中国优秀设计网站,网站后台邮箱设置,在网上找做设计是什么网站,哈尔滨信息网0451秋招面试专栏推荐 #xff1a;深度学习算法工程师面试问题总结【百面算法工程师】——点击即可跳转 #x1f4a1;#x1f4a1;#x1f4a1;本专栏所有程序均经过测试#xff0c;可成功执行#x1f4a1;#x1f4a1;#x1f4a1; 专栏目录#xff1a; 《YOLOv5入门 改…秋招面试专栏推荐 深度学习算法工程师面试问题总结【百面算法工程师】——点击即可跳转 本专栏所有程序均经过测试可成功执行 专栏目录 《YOLOv5入门 改进涨点》专栏介绍 专栏目录 |目前已有60篇内容内含各种Head检测头、损失函数Loss、Backbone、Neck、NMS等创新点改进 MobileNetV2是一种高效的卷积神经网络架构专为移动和嵌入式设备上的计算需求设计。它通过引入逆残差结构Inverted Residuals和线性瓶颈层有效地减少了计算量和参数数量同时保持了良好的精度。该网络在保持较低复杂度的同时能够在图像分类、目标检测和语义分割等任务中提供强大的性能。文章在介绍主要的原理后将手把手教学如何进行模块的代码添加和修改并将修改后的完整代码放在文章的最后方便大家一键运行小白也可轻松上手实践。以帮助您更好地学习深度学习目标检测YOLO系列的挑战。 专栏地址 YOLOv5改进入门——持续更新各种有效涨点方法 点击即可跳转 目录
1.原理
2. 将MobileNet v2添加到YOLOv5中
2.1 MobileNet v2的代码实现
2.2 新增yaml文件
2.3 注册模块
2.4 执行程序
3. 完整代码分享
4. GFLOPs
5. 进阶
6. 总结 1.原理 论文地址 MobileNetV2: Inverted Residuals and Linear Bottlenecks——点击即可跳转
官方代码官方代码仓库——点击即可跳转
以下原理内容来自太阳花的小绿豆
在MobileNet v1的网络结构表中能够发现网络的结构就像VGG一样是个直筒型的不像ResNet网络有shorcut之类的连接方式。而且有人反映说MobileNet v1网络中的DW卷积很容易训练废掉效果并没有那么理想。所以我们接着看下MobileNet v2网络。 MobileNet v2网络是由google团队在2018年提出的相比MobileNet V1网络准确率更高模型更小。刚刚说了MobileNet v1网络中的亮点是DW卷积那么在MobileNet v2中的亮点就是Inverted residual block倒残差结构如下下图所示左侧是ResNet网络中的残差结构右侧就是MobileNet v2中的到残差结构。在残差结构中是1x1卷积降维-3x3卷积-1x1卷积升维在倒残差结构中正好相反是1x1卷积升维-3x3DW卷积-1x1卷积降维。为什么要这样做原文的解释是高维信息通过ReLU激活函数后丢失的信息更少注意倒残差结构中基本使用的都是ReLU6激活函数但是最后一个1x1的卷积层使用的是线性激活函数。 在使用倒残差结构时需要注意下并不是所有的倒残差结构都有shortcut连接只有当stride1且输入特征矩阵与输出特征矩阵shape相同时才有shortcut连接只有当shape相同时两个矩阵才能做加法运算当stride1时并不能保证输入特征矩阵的channel与输出特征矩阵的channel相同。 下图是MobileNet v2网络的结构表其中t代表的是扩展因子倒残差结构中第一个1x1卷积的扩展因子c代表输出特征矩阵的channeln代表倒残差结构重复的次数s代表步距注意这里的步距只是针对重复n次的第一层倒残差结构后面的都默认为1。 2. 将MobileNet v2添加到YOLOv5中
2.1 MobileNet v2的代码实现 关键步骤一: 将下面代码添加到 yolov5/models/common.py中 class conv_bn_relu_maxpool(nn.Module):def __init__(self, c1, c2): # ch_in, ch_outsuper(conv_bn_relu_maxpool, self).__init__()self.conv Conv(c1, c2, k3, s2, p1, g1, actReLU)self.maxpool nn.MaxPool2d(kernel_size3, stride2, padding1, dilation1, ceil_modeFalse)def forward(self, x):return self.maxpool(self.conv(x))def fuse(self):self.conv.fuse()class RepVGGBlock(nn.Module):def __init__(self, in_channels, out_channels, kernel_size3, stride1, use_seFalse, use_cbamFalse,padding1, dilation1, groups1, padding_modezeros, deployFalse):super(RepVGGBlock, self).__init__()self.deploy deployself.groups groupsself.in_channels in_channelsself.out_channels out_channelsself.kernel_size kernel_sizeself.stride strideself.padding paddingself.dilation dilationself.groups groupsself.padding_mode padding_modepadding_11 padding - kernel_size // 2# self.nonlinearity nn.SiLU()self.nonlinearity nn.ReLU()if use_se or use_cbam:if use_se:self.se SEBlock(out_channels, internal_neuronsout_channels // 16)if use_cbam:self.se CBAM(out_channels, internal_neuronsout_channels // 16)else:self.se nn.Identity()if deploy:self.rbr_reparam nn.Conv2d(in_channelsin_channels, out_channelsout_channels, kernel_sizekernel_size,stridestride,paddingpadding, dilationdilation, groupsgroups, biasTrue,padding_modepadding_mode)else:self.rbr_identity nn.BatchNorm2d(num_featuresin_channels) if out_channels in_channels and stride 1 else Noneself.rbr_dense conv_bn(in_channelsin_channels, out_channelsout_channels, kernel_sizekernel_size,stridestride, paddingpadding, groupsgroups)self.rbr_1x1 conv_bn(in_channelsin_channels, out_channelsout_channels, kernel_size1, stridestride,paddingpadding_11, groupsgroups)# print(RepVGG Block, identity , self.rbr_identity)def get_equivalent_kernel_bias(self):kernel3x3, bias3x3 self._fuse_bn_tensor(self.rbr_dense)kernel1x1, bias1x1 self._fuse_bn_tensor(self.rbr_1x1)kernelid, biasid self._fuse_bn_tensor(self.rbr_identity)return kernel3x3 self._pad_1x1_to_3x3_tensor(kernel1x1) kernelid, bias3x3 bias1x1 biasiddef _pad_1x1_to_3x3_tensor(self, kernel1x1):if kernel1x1 is None:return 0else:return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])def _fuse_bn_tensor(self, branch):if branch is None:return 0, 0if isinstance(branch, nn.Sequential):kernel branch.conv.weightrunning_mean branch.bn.running_meanrunning_var branch.bn.running_vargamma branch.bn.weightbeta branch.bn.biaseps branch.bn.epselse:assert isinstance(branch, (nn.BatchNorm2d, nn.SyncBatchNorm))if not hasattr(self, id_tensor):input_dim self.in_channels // self.groupskernel_value np.zeros((self.in_channels, input_dim, 3, 3), dtypenp.float32)for i in range(self.in_channels):kernel_value[i, i % input_dim, 1, 1] 1self.id_tensor torch.from_numpy(kernel_value).to(branch.weight.device)kernel self.id_tensorrunning_mean branch.running_meanrunning_var branch.running_vargamma branch.weightbeta branch.biaseps branch.epsstd (running_var eps).sqrt()t (gamma / std).reshape(-1, 1, 1, 1)return kernel * t, beta - running_mean * gamma / stddef forward(self, inputs):if hasattr(self, rbr_reparam):return self.nonlinearity(self.se(self.rbr_reparam(inputs)))if self.rbr_identity is None:id_out 0else:id_out self.rbr_identity(inputs)return self.nonlinearity(self.se(self.rbr_dense(inputs) self.rbr_1x1(inputs) id_out))# RepVGGBlock(in_channelsself.in_planes, out_channelsplanes, kernel_size3,# stridestride, padding1, groups1, deployself.deploy, use_seself.use_se))def fuse(self):if self.deploy False:self.rbr_reparam nn.Conv2d(in_channelsself.in_channels, out_channelsself.out_channels,kernel_sizeself.kernel_size,strideself.stride,paddingself.padding, dilationself.dilation, groupsself.groups, biasTrue,padding_modeself.padding_mode).requires_grad_(False).to(self.rbr_dense.conv.weight.device)self.deploy Truekernel, bias self.get_equivalent_kernel_bias()self.rbr_reparam.weight.data kernelself.rbr_reparam.bias.data biasself.forward self.fusevggforwardself.__delattr__(rbr_identity)self.rbr_dense.__delattr__(conv)self.rbr_dense.__delattr__(bn)self.rbr_1x1.__delattr__(conv)self.rbr_1x1.__delattr__(bn)del self._modules[rbr_dense]del self._modules[rbr_1x1]def fusevggforward(self, inputs):return self.nonlinearity(self.se(self.rbr_reparam(inputs)))class MobileNetV2_Block(nn.Module):def __init__(self, inp, oup, stride1, expand_ratio1):super(MobileNetV2_Block, self).__init__()assert stride in [1, 2]self.stride strideself.identity stride 1 and inp ouphidden_dim int(round(inp * expand_ratio))act ReLUif expand_ratio ! 1:self.conv nn.Sequential(Conv(inp, hidden_dim, k1, s1, p0, actact),DWConv(hidden_dim, hidden_dim, k3, sstride, actact),Conv(hidden_dim, oup, k1, s1, p0, actFalse),)else:self.conv nn.Sequential(DWConv(hidden_dim, hidden_dim, k3, sstride, actact),Conv(hidden_dim, oup, k1, s1, p0, actFalse),)def forward(self, x):y self.conv(x)if self.identity:return x yelse:return ydef fuse(self):for m in self.conv:if isinstance(m, (Conv, DWConv, RepVGGBlock)):m.fuse()2.2 新增yaml文件 关键步骤二在下/yolov5/models下新建文件 yolov5_MobileNetv2.yaml并将下面代码复制进去 目标检测yaml文件
# YOLOv5 by Ultralytics, GPL-3.0 license# Parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # 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# Mobilenetv3Small backbone
# MobileNetV3_Block in_ch, [out_ch, hid_ch, k_s, stride, SE, HardSwish]
backbone:# [from, number, module, args][[-1, 1, Conv, [32, 3, 2]], # 0-p1/2[-1, 1, MobileNetV2_Block, [16, 1, 1]], # 1[-1, 1, MobileNetV2_Block, [24, 2, 6]], # 2-p2/4[-1, 1, MobileNetV2_Block, [24, 1, 6]], # 3[-1, 1, MobileNetV2_Block, [32, 2, 6]], # 4-p3/8[-1, 2, MobileNetV2_Block, [32, 1, 6]], # 5[-1, 1, MobileNetV2_Block, [64, 2, 6]], # 6-p4/16[-1, 3, MobileNetV2_Block, [64, 1, 6]], # 7[-1, 1, MobileNetV2_Block, [96, 1, 6]], # 8[-1, 2, MobileNetV2_Block, [96, 1, 6]], # 9[-1, 1, MobileNetV2_Block, [160, 2, 6]], # 10-p5/32[-1, 2, MobileNetV2_Block, [160, 1, 6]], # 11[-1, 1, MobileNetV2_Block, [320, 1, 6]], # 12[-1, 1, SPPF, [1024, 5]], # 13]# YOLOv5 v6.0 head
head:[[-1, 1, Conv, [256, 1, 1]], # 14[-1, 1, nn.Upsample, [None, 2, nearest]],[[-1, 9], 1, Concat, [1]], # cat backbone P4[-1, 1, C3, [256, False]], # 17[-1, 1, Conv, [128, 1, 1]], # 18[-1, 1, nn.Upsample, [None, 2, nearest]],[[-1, 5], 1, Concat, [1]], # cat backbone P3[-1, 1, C3, [128, False]], # 20 (P3/8-small)[-1, 1, Conv, [128, 3, 2]],[[-1, 18], 1, Concat, [1]], # cat head P4[-1, 1, C3, [256, False]], # 24 (P4/16-medium)[-1, 1, Conv, [256, 3, 2]],[[-1, 14], 1, Concat, [1]], # cat head P5[-1, 1, C3, [512, False]], # 27 (P5/32-large)[[21, 24, 27], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)]
语义分割yaml文件
# YOLOv5 by Ultralytics, GPL-3.0 license# Parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # 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# Mobilenetv3Small backbone
# MobileNetV3_Block in_ch, [out_ch, hid_ch, k_s, stride, SE, HardSwish]
backbone:# [from, number, module, args][[-1, 1, Conv, [32, 3, 2]], # 0-p1/2[-1, 1, MobileNetV2_Block, [16, 1, 1]], # 1[-1, 1, MobileNetV2_Block, [24, 2, 6]], # 2-p2/4[-1, 1, MobileNetV2_Block, [24, 1, 6]], # 3[-1, 1, MobileNetV2_Block, [32, 2, 6]], # 4-p3/8[-1, 2, MobileNetV2_Block, [32, 1, 6]], # 5[-1, 1, MobileNetV2_Block, [64, 2, 6]], # 6-p4/16[-1, 3, MobileNetV2_Block, [64, 1, 6]], # 7[-1, 1, MobileNetV2_Block, [96, 1, 6]], # 8[-1, 2, MobileNetV2_Block, [96, 1, 6]], # 9[-1, 1, MobileNetV2_Block, [160, 2, 6]], # 10-p5/32[-1, 2, MobileNetV2_Block, [160, 1, 6]], # 11[-1, 1, MobileNetV2_Block, [320, 1, 6]], # 12[-1, 1, SPPF, [1024, 5]], # 13]# YOLOv5 v6.0 head
head:[[-1, 1, Conv, [256, 1, 1]], # 14[-1, 1, nn.Upsample, [None, 2, nearest]],[[-1, 9], 1, Concat, [1]], # cat backbone P4[-1, 1, C3, [256, False]], # 17[-1, 1, Conv, [128, 1, 1]], # 18[-1, 1, nn.Upsample, [None, 2, nearest]],[[-1, 5], 1, Concat, [1]], # cat backbone P3[-1, 1, C3, [128, False]], # 20 (P3/8-small)[-1, 1, Conv, [128, 3, 2]],[[-1, 18], 1, Concat, [1]], # cat head P4[-1, 1, C3, [256, False]], # 24 (P4/16-medium)[-1, 1, Conv, [256, 3, 2]],[[-1, 14], 1, Concat, [1]], # cat head P5[-1, 1, C3, [512, False]], # 27 (P5/32-large)[[21, 24, 27], 1, Segment, [nc, anchors, 32, 256]], # Detect(P3, P4, P5)] 温馨提示本文只是对yolov5基础上添加模块如果要对yolov5n/l/m/x进行添加则只需要指定对应的depth_multiple 和 width_multiple。 # YOLOv5n
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.25 # layer channel multiple# YOLOv5s
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple# YOLOv5l
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple# YOLOv5m
depth_multiple: 0.67 # model depth multiple
width_multiple: 0.75 # layer channel multiple# YOLOv5x
depth_multiple: 1.33 # model depth multiple
width_multiple: 1.25 # layer channel multiple
2.3 注册模块 关键步骤三在yolo.py的parse_model函数中注册 添加“MobileNetv2, 2.4 执行程序
在train.py中将cfg的参数路径设置为yolov5_MobileNetv2.yaml的路径
建议大家写绝对路径确保一定能找到 运行程序如果出现下面的内容则说明添加成功 from n params module arguments0 -1 1 928 models.common.Conv [3, 32, 3, 2]1 -1 1 896 models.common.MobileNetV2_Block [32, 16, 1, 1]2 -1 1 5136 models.common.MobileNetV2_Block [16, 24, 2, 6]3 -1 1 8832 models.common.MobileNetV2_Block [24, 24, 1, 6]4 -1 1 10000 models.common.MobileNetV2_Block [24, 32, 2, 6]5 -1 2 29696 models.common.MobileNetV2_Block [32, 32, 1, 6]6 -1 1 21056 models.common.MobileNetV2_Block [32, 64, 2, 6]7 -1 3 162816 models.common.MobileNetV2_Block [64, 64, 1, 6]8 -1 1 66624 models.common.MobileNetV2_Block [64, 96, 1, 6]9 -1 2 236544 models.common.MobileNetV2_Block [96, 96, 1, 6]10 -1 1 155264 models.common.MobileNetV2_Block [96, 160, 2, 6]11 -1 2 640000 models.common.MobileNetV2_Block [160, 160, 1, 6]12 -1 1 473920 models.common.MobileNetV2_Block [160, 320, 1, 6]13 -1 1 708928 models.common.SPPF [320, 1024, 5]14 -1 1 262656 models.common.Conv [1024, 256, 1, 1]15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, nearest]16 [-1, 9] 1 0 models.common.Concat [1]17 -1 1 321024 models.common.C3 [352, 256, 1, False]18 -1 1 33024 models.common.Conv [256, 128, 1, 1]19 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, nearest]20 [-1, 5] 1 0 models.common.Concat [1]21 -1 1 78592 models.common.C3 [160, 128, 1, False]22 -1 1 147712 models.common.Conv [128, 128, 3, 2]23 [-1, 18] 1 0 models.common.Concat [1]24 -1 1 296448 models.common.C3 [256, 256, 1, False]25 -1 1 590336 models.common.Conv [256, 256, 3, 2]26 [-1, 14] 1 0 models.common.Concat [1]27 -1 1 1182720 models.common.C3 [512, 512, 1, False]28 [21, 24, 27] 1 229245 Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
YOLOv5 summary: 347 layers, 5662397 parameters, 5662397 gradients, 11.5 GFLOPs
3. 完整代码分享
https://pan.baidu.com/s/1uxmTHtaXpeL-hWyP1-me1w?pwdr6hg
提取码: r6hg
4. GFLOPs
关于GFLOPs的计算方式可以查看百面算法工程师 | 卷积基础知识——Convolution
未改进的GFLOPs
改进后的GFLOPs
现在手上没有卡了等过段时候有卡了把这补上需要的同学自己测一下 5. 进阶
可以结合损失函数或者卷积模块进行多重改进
YOLOv5改进 | 损失函数 | EIoU、SIoU、WIoU、DIoU、FocuSIoU等多种损失函数——点击即可跳转
6. 总结
MobileNetV2是谷歌于2018年提出的一种高效卷积神经网络架构专为移动和嵌入式设备设计。它通过引入逆残差结构和线性瓶颈层优化了计算效率和模型性能显著减少了计算量和参数数量。MobileNetV2在图像分类、目标检测和语义分割等任务中表现出色能够在资源受限的设备上提供与更大模型相近的精度。
