].squeeze()) * weight).sum() / target_scores_sum  # Focal
                # lbox += (iou[1].detach().squeeze() * (1 - iou[0].squeeze())* weight).sum() / target_scores_sum  # Focal-inv
                # 这里有两种方法，大家可以自行尝试,这里的Focal-inv也是文章中提出的.
            else:
                loss_iou = (iou[0] * iou[1] * weight).sum() / target_scores_sum
        else:
            loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum # iou loss
 
        # DFL loss
        if self.dfl_loss:
            target_ltrb = bbox2dist(anchor_points, target_bboxes, self.dfl_loss.reg_max - 1)
            loss_dfl = self.dfl_loss(pred_dist[fg_mask].view(-1, self.dfl_loss.reg_max), 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