目标检测算法——YOLOv5/YOLOv7改进之结合轻量化网络MobileNetV3（降参提速）
关注“PandaCVer”公众号
>>>深度学习Tricks，第一时间送达<<<
论文题目：Searching for MobileNetV3
论文地址：https://arxiv.org/abs/1905.02244
源代码：https://github.com/xiaolai-sqlai/mobilenetv3
一、论文简介
MobileNetV3，是谷歌在2019年3月21日提出的轻量化网络架构，在前两个版本的基础上，加入神经网络架构搜索（NAS）和h-swish激活函数，并引入SE通道注意力机制，性能和速度都表现优异，受到学术界和工业界的追捧。
相比于 MobileNetV2 版本而言，具体 MobileNetV3 在性能上有哪些提升呢？在原论文摘要中，作者提到在 ImageNet 分类任务中正确率上升了 3.2%，计算延时还降低了 20%。
小海带结合YOLOv5做实验时的参数：343 layers, 1376844 parameters, 1376844 gradients, 2.3 GFLOPS。参数量及浮点运算量大幅下降，且推理速度提升飞快！
总结其主要特点：
1.论文推出两个版本：Large 和 Small，分别适用于不同的场景
2.网络的架构基于NAS实现的MnasNet（效果比MobileNetV2好），由NAS搜索获取参数
3.引入MobileNetV1的深度可分离卷积
4.引入MobileNetV2的具有线性瓶颈的倒残差结构
5.引入基于squeeze and excitation结构的轻量级注意力模型(SE)
6.使用了一种新的激活函数h-swish(x)
7.网络结构搜索中，结合两种技术：资源受限的NAS（platform-aware NAS）与NetAdapt
8.修改了MobileNetV2网络端部最后阶段
二、YOLOv5结合轻量化网络MobileNetV3
1.配置.yaml文件
# anchors
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 backbone
backbone:
# [from, number, module, args]
[ [ -1, 1, conv_bn_hswish, [ 16, 2 ] ], # 0-p1/2
[ -1, 1, MobileNet_Block, [ 16, 16, 3, 2, 1, 0 ] ], # 1-p2/4
[ -1, 1, MobileNet_Block, [ 24, 72, 3, 2, 0, 0 ] ], # 2-p3/8
[ -1, 1, MobileNet_Block, [ 24, 88, 3, 1, 0, 0 ] ], # 3-p3/8
[ -1, 1, MobileNet_Block, [ 40, 96, 5, 2, 1, 1 ] ], # 4-p4/16
[ -1, 1, MobileNet_Block, [ 40, 240, 5, 1, 1, 1 ] ], # 5-p4/16
[ -1, 1, MobileNet_Block, [ 40, 240, 5, 1, 1, 1 ] ], # 6-p4/16
[ -1, 1, MobileNet_Block, [ 48, 120, 5, 1, 1, 1 ] ], # 7-p4/16
[ -1, 1, MobileNet_Block, [ 48, 144, 5, 1, 1, 1 ] ], # 8-p4/16
[ -1, 1, MobileNet_Block, [ 96, 288, 5, 2, 1, 1 ] ], # 9-p5/32
[ -1, 1, MobileNet_Block, [ 96, 576, 5, 1, 1, 1 ] ], # 10-p5/32
[ -1, 1, MobileNet_Block, [ 96, 576, 5, 1, 1, 1 ] ], # 11-p5/32
]
# YOLOv5 head
head:
[[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 8], 1, Concat, [1]], # cat backbone P4
[-1, 1, C3, [256, False]], # 15
[-1, 1, Conv, [128, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 3], 1, Concat, [1]], # cat backbone P3
[-1, 1, C3, [128, False]], # 19 (P3/8-small)
[-1, 1, Conv, [128, 3, 2]],
[[-1, 16], 1, Concat, [1]], # cat head P4
[-1, 1, C3, [256, False]], # 22 (P4/16-medium)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P5
[-1, 1, C3, [512, False]], # 25 (P5/32-large)
[[19, 22, 25], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
2.配置common.py
#——————MobileNetV3——————
class h_sigmoid(nn.Module):
def __init__(self, inplace=True):
super(h_sigmoid, self).__init__()
self.relu = nn.ReLU6(inplace=inplace)
def forward(self, x):
return self.relu(x + 3) / 6
class h_swish(nn.Module):
def __init__(self, inplace=True):
super(h_swish, self).__init__()
self.sigmoid = h_sigmoid(inplace=inplace)
def forward(self, x):
return x * self.sigmoid(x)
class SELayer(nn.Module):
def __init__(self, channel, reduction=4):
super(SELayer, self).__init__()
# Squeeze操作
self.avg_pool = nn.AdaptiveAvgPool2d(1)
# Excitation操作(FC+ReLU+FC+Sigmoid)
self.fc = nn.Sequential(
nn.Linear(channel, channel // reduction),
nn.ReLU(inplace=True),
nn.Linear(channel // reduction, channel),
h_sigmoid()
)
def forward(self, x):
b, c, _, _ = x.size()
y = self.avg_pool(x)
y = y.view(b, c)
y = self.fc(y).view(b, c, 1, 1) # 学习到的每一channel的权重
return x * y
class conv_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 = h_swish()
def forward(self, x):
return self.act(self.bn(self.conv(x)))
def fuseforward(self, x):
return self.act(self.conv(x))
class MobileNet_Block(nn.Module):
def __init__(self, inp, oup, hidden_dim, kernel_size, stride, use_se, use_hs):
super(MobileNet_Block, self).__init__()
assert stride in [1, 2]
self.identity = stride == 1 and inp == oup
# 输入通道数=扩张通道数 则不进行通道扩张
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),
h_swish() if use_hs else nn.ReLU(inplace=True),
# Squeeze-and-Excite
SELayer(hidden_dim) if use_se else nn.Sequential(),
# pw-linear
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
)
else:
# 否则 先进行通道扩张
self.conv = nn.Sequential(
# pw
nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
nn.BatchNorm2d(hidden_dim),
h_swish() if use_hs else nn.ReLU(inplace=True),
# 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
SELayer(hidden_dim) if use_se else nn.Sequential(),
h_swish() if use_hs else nn.ReLU(inplace=True),
# pw-linear
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
)
def forward(self, x):
y = self.conv(x)
if self.identity:
return x + y
else:
return y
3.修改yolo.py
找到parse_model函数，加入h_sigmoid， h_swish，SELayer，conv_bn_hswish， MobileNet_Block等5个模块即可。
最后一步！——小伙伴们可以自行训练自己的数据集啦！！！