游客jcvfrv6whvf7q_社区达人页_阿里云开发者社区

游客jcvfrv6whvf7q_社区达人页

《一文搞懂IoU发展历程》GIoU、DIoU、CIoU、EIoU、αIoU、SIoU

IoU出现背景目标检测任务的损失函数一般由Classificition Loss（分类损失函数）和Bounding Box Regeression Loss（回归损失函数）两部分构成。因此，更好的定位有利于模型精度的提高。在IoU Loss提出来之前，检测上有关候选框的回归主要是通过坐标的回归损失来优化。但L1 Loss和L2 Loss存在比较大的问题：L1 Loss的问题：损失函数对x的导数为常数，在训练后期，x很小时，如果learning rate 不变，损失函数会在稳定值附近波动，很难收敛到更高的精度。L2 Loss的问题：损失函数对x的导数在x值很大时，其导数也非常大，在训练初期不稳定。而且，基于L1/L2 Loss的坐标回归不具有尺度不变性，且并没有将四个坐标之间的相关性考虑进去。因此，像L1/L2 Loss直接的坐标回归实际上很难描述两框之间的相对位置关系。因此，在ACM2016的论文中提出了IoU loss，它将四个坐标点看成一个整体进行计算，具有尺度不变性（也就是对尺度不敏感）。IoU Loss的定义是先求出预测框和真实框之间的交集和并集之比，再求负对数，但是在实际使用中我们常常将IoU Loss写成1-IoU。如果两个框重合则交并比等于1，Loss为0说明重合度非常高。因此，IoU的取值范围为[0,1]。什么是IoU？IOU的全称为交并比（Intersection over Union），是目标检测中使用的一个概念，IoU计算的是“预测的边框”和“真实的边框”的交叠率，即它们的交集和并集的比值。最理想情况是完全重叠，即比值为1。IoU发展历程虽然IoU Loss虽然解决了Smooth L1系列变量相互独立和不具有尺度不变性的两大问题，但是它也存在两个问题：当预测框和目标框不相交时，即IoU(A,B)=0时，不能反映A,B距离的远近，此时损失函数不可导，IoU Loss 无法优化两个框不相交的情况。如上图三个框，假设预测框和目标框的大小都确定，只要两个框的相交值是确定的，即其IoU值相同时，IoU值不能反映两个框是如何相交的。GIoU（CVPR2019）针对IoU无法反映两个框是如何相交的问题，GIoU通过引入预测框和真实框的最小外接矩形（类似于图像处理中的闭包区域）来获取预测框、真实框在闭包区域中的比重。这样子，GIoU不仅可以关注重叠区域，还可以关注其他非重合区域，能比较好的反映两个框在闭包区域中的相交情况。从公式上来看，GIoU是一种IoU的下界，取值范围[-1,1]。在两者重合的时候取最大值1，在两者无交集且无限远的时候取最小值-1。因此，与IoU相比，GIoU是一个比较好的距离度量指标。DIoU（AAAI2020）虽然GIoU通过引入闭包区域缓解了预测框与真实框相交位置的衡量问题，但其实际上仍存在两个问题：对每个预测框与真实框均要去计算最小外接矩形，计算及收敛速度受到限制当预测框在真实框内部时，GIoU退化为IoU，也无法区分相对位置关系因此，考虑到GIoU的缺点，DIoU在IoU的基础上直接回归两个框中心点的欧式距离，加速了收敛速度。DIoU的惩罚项是基于中心点的距离和对角线距离的比值。这样就避免了GIoU在两框距离较远时产生较大闭包时所造成的Loss值较大而难以优化的情况。CIoU（AAAI2020）虽然DIoU Loss通过中心点回归缓解了两框距离较远时难优化的问题，但DIoU Loss仍存在两框中心点重合，但宽高比不同时，DIoU Loss退化为IoU Loss的问题。因此，为了得到更加精准的预测框，CIoU在DIoU的基础上增加了一个影响因子，即增加了预测框与真实框之间长宽比的一致性的考量。比如上面三种情况，目标框包裹预测框，本来DIoU可以起作用。但预测框的中心点的位置都是一样的，因此按照DIoU的计算公式，三者的值都是相同的。CIoU Loss虽然考虑了边界框回归的重叠面积、中心点距离及长宽比。但是其公式中的v反映的时长宽比的差异，而不是宽高分别与其置信度的真实差异，所以有时会阻碍模型有效的优化。EIoU（arXiv2021）EIoU在CIoU的基础上将长宽比拆开，明确地衡量了三个几何因素的差异，即重叠区域、中心点和边长，同时引入Fcoal loss解决了难易样本不平衡的问题。αIoU（NeurlPS2021）αIoU将现有的基于IoU 的损失进行了一个推广使得αIoU可以显着超越现有的基于 IoU 的损失，通过调节α，使探测器更灵活地实现不同水平的bbox回归精度，并且αIoU对小数据集和噪声的鲁棒性更强SIoU（arXiv2022）传统的目标检测损失函数依赖于边界框回归指标的聚合，例如预测框和真实框（即 GIoU、CIoU、ICIoU 等）的距离、重叠区域和纵横比。然而，迄今为止提出和使用的方法都没有考虑期望的真实框和预测框之间不匹配的方向。这种不足导致收敛速度较慢且效率较低，因为预测框在训练过程中可能会“四处游荡”，最终会产生一个更差的模型。SIoU提出了一种新的损失函数，重新定义了惩罚度量，考虑了期望回归之间的向量夹角。SIoU损失函数由4个成本函数组成Angle costDistance costShape costIoU cost将 SIoU 应用于 COCO-train/COCO-val 与其他损失函数相比，提高了 +2.4% (mAP@0.5:0.95) 和 +3.6%(mAP@0.5)各IoU源代IoUimport numpy as np def Iou(box1, box2, wh=False): if wh == False: xmin1, ymin1, xmax1, ymax1 = box1 xmin2, ymin2, xmax2, ymax2 = box2 else: xmin1, ymin1 = int(box1[0]-box1[2]/2.0), int(box1[1]-box1[3]/2.0) xmax1, ymax1 = int(box1[0]+box1[2]/2.0), int(box1[1]+box1[3]/2.0) xmin2, ymin2 = int(box2[0]-box2[2]/2.0), int(box2[1]-box2[3]/2.0) xmax2, ymax2 = int(box2[0]+box2[2]/2.0), int(box2[1]+box2[3]/2.0) # 获取矩形框交集对应的左上角和右下角的坐标（intersection） xx1 = np.max([xmin1, xmin2]) yy1 = np.max([ymin1, ymin2]) xx2 = np.min([xmax1, xmax2]) yy2 = np.min([ymax1, ymax2]) # 计算两个矩形框面积 area1 = (xmax1-xmin1) * (ymax1-ymin1) area2 = (xmax2-xmin2) * (ymax2-ymin2) inter_area = (np.max([0, xx2-xx1])) * (np.max([0, yy2-yy1]))　#计算交集面积 iou = inter_area / (area1+area2-inter_area+1e-6) 　#计算交并比 return iouGIoUdef Giou(rec1,rec2): #分别是第一个矩形左右上下的坐标 x1,x2,y1,y2 = rec1 x3,x4,y3,y4 = rec2 iou = Iou(rec1,rec2) area_C = (max(x1,x2,x3,x4)-min(x1,x2,x3,x4))*(max(y1,y2,y3,y4)-min(y1,y2,y3,y4)) area_1 = (x2-x1)*(y1-y2) area_2 = (x4-x3)*(y3-y4) sum_area = area_1 + area_2 w1 = x2 - x1 #第一个矩形的宽 w2 = x4 - x3 #第二个矩形的宽 h1 = y1 - y2 h2 = y3 - y4 W = min(x1,x2,x3,x4)+w1+w2-max(x1,x2,x3,x4) #交叉部分的宽 H = min(y1,y2,y3,y4)+h1+h2-max(y1,y2,y3,y4) #交叉部分的高 Area = W*H #交叉的面积 add_area = sum_area - Area #两矩形并集的面积 end_area = (area_C - add_area)/area_C #闭包区域中不属于两个框的区域占闭包区域的比重 giou = iou - end_area return giouDIoUdef Diou(bboxes1, bboxes2): rows = bboxes1.shape[0] cols = bboxes2.shape[0] dious = torch.zeros((rows, cols)) if rows * cols == 0:# return dious exchange = False if bboxes1.shape[0] > bboxes2.shape[0]: bboxes1, bboxes2 = bboxes2, bboxes1 dious = torch.zeros((cols, rows)) exchange = True # #xmin,ymin,xmax,ymax->[:,0],[:,1],[:,2],[:,3] w1 = bboxes1[:, 2] - bboxes1[:, 0] h1 = bboxes1[:, 3] - bboxes1[:, 1] w2 = bboxes2[:, 2] - bboxes2[:, 0] h2 = bboxes2[:, 3] - bboxes2[:, 1] area1 = w1 * h1 area2 = w2 * h2 center_x1 = (bboxes1[:, 2] + bboxes1[:, 0]) / 2 center_y1 = (bboxes1[:, 3] + bboxes1[:, 1]) / 2 center_x2 = (bboxes2[:, 2] + bboxes2[:, 0]) / 2 center_y2 = (bboxes2[:, 3] + bboxes2[:, 1]) / 2 inter_max_xy = torch.min(bboxes1[:, 2:],bboxes2[:, 2:]) inter_min_xy = torch.max(bboxes1[:, :2],bboxes2[:, :2]) out_max_xy = torch.max(bboxes1[:, 2:],bboxes2[:, 2:]) out_min_xy = torch.min(bboxes1[:, :2],bboxes2[:, :2]) inter = torch.clamp((inter_max_xy - inter_min_xy), min=0) inter_area = inter[:, 0] * inter[:, 1] inter_diag = (center_x2 - center_x1)**2 + (center_y2 - center_y1)**2 outer = torch.clamp((out_max_xy - out_min_xy), min=0) outer_diag = (outer[:, 0] ** 2) + (outer[:, 1] ** 2) union = area1+area2-inter_area dious = inter_area / union - (inter_diag) / outer_diag dious = torch.clamp(dious,min=-1.0,max = 1.0) if exchange: dious = dious.T return diousCIoUdef bbox_overlaps_ciou(bboxes1, bboxes2): rows = bboxes1.shape[0] cols = bboxes2.shape[0] cious = torch.zeros((rows, cols)) if rows * cols == 0: return cious exchange = False if bboxes1.shape[0] > bboxes2.shape[0]: bboxes1, bboxes2 = bboxes2, bboxes1 cious = torch.zeros((cols, rows)) exchange = True w1 = bboxes1[:, 2] - bboxes1[:, 0] h1 = bboxes1[:, 3] - bboxes1[:, 1] w2 = bboxes2[:, 2] - bboxes2[:, 0] h2 = bboxes2[:, 3] - bboxes2[:, 1] area1 = w1 * h1 area2 = w2 * h2 center_x1 = (bboxes1[:, 2] + bboxes1[:, 0]) / 2 center_y1 = (bboxes1[:, 3] + bboxes1[:, 1]) / 2 center_x2 = (bboxes2[:, 2] + bboxes2[:, 0]) / 2 center_y2 = (bboxes2[:, 3] + bboxes2[:, 1]) / 2 inter_max_xy = torch.min(bboxes1[:, 2:],bboxes2[:, 2:]) inter_min_xy = torch.max(bboxes1[:, :2],bboxes2[:, :2]) out_max_xy = torch.max(bboxes1[:, 2:],bboxes2[:, 2:]) out_min_xy = torch.min(bboxes1[:, :2],bboxes2[:, :2]) inter = torch.clamp((inter_max_xy - inter_min_xy), min=0) inter_area = inter[:, 0] * inter[:, 1] inter_diag = (center_x2 - center_x1)**2 + (center_y2 - center_y1)**2 outer = torch.clamp((out_max_xy - out_min_xy), min=0) outer_diag = (outer[:, 0] ** 2) + (outer[:, 1] ** 2) union = area1+area2-inter_area u = (inter_diag) / outer_diag iou = inter_area / union with torch.no_grad(): arctan = torch.atan(w2 / h2) - torch.atan(w1 / h1) v = (4 / (math.pi ** 2)) * torch.pow((torch.atan(w2 / h2) - torch.atan(w1 / h1)), 2) S = 1 - iou alpha = v / (S + v) w_temp = 2 * w1 ar = (8 / (math.pi ** 2)) * arctan * ((w1 - w_temp) * h1) cious = iou - (u + alpha * ar) cious = torch.clamp(cious,min=-1.0,max = 1.0) if exchange: cious = cious.T return cious参考文献https://mp.weixin.qq.com/s/jLnde0Xms-99g4z16OE9VQDIoU、CIoU、GIoU、IoU再理解结合代码IoU：《UnitBox: An Advanced Object Detection Network》GIoU：《Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression》D/C IoU：《Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression》EIoU：《Focal and Efficient IOU Loss for Accurate Bounding Box Regression》αIoU：《Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression》SIoU：《SIoU Loss: More Powerful Learning for Bounding Box Regression》

手把手带你Yolov5 (v6.1)添加注意力机制(二)（在C3模块中加入注意力机制）

1.第一版本添加方式介绍1.1 C3SE第一步；要把注意力结构代码放到common.py文件中，以C3SE举例，将这段代码粘贴到common.py文件中class SEBottleneck(nn.Module): # Standard bottleneck def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, ratio=16): # ch_in, ch_out, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c_, c2, 3, 1, g=g) self.add = shortcut and c1 == c2 # self.se=SE(c1,c2,ratio) self.avgpool = nn.AdaptiveAvgPool2d(1) self.l1 = nn.Linear(c1, c1 // ratio, bias=False) self.relu = nn.ReLU(inplace=True) self.l2 = nn.Linear(c1 // ratio, c1, bias=False) self.sig = nn.Sigmoid() def forward(self, x): x1 = self.cv2(self.cv1(x)) b, c, _, _ = x.size() y = self.avgpool(x1).view(b, c) y = self.l1(y) y = self.relu(y) y = self.l2(y) y = self.sig(y) y = y.view(b, c, 1, 1) out = x1 * y.expand_as(x1) # out=self.se(x1)*x1 return x + out if self.add else out class C3SE(C3): # C3 module with SEBottleneck() def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): super().__init__(c1, c2, n, shortcut, g, e) c_ = int(c2 * e) # hidden channels self.m = nn.Sequential(*(SEBottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) 第二步；找到yolo.py文件里的parse_model函数，将类名加入进去第三步；修改配置文件（我这里拿yolov5s.yaml举例子），将C3层替换为我们新引入的C3SE层yolov5s_C3SE.yaml# YOLOv5 🚀 by Ultralytics, GPL-3.0 license # Parameters nc: 80 # number of classes depth_multiple: 0.33 # model depth multiple width_multiple: 0.50 # layer channel multiple anchors: - [10,13, 16,30, 33,23] # P3/8 - [30,61, 62,45, 59,119] # P4/16 - [116,90, 156,198, 373,326] # P5/32 # YOLOv5 v6.0 backbone backbone: # [from, number, module, args] [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 [-1, 3, C3SE, [128]], [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 [-1, 6, C3SE, [256]], [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 [-1, 9, C3SE, [512]], [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 [-1, 3, C3SE, [1024]], [-1, 1, SPPF, [1024, 5]], # 9 ] # YOLOv5 v6.0 head head: [[-1, 1, Conv, [512, 1, 1]], [-1, 1, nn.Upsample, [None, 2, 'nearest']], [[-1, 6], 1, Concat, [1]], # cat backbone P4 [-1, 3, C3, [512, False]], # 13 [-1, 1, Conv, [256, 1, 1]], [-1, 1, nn.Upsample, [None, 2, 'nearest']], [[-1, 4], 1, Concat, [1]], # cat backbone P3 [-1, 3, C3, [256, False]], # 17 (P3/8-small) [-1, 1, Conv, [256, 3, 2]], [[-1, 14], 1, Concat, [1]], # cat head P4 [-1, 3, C3, [512, False]], # 20 (P4/16-medium) [-1, 1, Conv, [512, 3, 2]], [[-1, 10], 1, Concat, [1]], # cat head P5 [-1, 3, C3, [1024, False]], # 23 (P5/32-large) [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) ]其它注意力机制同理1.2 C3CAclass CABottleneck(nn.Module): # Standard bottleneck def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, ratio=32): # ch_in, ch_out, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c_, c2, 3, 1, g=g) self.add = shortcut and c1 == c2 # self.ca=CoordAtt(c1,c2,ratio) self.pool_h = nn.AdaptiveAvgPool2d((None, 1)) self.pool_w = nn.AdaptiveAvgPool2d((1, None)) mip = max(8, c1 // ratio) self.conv1 = nn.Conv2d(c1, mip, kernel_size=1, stride=1, padding=0) self.bn1 = nn.BatchNorm2d(mip) self.act = h_swish() self.conv_h = nn.Conv2d(mip, c2, kernel_size=1, stride=1, padding=0) self.conv_w = nn.Conv2d(mip, c2, kernel_size=1, stride=1, padding=0) def forward(self, x): x1=self.cv2(self.cv1(x)) n, c, h, w = x.size() # c*1*W x_h = self.pool_h(x1) # c*H*1 # C*1*h x_w = self.pool_w(x1).permute(0, 1, 3, 2) y = torch.cat([x_h, x_w], dim=2) # C*1*(h+w) y = self.conv1(y) y = self.bn1(y) y = self.act(y) x_h, x_w = torch.split(y, [h, w], dim=2) x_w = x_w.permute(0, 1, 3, 2) a_h = self.conv_h(x_h).sigmoid() a_w = self.conv_w(x_w).sigmoid() out = x1 * a_w * a_h # out=self.ca(x1)*x1 return x + out if self.add else out class C3CA(C3): # C3 module with CABottleneck() def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): super().__init__(c1, c2, n, shortcut, g, e) c_ = int(c2 * e) # hidden channels self.m = nn.Sequential(*(CABottleneck(c_, c_,shortcut, g, e=1.0) for _ in range(n)))1.3 C3CBAMclass CBAMBottleneck(nn.Module): # Standard bottleneck def __init__(self, c1, c2, shortcut=True, g=1, e=0.5,ratio=16,kernel_size=7): # ch_in, ch_out, shortcut, groups, expansion super(CBAMBottleneck,self).__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c_, c2, 3, 1, g=g) self.add = shortcut and c1 == c2 self.channel_attention = ChannelAttention(c2, ratio) self.spatial_attention = SpatialAttention(kernel_size) #self.cbam=CBAM(c1,c2,ratio,kernel_size) def forward(self, x): x1 = self.cv2(self.cv1(x)) out = self.channel_attention(x1) * x1 # print('outchannels:{}'.format(out.shape)) out = self.spatial_attention(out) * out return x + out if self.add else out class C3CBAM(C3): # C3 module with CBAMBottleneck() def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): super().__init__(c1, c2, n, shortcut, g, e) c_ = int(c2 * e) # hidden channels self.m = nn.Sequential(*(CBAMBottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))1.4 C3ECAclass ECABottleneck(nn.Module): # Standard bottleneck def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, ratio=16, k_size=3): # ch_in, ch_out, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c_, c2, 3, 1, g=g) self.add = shortcut and c1 == c2 # self.eca=ECA(c1,c2) self.avg_pool = nn.AdaptiveAvgPool2d(1) self.conv = nn.Conv1d(1, 1, kernel_size=k_size, padding=(k_size - 1) // 2, bias=False) self.sigmoid = nn.Sigmoid() def forward(self, x): x1 = self.cv2(self.cv1(x)) # out=self.eca(x1)*x1 y = self.avg_pool(x1) y = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1) y = self.sigmoid(y) out = x1 * y.expand_as(x1) return x + out if self.add else out class C3ECA(C3): # C3 module with ECABottleneck() def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): super().__init__(c1, c2, n, shortcut, g, e) c_ = int(c2 * e) # hidden channels self.m = nn.Sequential(*(ECABottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))2.第二版本添加方式介绍2.1 C3_SE_Attentionclass C3_SE_Attention(nn.Module): # CSP Bottleneck with 3 convolutions def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c1, c_, 1, 1) self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2) self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) self._SE = SE(c2, c2) def forward(self, x): return self._SE(self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1)))2.2 C3_ECA_Attentionclass C3_ECA_Attention(nn.Module): # CSP Bottleneck with 3 convolutions def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c1, c_, 1, 1) self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2) self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) self._ECA = ECA(c2, c2) def forward(self, x): return self._ECA(self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1)))2.3 C3_CBAM_Attentionclass C3_CBAM_Attention(nn.Module): # CSP Bottleneck with 3 convolutions def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c1, c_, 1, 1) self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2) self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) self._CBAM = CBAM(c2, c2) def forward(self, x): return self._CBAM(self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1)))2.4 C3_CoorAtt_Attentionclass C3_CoordAtt_Attention(nn.Module): # CSP Bottleneck with 3 convolutions def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c1, c_, 1, 1) self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2) self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) self._CoordAtt = CoordAtt(c2, c2) def forward(self, x): return self._CoordAtt(self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1)))第二版配置文件：# YOLOv5 🚀 by Ultralytics, GPL-3.0 license # Parameters nc: 80 # number of classes depth_multiple: 0.33 # model depth multiple width_multiple: 0.50 # layer channel multiple anchors: - [10,13, 16,30, 33,23] # P3/8 - [30,61, 62,45, 59,119] # P4/16 - [116,90, 156,198, 373,326] # P5/32 # YOLOv5 v6.0 backbone backbone: # [from, number, module, args] [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 [-1, 3, C3_CoorAtt_Attention, [128]], #可替换为C3_SE_Attention/C3_ECA_Attention/C3_CABAM_Attention [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 [-1, 6, C3_CoorAtt_Attention, [256]], #可替换为C3_SE_Attention/C3_ECA_Attention/C3_CABAM_Attention [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 [-1, 9, C3_CoorAtt_Attention, [512]], #可替换为C3_SE_Attention/C3_ECA_Attention/C3_CABAM_Attention [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 [-1, 3, C3_CoorAtt_Attention, [1024]], #可替换为C3_SE_Attention/C3_ECA_Attention/C3_CABAM_Attention [-1, 1, SPPF, [1024, 5]], # 9 ] # YOLOv5 v6.0 head head: [[-1, 1, Conv, [512, 1, 1]], [-1, 1, nn.Upsample, [None, 2, 'nearest']], [[-1, 6], 1, Concat, [1]], # cat backbone P4 [-1, 3, C3, [512, False]], # 13 [-1, 1, Conv, [256, 1, 1]], [-1, 1, nn.Upsample, [None, 2, 'nearest']], [[-1, 4], 1, Concat, [1]], # cat backbone P3 [-1, 3, C3, [256, False]], # 17 (P3/8-small) [-1, 1, Conv, [256, 3, 2]], [[-1, 14], 1, Concat, [1]], # cat head P4 [-1, 3, C3, [512, False]], # 20 (P4/16-medium) [-1, 1, Conv, [512, 3, 2]], [[-1, 10], 1, Concat, [1]], # cat head P5 [-1, 3, C3, [1024, False]], # 23 (P5/32-large) [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) ]有问题欢迎大家指正，如果感觉有帮助的话请点赞支持下👍📖🌟