MobileNetV1 V2 V3网络理解+pytorch源码
Posted 为了维护世界和平_
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了MobileNetV1 V2 V3网络理解+pytorch源码相关的知识，希望对你有一定的参考价值。
目录
Mobilenet简介
传统神经网络，内存需求大，运算量大。无法在移动设备以及嵌入式设备上运行。Mobilenet专注于移动端或者嵌入式设备中的轻量级CNN网络（相比VGG16准确率下降0.9%,但模型参数只有VGG1/32）
一、MobilenetV1
深度可分离卷积，Depthwise Convolution
增加超参数α(卷积核个数)，β（卷积核大小）
深度可分离卷积图形
深度可分离实现
激活函数：relu
存在的问题，dw卷积核参数大部分为0
二、MobilenetV2
相比V1网络模型更小，准确率更高
Inverted Residuals(倒残差结构) 先升维再降维
Linear Bottlenecks（倒残差最有一层使用linear激活函数）
激活函数Relu6,DW
倒残差结构最后一层使用线性激活，使用Relu容易丢失低纬度信息
倒残差结构
网络结构
t:扩展因子，倒残差结构第一层1x1卷积层的扩展倍率
c:输出通道数
n:bottleneck重复次数
s:步距，第一层，其它为1
性能对比
1）分类
2）目标检测
三、MobilenetV3
相比V2网络更快更高效，增加3.2%的准确率的同时减少20%的延时。
1）更新block，加入SE模块，更新了激活函数
SE理解：先进行平均池化->relu->h-sig->将因子乘上特征图
2）使用NAS搜索参数
3）重新设计耗时层结构
-
减少第一个卷积层的卷积核个数（32->16）
卷积核从32减少到16，精度相同，时间减少2毫秒，运算量减少2百万。 -
精简Last Stage
在精度没有减少的情况下，时间减少7毫秒（占用整个推理时间11%），运算量减少3千万Add
重新设计了激活函数
对推理速度和量化过程都比较友好
网络结构 MobileNetV3-Large
MobilenetV3 Small
Lage与Small网络对比
四、程序
MobileNetV2
from torch import nn
import torch
def _make_divisible(ch, divisor=8, min_ch=None):
"""
This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8
It can be seen here:
https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
"""
if min_ch is None:
min_ch = divisor
new_ch = max(min_ch, int(ch + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_ch < 0.9 * ch:
new_ch += divisor
return new_ch
class ConvBNReLU(nn.Sequential):
def __init__(self, in_channel, out_channel, kernel_size=3, stride=1, groups=1):
padding = (kernel_size - 1) // 2
super(ConvBNReLU, self).__init__(
nn.Conv2d(in_channel, out_channel, kernel_size, stride, padding, groups=groups, bias=False),
nn.BatchNorm2d(out_channel),
nn.ReLU6(inplace=True)
)
class InvertedResidual(nn.Module):
def __init__(self, in_channel, out_channel, stride, expand_ratio):
super(InvertedResidual, self).__init__()
hidden_channel = in_channel * expand_ratio
self.use_shortcut = stride == 1 and in_channel == out_channel
layers = []
if expand_ratio != 1:
# 1x1 pointwise conv
layers.append(ConvBNReLU(in_channel, hidden_channel, kernel_size=1))
layers.extend([
# 3x3 depthwise conv
ConvBNReLU(hidden_channel, hidden_channel, stride=stride, groups=hidden_channel),
# 1x1 pointwise conv(linear)
nn.Conv2d(hidden_channel, out_channel, kernel_size=1, bias=False),
nn.BatchNorm2d(out_channel),
])
self.conv = nn.Sequential(*layers)
def forward(self, x):
if self.use_shortcut:
return x + self.conv(x)
else:
return self.conv(x)
class MobileNetV2(nn.Module):
def __init__(self, num_classes=1000, alpha=1.0, round_nearest=8):
super(MobileNetV2, self).__init__()
block = InvertedResidual
input_channel = _make_divisible(32 * alpha, round_nearest)
last_channel = _make_divisible(1280 * alpha, round_nearest)
inverted_residual_setting = [
# t, c, n, s
[1, 16, 1, 1],
[6, 24, 2, 2],
[6, 32, 3, 2],
[6, 64, 4, 2],
[6, 96, 3, 1],
[6, 160, 3, 2],
[6, 320, 1, 1],
]
features = []
# conv1 layer
features.append(ConvBNReLU(3, input_channel, stride=2))#
# building inverted residual residual blockes
for t, c, n, s in inverted_residual_setting:
output_channel = _make_divisible(c * alpha, round_nearest)
for i in range(n):
stride = s if i == 0 else 1
features.append(block(input_channel, output_channel, stride, expand_ratio=t))
input_channel = output_channel
# building last several layers
features.append(ConvBNReLU(input_channel, last_channel, 1))
# combine feature layers
self.features = nn.Sequential(*features)
# building classifier
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.classifier = nn.Sequential(
nn.Dropout(0.2),
nn.Linear(last_channel, num_classes)#全连接 论文是卷积
)
# weight initialization
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out')
if m.bias is not None:
nn.init.zeros_(m.bias)
elif isinstance(m, nn.BatchNorm2d):
nn.init.ones_(m.weight)
nn.init.zeros_(m.bias)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.zeros_(m.bias)
def forward(self, x):
x = self.features(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)#
x = self.classifier(x)
return x
MobileNet V3
from typing import Callable, List, Optional
import torch
from torch import nn, Tensor
from torch.nn import functional as F
from functools import partial
def _make_divisible(ch, divisor=8, min_ch=None):
"""
This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8
It can be seen here:
https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
"""
if min_ch is None:
min_ch = divisor
new_ch = max(min_ch, int(ch + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_ch < 0.9 * ch:
new_ch += divisor
return new_ch
class ConvBNActivation(nn.Sequential):
def __init__(self,
in_planes: int,
out_planes: int,
kernel_size: int = 3,
stride: int = 1,
groups: int = 1,
norm_layer: Optional[Callable[..., nn.Module]] = None,
activation_layer: Optional[Callable[..., nn.Module]] = None):
padding = (kernel_size - 1) // 2
if norm_layer is None:
norm_layer = nn.BatchNorm2d
if activation_layer is None:
activation_layer = nn.ReLU6
super(ConvBNActivation, self).__init__(nn.Conv2d(in_channels=in_planes,
out_channels=out_planes,
kernel_size=kernel_size,
stride=stride,
padding=padding,
groups=groups,
bias=False),
norm_layer(out_planes),
activation_layer(inplace=True))
class SqueezeExcitation(nn.Module):
def __init__(self, input_c: int, squeeze_factor: int = 4):
super(SqueezeExcitation, self).__init__()
squeeze_c = _make_divisible(input_c // squeeze_factor, 8)
self.fc1 = nn.Conv2d(input_c, squeeze_c, 1)
self.fc2 = nn.Conv2d(squeeze_c, input_c, 1)
def forward(self, x: Tensor) -> Tensor:
scale = F.adaptive_avg_pool2d(x, output_size=(1, 1))
scale = self.fc1(scale)
scale = F.relu(scale, inplace=True)
scale = self.fc2(scale)
scale = F.hardsigmoid(scale, inplace=True)
return scale * x
class InvertedResidualConfig:
def __init__(self,
input_c: int,
kernel: int,
expanded_c: int,
out_c: int,
use_se: bool,
activation: str,
stride: int,
width_multi: float):
self.input_c = self.adjust_channels(input_c, width_multi)
self.kernel = kernel
self.expanded_c = self.adjust_channels(expanded_c, width_multi)
self.out_c = self.adjust_channels(out_c, width_multi)
self.use_se = use_se
self.use_hs = activation == "HS" # whether using h-swish activation
self.stride = stride
@staticmethod
def adjust_channels(channels: int, width_multi: float):
return _make_divisible(channels * width_multi, 8)
class InvertedResidual(nn.Module):
def __init__(self,
cnf: InvertedResidualConfig,
norm_layer: Callable[..., nn.Module]):
super(InvertedResidual, self).__init__()
if cnf.stride not in [1, 2]:
raise ValueError("illegal stride value.")
self.use_res_connect = (cnf.stride == 1 and cnf.input_c == cnf.out_c)
layers: List[nn.Module] = []
activation_layer = nn.Hardswish if cnf.use_hs else nn.ReLU
# expand
if cnf.expanded_c != cnf.input_c:
layers.append(ConvBNActivation(cnf.input_c,
cnf.expanded_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=activation_layer))
# depthwise
layers.append(ConvBNActivation(cnf.expanded_c,
cnf.expanded_c,
kernel_size=cnf.kernel,
stride=cnf.stride,
groups=cnf.expanded_c,
norm_layer=norm_layer,
activation_layer=activation_layer))
if cnf.use_se:
layers.append(SqueezeExcitation(cnf.expanded_c))
# project
layers.append(ConvBNActivation(cnf.expanded_c,
cnf.out_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=nn.Identity))
self.block = nn.Sequential(*layers)
self.out_channels = cnf.out_c
self.is_strided = cnf.stride > 1
def forward(self, x: Tensor) -> Tensor:
result = self.block(x)
if self.use_res_connect:
result += x
return result
class MobileNetV3(nn.Module):
def __init__(self,
inverted_residual_setting: List[InvertedResidualConfig],
last_channel: int,
num_classes: int = 1000,
block: Optional[Callable[..., nn.Module]] = None,
norm_layer: Optional[Callable[..., nn.Module]] = None):
super(MobileNetV3, self).__init__()
if not inverted_residual_setting:
raise ValueError("The inverted_residual_setting should not be empty.")
elif not (isinstance(inverted_residual_setting, List) and
all([isinstance(s, InvertedResidualConfig) for s in inverted_residual_setting])):
raise TypeError("The inverted_residual_setting should be List[InvertedResidualConfig]")
if block is None:
block = InvertedResidual
if norm_layer is None:
norm_layer = partial(nn.BatchNorm2d, eps=0.001, momentum=0.01)
layers: List[nn.Module] = []
# building first layer
firstconv_output_c = inverted_residual_setting[0].input_c
layers.append(ConvBNActivation(3,
firstconv_output_c,
kernel_size=3,
stride=2,
norm_layer=norm_layer,
activation_layer=nn.Hardswish))
# building inverted residual blocks
for cnf in inverted_residual_setting:
layers.append(block(cnf, norm_layer))
# building last several layers
lastconv_input_c = inverted_residual_setting[-1].out_c
lastconv_output_c = 6 * lastconv_input_c
layers.append(ConvBNActivation(lastconv_input_c,
lastconv_output_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=nn.Hardswish))
self.features = nn.Sequential(*layers)
self.avgpool = nn.AdaptiveAvgPool2d(1)
self.classifier = nn.Sequential(nn.Linear(lastconv_output_c, last_channel),
nn.Hardswish(inplace=True),
nn.Dropout(p=0.2, inplace=True),
nn轻量化网络总结[2]--ShuffleNetv1/v2，OSNet，GHostNet