论文地址:https://arxiv.org/abs/1905.02244
代码地址:https://github.com/xiaolai-sqlai/mobilenetv3
我们展示了基于互补搜索技术和新颖架构设计相结合的下一代 MobileNets。MobileNetV3通过结合硬件感知网络架构搜索(NAS)和 NetAdapt算法对移动设计如何协同工作,利用互补的方法来提高移动端CPU推理整体水平。通过这个过程,创建了两个新的发布的 MobileNet模型:MobileNetV3-Large 和 MobileNetV3-Small,分别针对高资源和低资源用例。然后将这些模型应用于目标检测和语义分割。针对语义分割(或任何密集像素预测)任务,提出了一种新的高效分割解码器 Lite reduce Atrous Spatial Pyramid Pooling(LR-ASPP)。实现了移动端分类,检测和分割的最新SOTA成果。与 MobileNetV2 相比,MobileNetV3-Large 在 ImageNet 分类上的准确率提高了 3.2%,同时延迟降低了 20%。与 MobileNetV2 相比,MobileNetV3-Small 的准确率高 6.6%,同时延迟相当。 MobileNetV3-Large 检测速度比 MobileNetV2 快 25%,在COCO检测上的精度大致相等。MobileNetV3-Large LR-ASPP 的速度比 MobileNetV2 R-ASPP 快 30%,在 Cityscapes segmentation分割数据集上,MobileNetV3-Large LR-ASPP 比 MobileNet V2 R-ASPP 快 34%。
MobileNet V3 主要特点
- 论文推出两个版本:
Large
和Small
,分别适用于不同的资源用例; - 使用
NetAdapt
算法获得卷积核和通道的最佳数量; - 继承
V1
的深度可分离卷积; - 继承
V2
的具有线性瓶颈的残差结构; - 引入
SE
通道注意力结构; - 使用了一种新的激活函数
h-swish(x)
代替Relu6
,h
的意思表示hard
; - 使用了
Relu6(x + 3)/6
来近似SE
模块中的sigmoid
; - 修改了
MobileNetV2
后端输出head。
MobileNetV3网络结构
MobileNetV3-Large结构
将YOLOv5主干网络替换为MobileNetV3-large:
yolov5-mobilenetv3large-backbone.yaml
# parametersnc:80# number of classesdepth_multiple:1.0width_multiple:1.0# anchorsanchors:-[10,13,16,30,33,23]# P3/8-[30,61,62,45,59,119]# P4/16-[116,90,156,198,373,326]# P5/32# MobileNetV3-large backbone# MobileNetV3_InvertedResidual [out_ch, hid_ch, k_s, stride, SE, HardSwish]backbone:# [from, number, module, args][[-1,1, Conv_BN_HSwish,[16,2]],# 0-p1/2[-1,1, MobileNetV3_InvertedResidual,[16,16,3,1,0,0]],# 1-p1/2[-1,1, MobileNetV3_InvertedResidual,[24,64,3,2,0,0]],# 2-p2/4[-1,1, MobileNetV3_InvertedResidual,[24,72,3,1,0,0]],# 3-p2/4[-1,1, MobileNetV3_InvertedResidual,[40,72,5,2,1,0]],# 4-p3/8[-1,1, MobileNetV3_InvertedResidual,[40,120,5,1,1,0]],# 5-p3/8[-1,1, MobileNetV3_InvertedResidual,[40,120,5,1,1,0]],# 6-p3/8[-1,1, MobileNetV3_InvertedResidual,[80,240,3,2,0,1]],# 7-p4/16[-1,1, MobileNetV3_InvertedResidual,[80,200,3,1,0,1]],# 8-p4/16[-1,1, MobileNetV3_InvertedResidual,[80,184,3,1,0,1]],# 9-p4/16[-1,1, MobileNetV3_InvertedResidual,[80,184,3,1,0,1]],# 10-p4/16[-1,1, MobileNetV3_InvertedResidual,[112,480,3,1,1,1]],# 11-p4/16[-1,1, MobileNetV3_InvertedResidual,[112,672,3,1,1,1]],# 12-p4/16[-1,1, MobileNetV3_InvertedResidual,[160,672,5,1,1,1]],# 13-p4/16[-1,1, MobileNetV3_InvertedResidual,[160,672,5,2,1,1]],# 14-p5/32[-1,1, MobileNetV3_InvertedResidual,[160,960,5,1,1,1]],# 15-p5/32]head:[[-1,1, Conv,[160,1,1]],[-1,1, nn.Upsample,[None,2,'nearest']],[[-1,13],1, Concat,[1]],# cat backbone P4[-1,1, C3,[320,False]],# 19[-1,1, Conv,[320,1,1]],[-1,1, nn.Upsample,[None,2,'nearest']],[[-1,6],1, Concat,[1]],# cat backbone P3[-1,1, C3,[360,False]],# 23 (P3/8-small)[-1,1, Conv,[360,3,2]],[[-1,20],1, Concat,[1]],# cat head P4[-1,1, C3,[680,False]],# 26 (P4/16-medium)[-1,1, Conv,[680,3,2]],[[-1,16],1, Concat,[1]],# cat head P5[-1,1, C3,[840,False]],# 29 (P5/32-large)[[23,26,29],1, Detect,[nc, anchors]],# Detect(P3, P4, P5)]
MobileNetV3-Small结构
将YOLOv5主干网络替换为MobileNetV3-Small:
yolov5-mobilenetv3small-backbone.yaml
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license# Parametersnc:80# number of classesdepth_multiple:1.0# model depth multiplewidth_multiple:1.0# layer channel multipleanchors:-[10,13,16,30,33,23]# P3/8-[30,61,62,45,59,119]# P4/16-[116,90,156,198,373,326]# P5/32# Mobilenetv3-small backbone# MobileNetV3_InvertedResidual [out_ch, hid_ch, k_s, stride, SE, HardSwish]backbone:# [from, number, module, args][[-1,1, Conv_BN_HSwish,[16,2]],# 0-p1/2[-1,1, MobileNetV3_InvertedResidual,[16,16,3,2,1,0]],# 1-p2/4[-1,1, MobileNetV3_InvertedResidual,[24,72,3,2,0,0]],# 2-p3/8[-1,1, MobileNetV3_InvertedResidual,[24,88,3,1,0,0]],# 3[-1,1, MobileNetV3_InvertedResidual,[40,96,5,2,1,1]],# 4-p4/16[-1,1, MobileNetV3_InvertedResidual,[40,240,5,1,1,1]],# 5[-1,1, MobileNetV3_InvertedResidual,[40,240,5,1,1,1]],# 6[-1,1, MobileNetV3_InvertedResidual,[48,120,5,1,1,1]],# 7[-1,1, MobileNetV3_InvertedResidual,[48,144,5,1,1,1]],# 8[-1,1, MobileNetV3_InvertedResidual,[96,288,5,2,1,1]],# 9-p5/32[-1,1, MobileNetV3_InvertedResidual,[96,576,5,1,1,1]],# 10[-1,1, MobileNetV3_InvertedResidual,[96,576,5,1,1,1]],# 11]# YOLOv5 v6.0 headhead:[[-1,1, Conv,[96,1,1]],# 12[-1,1, nn.Upsample,[None,2,'nearest']],[[-1,8],1, Concat,[1]],# cat backbone P4[-1,3, C3,[144,False]],# 15[-1,1, Conv,[144,1,1]],# 16[-1,1, nn.Upsample,[None,2,'nearest']],[[-1,3],1, Concat,[1]],# cat backbone P3[-1,3, C3,[168,False]],# 19 (P3/8-small)[-1,1, Conv,[168,3,2]],[[-1,16],1, Concat,[1]],# cat head P4[-1,3, C3,[312,False]],# 22 (P4/16-medium)[-1,1, Conv,[312,3,2]],[[-1,12],1, Concat,[1]],# cat head P5[-1,3, C3,[408,False]],# 25 (P5/32-large)[[19,22,25],1, Detect,[nc, anchors]],# Detect(P3, P4, P5)]
在YOLOv5项目中添加方式:
common.py中加入以下代码:
# Mobilenetv3SmallclassSeBlock(nn.Module):def__init__(self, in_channel, reduction=4):super().__init__()
self.Squeeze = nn.AdaptiveAvgPool2d(1)
self.Excitation = nn.Sequential()
self.Excitation.add_module('FC1', nn.Conv2d(in_channel, in_channel // reduction, kernel_size=1))# 1*1卷积与此效果相同
self.Excitation.add_module('ReLU', nn.ReLU())
self.Excitation.add_module('FC2', nn.Conv2d(in_channel // reduction, in_channel, kernel_size=1))
self.Excitation.add_module('Sigmoid', nn.Sigmoid())defforward(self, x):
y = self.Squeeze(x)
ouput = self.Excitation(y)return x *(ouput.expand_as(x))classConv_BN_HSwish(nn.Module):"""
This equals to
def conv_3x3_bn(inp, oup, stride):
return nn.Sequential(
nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
nn.BatchNorm2d(oup),
h_swish()
)
"""def__init__(self, c1, c2, stride):super(Conv_BN_HSwish, self).__init__()
self.conv = nn.Conv2d(c1, c2,3, stride,1, bias=False)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.Hardswish()defforward(self, x):return self.act(self.bn(self.conv(x)))classMobileNetV3_InvertedResidual(nn.Module):def__init__(self, inp, oup, hidden_dim, kernel_size, stride, use_se, use_hs):super(MobileNetV3_InvertedResidual, self).__init__()assert stride in[1,2]
self.identity = stride ==1and inp == oup
if inp == hidden_dim:
self.conv = nn.Sequential(# dw
nn.Conv2d(hidden_dim, hidden_dim, kernel_size, stride,(kernel_size -1)//2, groups=hidden_dim,
bias=False),
nn.BatchNorm2d(hidden_dim),
nn.Hardswish()if use_hs else nn.ReLU(),# Squeeze-and-Excite
SeBlock(hidden_dim)if use_se else nn.Sequential(),# pw-linear
nn.Conv2d(hidden_dim, oup,1,1,0, bias=False),
nn.BatchNorm2d(oup),)else:
self.conv = nn.Sequential(# pw
nn.Conv2d(inp, hidden_dim,1,1,0, bias=False),
nn.BatchNorm2d(hidden_dim),
nn.Hardswish()if use_hs else nn.ReLU(),# dw
nn.Conv2d(hidden_dim, hidden_dim, kernel_size, stride,(kernel_size -1)//2, groups=hidden_dim,
bias=False),
nn.BatchNorm2d(hidden_dim),# Squeeze-and-Excite
SeBlock(hidden_dim)if use_se else nn.Sequential(),
nn.Hardswish()if use_hs else nn.ReLU(),# pw-linear
nn.Conv2d(hidden_dim, oup,1,1,0, bias=False),
nn.BatchNorm2d(oup),)defforward(self, x):
y = self.conv(x)if self.identity:return x + y
else:return y
yolo.py中添加如下代码:
本人更多YOLOv5实战内容导航🍀🌟🚀
- 手把手带你调参Yolo v5 (v6.2)(推理)🌟强烈推荐
- 手把手带你调参Yolo v5 (v6.2)(训练)🚀
- 手把手带你调参Yolo v5 (v6.2)(验证)
- 如何快速使用自己的数据集训练Yolov5模型
- 手把手带你Yolov5 (v6.2)添加注意力机制(一)(并附上30多种顶会Attention原理图)🌟强烈推荐🍀新增8种
- 手把手带你Yolov5 (v6.2)添加注意力机制(二)(在C3模块中加入注意力机制)
- Yolov5如何更换激活函数?
- Yolov5如何更换BiFPN?
- Yolov5 (v6.2)数据增强方式解析
- Yolov5更换上采样方式( 最近邻 / 双线性 / 双立方 / 三线性 / 转置卷积)
- Yolov5如何更换EIOU / alpha IOU / SIoU?
- Yolov5更换主干网络之《旷视轻量化卷积神经网络ShuffleNetv2》
- YOLOv5应用轻量级通用上采样算子CARAFE
- 空间金字塔池化改进 SPP / SPPF / SimSPPF / ASPP / RFB / SPPCSPC / SPPFCSPC🚀
- 用于低分辨率图像和小物体的模块SPD-Conv
- GSConv+Slim-neck 减轻模型的复杂度同时提升精度🍀
- 头部解耦 | 将YOLOX解耦头添加到YOLOv5 | 涨点杀器🍀
- Stand-Alone Self-Attention | 搭建纯注意力FPN+PAN结构🍀
- YOLOv5模型剪枝实战🚀
- YOLOv5知识蒸馏实战🚀
- YOLOv7知识蒸馏实战🚀
- 改进YOLOv5 | 引入密集连接卷积网络DenseNet思想 | 搭建密集连接模块🍀
参考文献:
版权归原作者 迪菲赫尔曼 所有, 如有侵权,请联系我们删除。