自己做网赌网站,重庆建筑公司排名,网页转发到WordPress,学网页设计哪个培训学校好一、本文介绍
本文给大家带来的改进机制是利用今年新推出的AFPN#xff08;渐近特征金字塔网络#xff09;来优化检测头#xff0c;AFPN的核心思想是通过引入一种渐近的特征融合策略#xff0c;将底层、高层和顶层的特征逐渐整合到目标检测过程中。这种渐近融合方式有助于…一、本文介绍
本文给大家带来的改进机制是利用今年新推出的AFPN渐近特征金字塔网络来优化检测头AFPN的核心思想是通过引入一种渐近的特征融合策略将底层、高层和顶层的特征逐渐整合到目标检测过程中。这种渐近融合方式有助于减小不同层次特征之间的语义差距提高特征融合效果使得检测模型能更好地适应不同层次的语义信息。本文在AFPN的结构基础上为了适配YOLOv8改进AFPN结构同时将AFPN融合到YOLOv8中(因为AFPN需要四个检测头我们只有三个下一篇文章我会出YOLOv8适配AFPN增加小目标检测头)实现暴力涨点。
推荐指数⭐⭐⭐⭐
打星原因为什么打四颗星是因为我觉得这个机制的计算量会上涨这是扣分点同时替换这个检测头刚开始前20个epochs的效果不好随着轮次的增加涨幅才能体现出来这也是扣分点我给结构打分完全是客观的并不是我推出的结构必须满分。 专栏回顾YOLOv8改进系列专栏——本专栏持续复习各种顶会内容——科研必备 训练结果对比图- 这次试验我用的数据集大概有七八百张照片训练了150个epochs虽然没有完全拟合但是效果有一定的涨点幅度所以大家可以进行尝试毕竟不同的数据集上效果也可能差很多同时我在后面给了多种yaml文件大家可以分别进行实验来检验效果。 目录
一、本文介绍
二、AFPN基本框架原理编辑
2.1 AFPN的基本原理
三、Detect_AFPN完整代码
四、手把手教你添加Detect_AFPN检测头
4.1 修改一
4.2 修改二
4.3 修改三
4.4 修改四
4.5 修改五
4.6 修改六
4.7 修改七
4.8 修改八
4.9 修改九
五、Detect_AFPN检测头的yaml文件
六、完美运行记录
七、本文总结 二、AFPN基本框架原理
论文地址官方论文地址
代码地址官方代码地址 2.1 AFPN的基本原理
AFPN的核心思想是通过引入一种渐近的特征融合策略将底层、高层和顶层的特征逐渐整合到目标检测过程中。这种渐近融合方式有助于减小不同层次特征之间的语义差距提高特征融合效果使得检测模型能更好地适应不同层次的语义信息。
主要改进机制1. 底层特征融合 AFPN通过引入底层特征的逐步融合首先融合底层特征接着深层特征最后整合顶层特征。这种层级融合的方式有助于更好地利用不同层次的语义信息提高检测性能。
2. 自适应空间融合 引入自适应空间融合机制ASFF在多级特征融合过程中引入变化的空间权重加强关键级别的重要性同时抑制来自不同对象的矛盾信息的影响。这有助于提高检测性能尤其在处理矛盾信息时更为有效。
3. 底层特征对齐 AFPN采用渐近融合的思想使得不同层次的特征在融合过程中逐渐接近减小它们之间的语义差距。通过底层特征的逐步整合提高了特征融合的效果使得模型更能理解和利用不同层次的信息。
个人总结AFPN的灵感就像是搭积木一样它不是一下子把所有的积木都放到一起而是逐步地将不同层次的积木慢慢整合在一起。这样一来我们可以更好地理解和利用每一层次的积木从而构建一个更牢固的目标检测系统。同时引入了一种智能的机制能够根据不同情况调整注意力更好地处理矛盾信息。 上面上AFPN的网络结构可以看出从Backbone中提取出特征之后将特征输入到AFPN中进行处理然后它可以获得不同层级的特征进行融合这也是它的主要思想质疑同时将结果输入到检测头中进行预测。
(需要注意的是本文砍掉了最下面那一条线适应YOLOv8因为我们是三个检测头下一篇文章我会出增加小目标检测头的然后四个头的yolov8改进从而适应AFPN的结构)。 三、Detect_AFPN完整代码
这里代码是我对于2023年新提出的AFPN进行了修改然后适配YOLOv8的整体结构提出的检测头本来该结构是四个检测头部分但是我去除掉了一个从而适配yolov8当然在我也在出一篇文章里会用到四头的增加辅助训练头针对小目标检测讲解(要不然一个博客放不下 这么多代码)。
import math
from collections import OrderedDict
import torch
import torch.nn as nn
import torch.nn.functional as F
from ultralytics.nn.modules import DFL
from ultralytics.nn.modules.conv import Conv
from ultralytics.utils.tal import dist2bbox, make_anchors__all__ [Detect_AFPN]def BasicConv(filter_in, filter_out, kernel_size, stride1, padNone):if not pad:pad (kernel_size - 1) // 2 if kernel_size else 0else:pad padreturn nn.Sequential(OrderedDict([(conv, nn.Conv2d(filter_in, filter_out, kernel_sizekernel_size, stridestride, paddingpad, biasFalse)),(bn, nn.BatchNorm2d(filter_out)),(relu, nn.ReLU(inplaceTrue)),]))class BasicBlock(nn.Module):expansion 1def __init__(self, filter_in, filter_out):super(BasicBlock, self).__init__()self.conv1 nn.Conv2d(filter_in, filter_out, 3, padding1)self.bn1 nn.BatchNorm2d(filter_out, momentum0.1)self.relu nn.ReLU(inplaceTrue)self.conv2 nn.Conv2d(filter_out, filter_out, 3, padding1)self.bn2 nn.BatchNorm2d(filter_out, momentum0.1)def forward(self, x):residual xout self.conv1(x)out self.bn1(out)out self.relu(out)out self.conv2(out)out self.bn2(out)out residualout self.relu(out)return outclass Upsample(nn.Module):def __init__(self, in_channels, out_channels, scale_factor2):super(Upsample, self).__init__()self.upsample nn.Sequential(BasicConv(in_channels, out_channels, 1),nn.Upsample(scale_factorscale_factor, modebilinear))def forward(self, x):x self.upsample(x)return xclass Downsample_x2(nn.Module):def __init__(self, in_channels, out_channels):super(Downsample_x2, self).__init__()self.downsample nn.Sequential(BasicConv(in_channels, out_channels, 2, 2, 0))def forward(self, x, ):x self.downsample(x)return xclass Downsample_x4(nn.Module):def __init__(self, in_channels, out_channels):super(Downsample_x4, self).__init__()self.downsample nn.Sequential(BasicConv(in_channels, out_channels, 4, 4, 0))def forward(self, x, ):x self.downsample(x)return xclass Downsample_x8(nn.Module):def __init__(self, in_channels, out_channels):super(Downsample_x8, self).__init__()self.downsample nn.Sequential(BasicConv(in_channels, out_channels, 8, 8, 0))def forward(self, x, ):x self.downsample(x)return xclass ASFF_2(nn.Module):def __init__(self, inter_dim512):super(ASFF_2, self).__init__()self.inter_dim inter_dimcompress_c 8self.weight_level_1 BasicConv(self.inter_dim, compress_c, 1, 1)self.weight_level_2 BasicConv(self.inter_dim, compress_c, 1, 1)self.weight_levels nn.Conv2d(compress_c * 2, 2, kernel_size1, stride1, padding0)self.conv BasicConv(self.inter_dim, self.inter_dim, 3, 1)def forward(self, input1, input2):level_1_weight_v self.weight_level_1(input1)level_2_weight_v self.weight_level_2(input2)levels_weight_v torch.cat((level_1_weight_v, level_2_weight_v), 1)levels_weight self.weight_levels(levels_weight_v)levels_weight F.softmax(levels_weight, dim1)fused_out_reduced input1 * levels_weight[:, 0:1, :, :] \input2 * levels_weight[:, 1:2, :, :]out self.conv(fused_out_reduced)return outclass ASFF_3(nn.Module):def __init__(self, inter_dim512):super(ASFF_3, self).__init__()self.inter_dim inter_dimcompress_c 8self.weight_level_1 BasicConv(self.inter_dim, compress_c, 1, 1)self.weight_level_2 BasicConv(self.inter_dim, compress_c, 1, 1)self.weight_level_3 BasicConv(self.inter_dim, compress_c, 1, 1)self.weight_levels nn.Conv2d(compress_c * 3, 3, kernel_size1, stride1, padding0)self.conv BasicConv(self.inter_dim, self.inter_dim, 3, 1)def forward(self, input1, input2, input3):level_1_weight_v self.weight_level_1(input1)level_2_weight_v self.weight_level_2(input2)level_3_weight_v self.weight_level_3(input3)levels_weight_v torch.cat((level_1_weight_v, level_2_weight_v, level_3_weight_v), 1)levels_weight self.weight_levels(levels_weight_v)levels_weight F.softmax(levels_weight, dim1)fused_out_reduced input1 * levels_weight[:, 0:1, :, :] \input2 * levels_weight[:, 1:2, :, :] \input3 * levels_weight[:, 2:, :, :]out self.conv(fused_out_reduced)return outclass ASFF_4(nn.Module):def __init__(self, inter_dim512):super(ASFF_4, self).__init__()self.inter_dim inter_dimcompress_c 8self.weight_level_0 BasicConv(self.inter_dim, compress_c, 1, 1)self.weight_level_1 BasicConv(self.inter_dim, compress_c, 1, 1)self.weight_level_2 BasicConv(self.inter_dim, compress_c, 1, 1)self.weight_levels nn.Conv2d(compress_c * 3, 3, kernel_size1, stride1, padding0)self.conv BasicConv(self.inter_dim, self.inter_dim, 3, 1)def forward(self, input0, input1, input2):level_0_weight_v self.weight_level_0(input0)level_1_weight_v self.weight_level_1(input1)level_2_weight_v self.weight_level_2(input2)levels_weight_v torch.cat((level_0_weight_v, level_1_weight_v, level_2_weight_v), 1)levels_weight self.weight_levels(levels_weight_v)levels_weight F.softmax(levels_weight, dim1)fused_out_reduced input0 * levels_weight[:, 0:1, :, :] \input1 * levels_weight[:, 1:2, :, :] \input2 * levels_weight[:, 2:3, :, :]out self.conv(fused_out_reduced)return outclass BlockBody(nn.Module):def __init__(self, channels[64, 128, 256, 512]):super(BlockBody, self).__init__()self.blocks_scalezero1 nn.Sequential(BasicConv(channels[0], channels[0], 1),)self.blocks_scaleone1 nn.Sequential(BasicConv(channels[1], channels[1], 1),)self.blocks_scaletwo1 nn.Sequential(BasicConv(channels[2], channels[2], 1),)self.downsample_scalezero1_2 Downsample_x2(channels[0], channels[1])self.upsample_scaleone1_2 Upsample(channels[1], channels[0], scale_factor2)self.asff_scalezero1 ASFF_2(inter_dimchannels[0])self.asff_scaleone1 ASFF_2(inter_dimchannels[1])self.blocks_scalezero2 nn.Sequential(BasicBlock(channels[0], channels[0]),BasicBlock(channels[0], channels[0]),BasicBlock(channels[0], channels[0]),BasicBlock(channels[0], channels[0]),)self.blocks_scaleone2 nn.Sequential(BasicBlock(channels[1], channels[1]),BasicBlock(channels[1], channels[1]),BasicBlock(channels[1], channels[1]),BasicBlock(channels[1], channels[1]),)self.downsample_scalezero2_2 Downsample_x2(channels[0], channels[1])self.downsample_scalezero2_4 Downsample_x4(channels[0], channels[2])self.downsample_scaleone2_2 Downsample_x2(channels[1], channels[2])self.upsample_scaleone2_2 Upsample(channels[1], channels[0], scale_factor2)self.upsample_scaletwo2_2 Upsample(channels[2], channels[1], scale_factor2)self.upsample_scaletwo2_4 Upsample(channels[2], channels[0], scale_factor4)self.asff_scalezero2 ASFF_3(inter_dimchannels[0])self.asff_scaleone2 ASFF_3(inter_dimchannels[1])self.asff_scaletwo2 ASFF_3(inter_dimchannels[2])self.blocks_scalezero3 nn.Sequential(BasicBlock(channels[0], channels[0]),BasicBlock(channels[0], channels[0]),BasicBlock(channels[0], channels[0]),BasicBlock(channels[0], channels[0]),)self.blocks_scaleone3 nn.Sequential(BasicBlock(channels[1], channels[1]),BasicBlock(channels[1], channels[1]),BasicBlock(channels[1], channels[1]),BasicBlock(channels[1], channels[1]),)self.blocks_scaletwo3 nn.Sequential(BasicBlock(channels[2], channels[2]),BasicBlock(channels[2], channels[2]),BasicBlock(channels[2], channels[2]),BasicBlock(channels[2], channels[2]),)self.downsample_scalezero3_2 Downsample_x2(channels[0], channels[1])self.downsample_scalezero3_4 Downsample_x4(channels[0], channels[2])self.upsample_scaleone3_2 Upsample(channels[1], channels[0], scale_factor2)self.downsample_scaleone3_2 Downsample_x2(channels[1], channels[2])self.upsample_scaletwo3_4 Upsample(channels[2], channels[0], scale_factor4)self.upsample_scaletwo3_2 Upsample(channels[2], channels[1], scale_factor2)self.asff_scalezero3 ASFF_4(inter_dimchannels[0])self.asff_scaleone3 ASFF_4(inter_dimchannels[1])self.asff_scaletwo3 ASFF_4(inter_dimchannels[2])self.blocks_scalezero4 nn.Sequential(BasicBlock(channels[0], channels[0]),BasicBlock(channels[0], channels[0]),BasicBlock(channels[0], channels[0]),BasicBlock(channels[0], channels[0]),)self.blocks_scaleone4 nn.Sequential(BasicBlock(channels[1], channels[1]),BasicBlock(channels[1], channels[1]),BasicBlock(channels[1], channels[1]),BasicBlock(channels[1], channels[1]),)self.blocks_scaletwo4 nn.Sequential(BasicBlock(channels[2], channels[2]),BasicBlock(channels[2], channels[2]),BasicBlock(channels[2], channels[2]),BasicBlock(channels[2], channels[2]),)def forward(self, x):x0, x1, x2 xx0 self.blocks_scalezero1(x0)x1 self.blocks_scaleone1(x1)x2 self.blocks_scaletwo1(x2)scalezero self.asff_scalezero1(x0, self.upsample_scaleone1_2(x1))scaleone self.asff_scaleone1(self.downsample_scalezero1_2(x0), x1)x0 self.blocks_scalezero2(scalezero)x1 self.blocks_scaleone2(scaleone)scalezero self.asff_scalezero2(x0, self.upsample_scaleone2_2(x1), self.upsample_scaletwo2_4(x2))scaleone self.asff_scaleone2(self.downsample_scalezero2_2(x0), x1, self.upsample_scaletwo2_2(x2))scaletwo self.asff_scaletwo2(self.downsample_scalezero2_4(x0), self.downsample_scaleone2_2(x1), x2)x0 self.blocks_scalezero3(scalezero)x1 self.blocks_scaleone3(scaleone)x2 self.blocks_scaletwo3(scaletwo)scalezero self.asff_scalezero3(x0, self.upsample_scaleone3_2(x1), self.upsample_scaletwo3_4(x2))scaleone self.asff_scaleone3(self.downsample_scalezero3_2(x0), x1, self.upsample_scaletwo3_2(x2))scaletwo self.asff_scaletwo3(self.downsample_scalezero3_4(x0), self.downsample_scaleone3_2(x1), x2)scalezero self.blocks_scalezero4(scalezero)scaleone self.blocks_scaleone4(scaleone)scaletwo self.blocks_scaletwo4(scaletwo)return scalezero, scaleone, scaletwoclass AFPN(nn.Module):def __init__(self,in_channels[256, 512, 1024, 2048],out_channels128):super(AFPN, self).__init__()self.fp16_enabled Falseself.conv0 BasicConv(in_channels[0], in_channels[0] // 8, 1)self.conv1 BasicConv(in_channels[1], in_channels[1] // 8, 1)self.conv2 BasicConv(in_channels[2], in_channels[2] // 8, 1)# self.conv3 BasicConv(in_channels[3], in_channels[3] // 8, 1)self.body nn.Sequential(BlockBody([in_channels[0] // 8, in_channels[1] // 8, in_channels[2] // 8]))self.conv00 BasicConv(in_channels[0] // 8, out_channels, 1)self.conv11 BasicConv(in_channels[1] // 8, out_channels, 1)self.conv22 BasicConv(in_channels[2] // 8, out_channels, 1)# self.conv33 BasicConv(in_channels[3] // 8, out_channels, 1)# init weightfor m in self.modules():if isinstance(m, nn.Conv2d):nn.init.xavier_normal_(m.weight, gain0.02)elif isinstance(m, nn.BatchNorm2d):torch.nn.init.normal_(m.weight.data, 1.0, 0.02)torch.nn.init.constant_(m.bias.data, 0.0)def forward(self, x):x0, x1, x2 xx0 self.conv0(x0)x1 self.conv1(x1)x2 self.conv2(x2)# x3 self.conv3(x3)out0, out1, out2 self.body([x0, x1, x2])out0 self.conv00(out0)out1 self.conv11(out1)out2 self.conv22(out2)return out0, out1, out2class Detect_AFPN(nn.Module):YOLOv8 Detect head for detection models.dynamic False # force grid reconstructionexport False # export modeshape Noneanchors torch.empty(0) # initstrides torch.empty(0) # initdef __init__(self, nc80, channel256, ch()):Initializes the YOLOv8 detection layer with specified number of classes and channels.super().__init__()self.nc nc # number of classesself.nl len(ch) # number of detection layersself.reg_max 16 # DFL channels (ch[0] // 16 to scale 4/8/12/16/20 for n/s/m/l/x)self.no nc self.reg_max * 4 # number of outputs per anchorself.stride torch.zeros(self.nl) # strides computed during buildc2, c3 max((16, ch[0] // 4, self.reg_max * 4)), max(ch[0], min(self.nc, 100)) # channelsself.cv2 nn.ModuleList(nn.Sequential(Conv(channel, c2, 3), Conv(c2, c2, 3), nn.Conv2d(c2, 4 * self.reg_max, 1)) for x in ch)self.cv3 nn.ModuleList(nn.Sequential(Conv(channel, c3, 3), Conv(c3, c3, 3), nn.Conv2d(c3, self.nc, 1)) for x in ch)self.dfl DFL(self.reg_max) if self.reg_max 1 else nn.Identity()self.AFPN AFPN(ch, channel)def forward(self, x):Concatenates and returns predicted bounding boxes and class probabilities.x list(self.AFPN(x))shape x[0].shape # BCHWfor i in range(self.nl):x[i] torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1)if self.training:return xelif self.dynamic or self.shape ! shape:self.anchors, self.strides (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))self.shape shapex_cat torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2)if self.export and self.format in (saved_model, pb, tflite, edgetpu, tfjs): # avoid TF FlexSplitV opsbox x_cat[:, :self.reg_max * 4]cls x_cat[:, self.reg_max * 4:]else:box, cls x_cat.split((self.reg_max * 4, self.nc), 1)dbox dist2bbox(self.dfl(box), self.anchors.unsqueeze(0), xywhTrue, dim1) * self.stridesif self.export and self.format in (tflite, edgetpu):# Normalize xywh with image size to mitigate quantization error of TFLite integer models as done in YOLOv5:# https://github.com/ultralytics/yolov5/blob/0c8de3fca4a702f8ff5c435e67f378d1fce70243/models/tf.py#L307-L309# See this PR for details: https://github.com/ultralytics/ultralytics/pull/1695img_h shape[2] * self.stride[0]img_w shape[3] * self.stride[0]img_size torch.tensor([img_w, img_h, img_w, img_h], devicedbox.device).reshape(1, 4, 1)dbox / img_sizey torch.cat((dbox, cls.sigmoid()), 1)return y if self.export else (y, x)def bias_init(self):Initialize Detect() biases, WARNING: requires stride availability.m self # self.model[-1] # Detect() module# cf torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlengthnc) 1# ncf math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # nominal class frequencyfor a, b, s in zip(m.cv2, m.cv3, m.stride): # froma[-1].bias.data[:] 1.0 # boxb[-1].bias.data[:m.nc] math.log(5 / m.nc / (640 / s) ** 2) # cls (.01 objects, 80 classes, 640 img)四、手把手教你添加Detect_AFPN检测头
这里教大家添加检测头检测头的添加相对于其它机制来说比较复杂一点修改的地方比较多。
具体更多细节可以看我的添加教程博客下面的教程也是完美运行的看那个都行具体大家选择。
添加教程-YOLOv8改进 | 如何在网络结构中添加注意力机制、C2f、卷积、Neck、检测头 4.1 修改一
首先我们将上面的代码复制粘贴到ultralytics/nn/modules 目录下新建一个py文件复制粘贴进去具体名字自己来定我这里起名为AFPN.py。 4.2 修改二
我们新建完上面的文件之后找到如下的文件ultralytics/nn/tasks.py。这里需要修改的地方有点多总共有7处但都很简单。首先我们在该文件的头部导入我们AFPN文件中的检测头。 4.3 修改三
找到如下的代码进行将检测头添加进去这里给大家推荐个快速搜索的方法用ctrlf然后搜索Detect然后就能快速查找了。 4.4 修改四
同理将我们的检测头添加到如下的代码里。
4.5 修改五
同理
4.6 修改六
同理
4.7 修改七
同理
4.8 修改八
这里有一些不一样我们需要加一行代码 else:return detect 为啥呢不一样因为这里的m在代码执行过程中会将你的代码自动转换为小写所以直接else方便一点以后出现一些其它分割或者其它的教程的时候在提供其它的修改教程。
4.9 修改九
这里也有一些不一样需要自己手动添加一个括号提醒一下大家不要直接添加和我下面保持一致。
五、Detect_AFPN检测头的yaml文件
这个代码的yaml文件和正常的对比也需要修改一下如下- # Ultralytics YOLO , AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. modelyolov8n.yaml will call yolov8.yaml with scale n# [depth, width, max_channels]n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPss: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPsm: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPsl: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPsx: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs# YOLOv8.0n backbone
backbone:# [from, repeats, module, args]- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4- [-1, 3, C2f, [128, True]]- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8- [-1, 6, C2f, [256, True]]- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16- [-1, 6, C2f, [512, True]]- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32- [-1, 3, C2f, [1024, True]]- [-1, 1, SPPF, [1024, 5]] # 9# YOLOv8.0n head
head:- [-1, 1, nn.Upsample, [None, 2, nearest]]- [[-1, 6], 1, Concat, [1]] # cat backbone P4- [-1, 3, C2f, [512]] # 12- [-1, 1, nn.Upsample, [None, 2, nearest]]- [[-1, 4], 1, Concat, [1]] # cat backbone P3- [-1, 3, C2f, [256]] # 15 (P3/8-small)- [-1, 1, Conv, [256, 3, 2]]- [[-1, 12], 1, Concat, [1]] # cat head P4- [-1, 3, C2f, [512]] # 18 (P4/16-medium)- [-1, 1, Conv, [512, 3, 2]]- [[-1, 9], 1, Concat, [1]] # cat head P5- [-1, 3, C2f, [1024]] # 21 (P5/32-large)- [[15, 18, 21], 1, Detect_AFPN, [nc, 256]] # Detect(P3, P4, P5)六、完美运行记录
最后提供一下完美运行的图片。
七、本文总结
到此本文的正式分享内容就结束了在这里给大家推荐我的YOLOv8改进有效涨点专栏本专栏目前为新开的平均质量分98分后期我会根据各种最新的前沿顶会进行论文复现也会对一些老的改进机制进行补充目前本专栏免费阅读(暂时大家尽早关注不迷路~)如果大家觉得本文帮助到你了订阅本专栏关注后续更多的更新~ 专栏回顾YOLOv8改进系列专栏——本专栏持续复习各种顶会内容——科研必备
