mobilenetv2模型主干部分有多少层卷积层？

MobileNetV2 模型主干部分包含了 16 个 bottleneck 模块，其中每个 bottleneck 模块包含了若干个卷积层。具体地，每个 bottleneck 模块由一个 1x1 的卷积层、一个 depthwise 卷积层和一个 1x1 的卷积层组成，因此，MobileNetV2 模型主干部分的卷积层数为 16 x 3 = 48。

相关问题

在pytorch环境中，使用mobilenetv2为主干网络的deeplabv3plus模型添加SE教程

1. 安装必要的库和模块

在使用SE模块之前，需要安装必要的库和模块，包括pytorch、torchvision和numpy等。可以使用pip或conda来安装。

!pip install torch torchvision numpy

2. 定义SE模块

SE模块包括两个部分：squeeze和excitation。squeeze部分是一个全局平均池化层，用于将特征图压缩成一个数值，excitation部分是一个全连接层，用于学习特征图的重要性权重。

import torch.nn as nn

class SEModule(nn.Module):
    def __init__(self, channels, reduction=16):
        super(SEModule, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Sequential(
            nn.Linear(channels, channels // reduction, bias=False),
            nn.ReLU(inplace=True),
            nn.Linear(channels // reduction, channels, bias=False),
            nn.Sigmoid()
        )

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avg_pool(x).view(b, c)
        y = self.fc(y).view(b, c, 1, 1)
        return x * y

3. 修改deeplabv3plus模型

在deeplabv3plus模型中，需要修改主干网络部分，将每个卷积层后添加一个SE模块。

import torchvision.models as models

class DeepLabV3Plus(nn.Module):
    def __init__(self, n_classes=21):
        super(DeepLabV3Plus, self).__init__()
        self.mobilenetv2 = models.mobilenet_v2(pretrained=True).features
        self.se_module1 = SEModule(24)
        self.se_module2 = SEModule(32)
        self.se_module3 = SEModule(96)
        self.se_module4 = SEModule(320)
        self.aspp = ASPP(320, [12, 24, 36])
        self.decoder = Decoder(n_classes)
        
    def forward(self, x):
        x_size = x.size()
        h, w = x_size[2], x_size[3]
        x = self.mobilenetv2(x)
        x = self.se_module1(x)
        x = self.mobilenetv2[3:6](x)
        x = self.se_module2(x)
        x = self.mobilenetv2[6](x)
        x = self.se_module3(x)
        x = self.mobilenetv2[7](x)
        x = self.se_module4(x)
        x = self.aspp(x)
        x = self.decoder(x, h, w)
        x = F.interpolate(x, size=x_size[2:], mode='bilinear', align_corners=False)
        return x

4. 模型训练和测试

使用修改后的模型进行训练和测试，可以使用与原模型相同的训练和测试代码。

model = DeepLabV3Plus(n_classes=21)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9, weight_decay=1e-4)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=30, gamma=0.1)

for epoch in range(num_epochs):
    for i, (inputs, labels) in enumerate(train_loader):
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

with torch.no_grad():
    for i, (inputs, labels) in enumerate(test_loader):
        outputs = model(inputs)
        _, preds = torch.max(outputs, 1)
        # do something with preds

mmsegmentation框架下给mobilenetv2主干加入SKNet

在`mmsegmentation`框架中，可以通过修改`mmseg/models/backbones/mobilenet_v2.py`文件来给`MobileNetV2`主干加入`SKNet`。下面是实现的步骤：

1. 首先需要导入`SKNet`的相关模块，可以在文件最上面添加以下代码：

from mmcv.cnn import build_conv_layer, build_norm_layer, build_plugin_layer
from ..builder import BACKBONES

2. 接着在`MobileNetV2`类中定义`SKNet`的结构，可以在`_make_stem_layer`函数中加入以下代码：

def _make_stem_layer(self, in_channels, stem_channels):
    layers = []
    layers.append(ConvModule(
        in_channels,
        stem_channels,
        3,
        stride=2,
        padding=1,
        bias=False,
        norm_cfg=dict(type='BN', momentum=0.1, eps=1e-5),
        activation='relu',
        inplace=True))
    in_channels = stem_channels

    layers.append(ConvModule(
        in_channels,
        in_channels,
        3,
        stride=1,
        padding=1,
        bias=False,
        norm_cfg=dict(type='BN', momentum=0.1, eps=1e-5),
        activation='relu',
        inplace=True))

    # add SKNet module
    channels = in_channels
    mid_channels = channels // 2
    squeeze_channels = max(1, mid_channels // 8)
    layers.append(
        build_plugin_layer(dict(
            type='SKConv',
            channels=channels,
            squeeze_channels=squeeze_channels,
            kernel_size=3,
            stride=1,
            padding=1,
            dilation=1,
            groups=32,
            sk_mode='two',
            norm_cfg=dict(type='BN', momentum=0.1, eps=1e-5),
            act_cfg=dict(type='ReLU', inplace=True),
        ),
        [build_conv_layer(
            dict(type='Conv2d'),
            channels,
            channels,
            kernel_size=3,
            stride=1,
            padding=1,
            bias=False),
        build_norm_layer(dict(type='BN', momentum=0.1, eps=1e-5), channels)[1]]))
    return nn.Sequential(*layers)

3. 最后在`BACKBONES`中注册`MobileNetV2`主干即可。完整代码如下：

import torch.nn as nn
from mmcv.cnn import ConvModule
from mmcv.cnn import build_conv_layer, build_norm_layer, build_plugin_layer
from ..builder import BACKBONES


@BACKBONES.register_module()
class MobileNetV2(nn.Module):
    def __init__(self,
                 widen_factor=1.0,
                 output_stride=32,
                 norm_cfg=dict(type='BN', momentum=0.1, eps=1e-5),
                 with_cp=False,
                 ):
        super(MobileNetV2, self).__init__()

        assert output_stride in [8, 16, 32]
        self.output_stride = output_stride
        self.with_cp = with_cp
        self.norm_cfg = norm_cfg

        input_channel = int(32 * widen_factor)
        self.stem = self._make_stem_layer(3, input_channel)

        self.layer1 = self._make_layer(
            input_channel, int(16 * widen_factor), 1, 1, 16, 2)
        self.layer2 = self._make_layer(
            int(16 * widen_factor), int(24 * widen_factor), 2, 6, 16, 2)
        self.layer3 = self._make_layer(
            int(24 * widen_factor), int(32 * widen_factor), 3, 6, 24, 2)
        self.layer4 = self._make_layer(
            int(32 * widen_factor), int(64 * widen_factor), 4, 6, 32, 2)
        self.layer5 = self._make_layer(
            int(64 * widen_factor), int(96 * widen_factor), 3, 6, 64, 1)
        self.layer6 = self._make_layer(
            int(96 * widen_factor), int(160 * widen_factor), 3, 6, 96, 1)
        self.layer7 = self._make_layer(
            int(160 * widen_factor), int(320 * widen_factor), 1, 6, 160, 1)

        if self.output_stride == 8:
            self.layer2[0].conv2.stride = (1, 1)
            self.layer2[0].downsample[0].stride = (1, 1)
            self.layer3[0].conv2.stride = (1, 1)
            self.layer3[0].downsample[0].stride = (1, 1)
        elif self.output_stride == 16:
            self.layer3[0].conv2.stride = (1, 1)
            self.layer3[0].downsample[0].stride = (1, 1)

        self._freeze_stages()

    def _make_stem_layer(self, in_channels, stem_channels):
        layers = []
        layers.append(ConvModule(
            in_channels,
            stem_channels,
            3,
            stride=2,
            padding=1,
            bias=False,
            norm_cfg=dict(type='BN', momentum=0.1, eps=1e-5),
            activation='relu',
            inplace=True))
        in_channels = stem_channels

        layers.append(ConvModule(
            in_channels,
            in_channels,
            3,
            stride=1,
            padding=1,
            bias=False,
            norm_cfg=dict(type='BN', momentum=0.1, eps=1e-5),
            activation='relu',
            inplace=True))

        # add SKNet module
        channels = in_channels
        mid_channels = channels // 2
        squeeze_channels = max(1, mid_channels // 8)
        layers.append(
            build_plugin_layer(dict(
                type='SKConv',
                channels=channels,
                squeeze_channels=squeeze_channels,
                kernel_size=3,
                stride=1,
                padding=1,
                dilation=1,
                groups=32,
                sk_mode='two',
                norm_cfg=dict(type='BN', momentum=0.1, eps=1e-5),
                act_cfg=dict(type='ReLU', inplace=True),
            ),
            [build_conv_layer(
                dict(type='Conv2d'),
                channels,
                channels,
                kernel_size=3,
                stride=1,
                padding=1,
                bias=False),
            build_norm_layer(dict(type='BN', momentum=0.1, eps=1e-5), channels)[1]]))
        return nn.Sequential(*layers)

    def _make_layer(self,
                    in_channels,
                    out_channels,
                    num_blocks,
                    stride,
                    t,
                    dilation=1):
        layers = []
        layers.append(InvertedResidual(
            in_channels,
            out_channels,
            stride,
            expand_ratio=t,
            dilation=dilation,
            norm_cfg=self.norm_cfg,
            with_cp=self.with_cp))
        for i in range(1, num_blocks):
            layers.append(InvertedResidual(
                out_channels,
                out_channels,
                1,
                expand_ratio=t,
                dilation=dilation,
                norm_cfg=self.norm_cfg,
                with_cp=self.with_cp))

        return nn.Sequential(*layers)

    def _freeze_stages(self):
        if self.output_stride == 8:
            self.stem.eval()
            for param in self.stem.parameters():
                param.requires_grad = False
        elif self.output_stride == 16:
            self.stem[0].eval()
            self.stem[1].eval()
            for param in self.stem[0].parameters():
                param.requires_grad = False
            for param in self.stem[1].parameters():
                param.requires_grad = False

这样就给`MobileNetV2`主干加入了`SKNet`结构。