yolov5增加iou loss(SIoU,EIoU,WIoU),无痛涨点trick

这篇具有很好参考价值的文章主要介绍了yolov5增加iou loss(SIoU,EIoU,WIoU),无痛涨点trick。希望对大家有所帮助。如果存在错误或未考虑完全的地方,请大家不吝赐教,您也可以点击"举报违法"按钮提交疑问。

        yolo无痛涨点trick,简单实用

        先贴一张最近一篇论文的结果

wiou,YOLO,人工智能,深度学习,计算机视觉

后来的几种iou的消融实验结果在一定程度上要优于CIoU。

        本文将在yolov5的基础上增加SIoU,EIoU,Focal-XIoU(X为C,D,G,E,S等)以及AlphaXIoU。

        在yolov5的utils文件夹下新增iou.py文件

import math
import torch


def bbox_iou(box1,
             box2,
             xywh=True,
             GIoU=False,
             DIoU=False,
             CIoU=False,
             SIoU=False,
             EIoU=False,
             WIoU=False,
             Focal=False,
             alpha=1,
             gamma=0.5,
             scale=False,
             monotonous=False,
             eps=1e-7):
    """
    计算bboxes iou
    Args:
        box1: predict bboxes
        box2: target bboxes
        xywh: 将bboxes转换为xyxy的形式
        GIoU: 为True时计算GIoU LOSS (yolov5自带)
        DIoU: 为True时计算DIoU LOSS (yolov5自带)
        CIoU: 为True时计算CIoU LOSS (yolov5自带,默认使用)
        SIoU: 为True时计算SIoU LOSS (新增)
        EIoU: 为True时计算EIoU LOSS (新增)
        WIoU: 为True时计算WIoU LOSS (新增)
        Focal: 为True时,可结合其他的XIoU生成对应的IoU变体,如CIoU=True,Focal=True时为Focal-CIoU
        alpha: AlphaIoU中的alpha参数,默认为1,为1时则为普通的IoU,如果想采用AlphaIoU,论文alpha默认值为3,此时设置CIoU=True则为AlphaCIoU
        gamma: Focal_XIoU中的gamma参数,默认为0.5
        scale: scale为True时,WIoU会乘以一个系数
        monotonous: 3个输入分别代表WIoU的3个版本,None: origin v1, True: monotonic FM v2, False: non-monotonic FM v3
        eps: 防止除0

    Returns:
        iou
    """
    # 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)

    # 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
    if scale:
        wise_scale = WIoU_Scale(1 - (inter / union), monotonous=monotonous)

    # 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
                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
                return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2)  # EIou
            elif SIoU:
                # SIoU Loss https://arxiv.org/pdf/2205.12740.pdf
                s_cw, s_ch = (b2_x1 + b2_x2 - b1_x1 - b1_x2) * 0.5 + eps, (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, sin_alpha_2 = torch.abs(s_cw) / sigma, 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, rho_y = (s_cw / cw) ** 2, (s_ch / ch) ** 2
                gamma = angle_cost - 2
                distance_cost = 2 - torch.exp(gamma * rho_x) - torch.exp(gamma * rho_y)
                omiga_w, omiga_h = torch.abs(w1 - w2) / torch.max(w1, w2), 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
                return iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha)  # SIou
            elif WIoU:
                if scale:
                    return getattr(WIoU_Scale, '_scaled_loss')(wise_scale), (1 - iou) * torch.exp((rho2 / c2)), iou  # WIoU v3 https://arxiv.org/abs/2301.10051
                return iou, torch.exp((rho2 / c2))  # WIoU v1
            if Focal:
                return iou - rho2 / c2, torch.pow(inter / (union + eps), gamma)  # Focal_DIoU
            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
        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
    return iou  # IoU


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.
    _momentum = 1 - pow(0.5, exp=1 / 7000)
    _is_train = True

    def __init__(self, iou, monotonous=False):
        self.iou = iou
        self.monotonous = monotonous
        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

在调用bbox_iou函数的地方做如下修改(主要是__call__中):

class ComputeLoss:
    sort_obj_iou = False

    # Compute losses
    def __init__(self, model, autobalance=False):
        device = next(model.parameters()).device  # get model device
        h = model.hyp  # hyperparameters

        # Define criteria
        BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device))
        BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device))

        # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
        self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0))  # positive, negative BCE targets

        # Focal loss
        g = h['fl_gamma']  # focal loss gamma
        if g > 0:
            BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)

        m = de_parallel(model).model[-1]  # Detect() module
        self.balance = {3: [4.0, 1.0, 0.4]}.get(m.nl, [4.0, 1.0, 0.25, 0.06, 0.02])  # P3-P7
        self.ssi = list(m.stride).index(16) if autobalance else 0  # stride 16 index
        self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance
        self.na = m.na  # number of anchors
        self.nc = m.nc  # number of classes
        self.nl = m.nl  # number of layers
        self.anchors = m.anchors
        self.device = device

    def __call__(self, p, targets):  # predictions, targets
        lcls = torch.zeros(1, device=self.device)  # class loss
        lbox = torch.zeros(1, device=self.device)  # box loss
        lobj = torch.zeros(1, device=self.device)  # object loss
        tcls, tbox, indices, anchors = self.build_targets(p, targets)  # targets

        # Losses
        for i, pi in enumerate(p):  # layer index, layer predictions
            b, a, gj, gi = indices[i]  # image, anchor, gridy, gridx
            tobj = torch.zeros(pi.shape[:4], dtype=pi.dtype, device=self.device)  # target obj

            n = b.shape[0]  # number of targets
            if n:
                # pxy, pwh, _, pcls = pi[b, a, gj, gi].tensor_split((2, 4, 5), dim=1)  # faster, requires torch 1.8.0
                pxy, pwh, _, pcls = pi[b, a, gj, gi].split((2, 2, 1, self.nc), 1)  # target-subset of predictions

                # Regression
                pxy = pxy.sigmoid() * 2 - 0.5
                pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i]
                pbox = torch.cat((pxy, pwh), 1)  # predicted box
                # iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze()  # iou(prediction, target)
                # lbox += (1.0 - iou).mean()  # iou loss
                # //
                iou = bbox_iou(pbox, tbox[i], WIoU=True, scale=True)
                if isinstance(iou, tuple):
                    if len(iou) == 2:
                        lbox += (iou[1].detach().squeeze() * (1 - iou[0].squeeze())).mean()
                        iou = iou[0].squeeze()
                    else:
                        lbox += (iou[0] * iou[1]).mean()
                        iou = iou[2].squeeze()
                else:
                    lbox += (1.0 - iou.squeeze()).mean()  # iou loss
                    iou = iou.squeeze()
                # /

                # Objectness
                iou = iou.detach().clamp(0).type(tobj.dtype)
                if self.sort_obj_iou:
                    j = iou.argsort()
                    b, a, gj, gi, iou = b[j], a[j], gj[j], gi[j], iou[j]
                if self.gr < 1:
                    iou = (1.0 - self.gr) + self.gr * iou
                tobj[b, a, gj, gi] = iou  # iou ratio

                # Classification
                if self.nc > 1:  # cls loss (only if multiple classes)
                    t = torch.full_like(pcls, self.cn, device=self.device)  # targets
                    t[range(n), tcls[i]] = self.cp
                    lcls += self.BCEcls(pcls, t)  # BCE

                # Append targets to text file
                # with open('targets.txt', 'a') as file:
                #     [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]

            obji = self.BCEobj(pi[..., 4], tobj)
            lobj += obji * self.balance[i]  # obj loss
            if self.autobalance:
                self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item()

        if self.autobalance:
            self.balance = [x / self.balance[self.ssi] for x in self.balance]
        lbox *= self.hyp['box']
        lobj *= self.hyp['obj']
        lcls *= self.hyp['cls']
        bs = tobj.shape[0]  # batch size

        return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach()

    def build_targets(self, p, targets):
        # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
        na, nt = self.na, targets.shape[0]  # number of anchors, targets
        tcls, tbox, indices, anch = [], [], [], []
        gain = torch.ones(7, device=self.device)  # normalized to gridspace gain
        ai = torch.arange(na, device=self.device).float().view(na, 1).repeat(1, nt)  # same as .repeat_interleave(nt)
        targets = torch.cat((targets.repeat(na, 1, 1), ai[..., None]), 2)  # append anchor indices

        g = 0.5  # bias
        off = torch.tensor(
            [
                [0, 0],
                [1, 0],
                [0, 1],
                [-1, 0],
                [0, -1],  # j,k,l,m
                # [1, 1], [1, -1], [-1, 1], [-1, -1],  # jk,jm,lk,lm
            ],
            device=self.device).float() * g  # offsets

        for i in range(self.nl):
            anchors, shape = self.anchors[i], p[i].shape
            gain[2:6] = torch.tensor(shape)[[3, 2, 3, 2]]  # xyxy gain

            # Match targets to anchors
            t = targets * gain  # shape(3,n,7)
            if nt:
                # Matches
                r = t[..., 4:6] / anchors[:, None]  # wh ratio
                j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t']  # compare
                # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t']  # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
                t = t[j]  # filter

                # Offsets
                gxy = t[:, 2:4]  # grid xy
                gxi = gain[[2, 3]] - gxy  # inverse
                j, k = ((gxy % 1 < g) & (gxy > 1)).T
                l, m = ((gxi % 1 < g) & (gxi > 1)).T
                j = torch.stack((torch.ones_like(j), j, k, l, m))
                t = t.repeat((5, 1, 1))[j]
                offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
            else:
                t = targets[0]
                offsets = 0

            # Define
            bc, gxy, gwh, a = t.chunk(4, 1)  # (image, class), grid xy, grid wh, anchors
            a, (b, c) = a.long().view(-1), bc.long().T  # anchors, image, class
            gij = (gxy - offsets).long()
            gi, gj = gij.T  # grid indices

            # Append
            indices.append((b, a, gj.clamp_(0, shape[2] - 1), gi.clamp_(0, shape[3] - 1)))  # image, anchor, grid
            tbox.append(torch.cat((gxy - gij, gwh), 1))  # box
            anch.append(anchors[a])  # anchors
            tcls.append(c)  # class

        return tcls, tbox, indices, anch

        注意需要从对应的py文件中import对应的函数,并需要注释原始函数

# from utils.metrics import bbox_iou
from utils.iou import bbox_iou

         如果需要应用对应的IoU loss的变体,即可将Focal设置为True,并将对应的IoU也设置为True,如CIoU=True,Focal=True时为Focal-CIoU,此时可以调整gamma,默认设置为0.5。

        如果想要使用AlphaXIoU,将alpha设置为3同时将对应的IoU也设置为True即可,alpha默认设置为1。

        更新WIoU,monotonous有3个输入分别代表WIoU的3个版本,None: origin v1, True: monotonic FM v2, False: non-monotonic FM v3,同时需要设置scale,scale为True时,WIoU会乘以一个系数,结合monotonous即会对应WIoU的3个版本。

        yolov7的代码结构也是一样的,也可以替换到yolov7中,__call__中的bbox_iou函数要改成yolov5的调用方式(pbox不用矩阵转置(T))。文章来源地址https://www.toymoban.com/news/detail-804589.html

到了这里,关于yolov5增加iou loss(SIoU,EIoU,WIoU),无痛涨点trick的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若转载,请注明出处: 如若内容造成侵权/违法违规/事实不符,请点击违法举报进行投诉反馈,一经查实,立即删除!

领支付宝红包 赞助服务器费用

相关文章

觉得文章有用就打赏一下文章作者

支付宝扫一扫打赏

博客赞助

微信扫一扫打赏

请作者喝杯咖啡吧~博客赞助

支付宝扫一扫领取红包,优惠每天领

二维码1

领取红包

二维码2

领红包