【深度学习实战（38）】模型结构之deeplabv3+

一、deeplabv3+结构图

二、deeplabv3+结构搭建

（1）选取backbone
图像输入进模型，经过backbone输出16倍和4倍（Low-Level Features）的特征图。

class MobileNetV2(nn.Module):
    def __init__(self, downsample_factor=8, pretrained=True):
        super(MobileNetV2, self).__init__()
        from functools import partial
        
        model           = mobilenetv2(pretrained)
        self.features   = model.features[:-1]

        self.total_idx  = len(self.features)
        self.down_idx   = [2, 4, 7, 14]

        if downsample_factor == 8:
            for i in range(self.down_idx[-2], self.down_idx[-1]):
                self.features[i].apply(
                    partial(self._nostride_dilate, dilate=2)
                )
            for i in range(self.down_idx[-1], self.total_idx):
                self.features[i].apply(
                    partial(self._nostride_dilate, dilate=4)
                )
        elif downsample_factor == 16:
            for i in range(self.down_idx[-1], self.total_idx):
                self.features[i].apply(
                    partial(self._nostride_dilate, dilate=2)
                )
        
    def _nostride_dilate(self, m, dilate):
        classname = m.__class__.__name__
        if classname.find('Conv') != -1:
            if m.stride == (2, 2):
                m.stride = (1, 1)
                if m.kernel_size == (3, 3):
                    m.dilation = (dilate//2, dilate//2)
                    m.padding = (dilate//2, dilate//2)
            else:
                if m.kernel_size == (3, 3):
                    m.dilation = (dilate, dilate)
                    m.padding = (dilate, dilate)

    def forward(self, x):
        low_level_features = self.features[:4](x)
        x = self.features[4:](low_level_features)
        return low_level_features, x 

(2)处理4倍（Low-Level Features）下采样特征图

• 降维

        #----------------------------------#
        #   浅层特征边
        #----------------------------------#
        self.shortcut_conv = nn.Sequential(
            nn.Conv2d(low_level_channels, 48, 1),
            nn.BatchNorm2d(48),
            nn.ReLU(inplace=True)
        )
        
low_level_features = self.shortcut_conv(low_level_features)

(3)处理16倍（Hign-Level Features）下采样特征图

• 施加由空洞卷积组成的APSS结构

 self.aspp = ASPP(dim_in=in_channels, dim_out=256, rate=16//downsample_factor)
  x = self.aspp(x)

#-----------------------------------------#
#   ASPP特征提取模块
#   利用不同膨胀率的膨胀卷积进行特征提取
#-----------------------------------------#
class ASPP(nn.Module):
	def __init__(self, dim_in, dim_out, rate=1, bn_mom=0.1):
		super(ASPP, self).__init__()
		self.branch1 = nn.Sequential(
				nn.Conv2d(dim_in, dim_out, 1, 1, padding=0, dilation=rate,bias=True),
				nn.BatchNorm2d(dim_out, momentum=bn_mom),
				nn.ReLU(inplace=True),
		)
		self.branch2 = nn.Sequential(
				nn.Conv2d(dim_in, dim_out, 3, 1, padding=6*rate, dilation=6*rate, bias=True),
				nn.BatchNorm2d(dim_out, momentum=bn_mom),
				nn.ReLU(inplace=True),	
		)
		self.branch3 = nn.Sequential(
				nn.Conv2d(dim_in, dim_out, 3, 1, padding=12*rate, dilation=12*rate, bias=True),
				nn.BatchNorm2d(dim_out, momentum=bn_mom),
				nn.ReLU(inplace=True),	
		)
		self.branch4 = nn.Sequential(
				nn.Conv2d(dim_in, dim_out, 3, 1, padding=18*rate, dilation=18*rate, bias=True),
				nn.BatchNorm2d(dim_out, momentum=bn_mom),
				nn.ReLU(inplace=True),	
		)
		self.branch5_conv = nn.Conv2d(dim_in, dim_out, 1, 1, 0,bias=True)
		self.branch5_bn = nn.BatchNorm2d(dim_out, momentum=bn_mom)
		self.branch5_relu = nn.ReLU(inplace=True)

		self.conv_cat = nn.Sequential(
				nn.Conv2d(dim_out*5, dim_out, 1, 1, padding=0,bias=True),
				nn.BatchNorm2d(dim_out, momentum=bn_mom),
				nn.ReLU(inplace=True),		
		)

	def forward(self, x):
		[b, c, row, col] = x.size()
        #-----------------------------------------#
        #   一共五个分支
        #-----------------------------------------#
		conv1x1 = self.branch1(x)
		conv3x3_1 = self.branch2(x)
		conv3x3_2 = self.branch3(x)
		conv3x3_3 = self.branch4(x)
        #-----------------------------------------#
        #   第五个分支，全局平均池化+卷积
        #-----------------------------------------#
		global_feature = torch.mean(x,2,True)
		global_feature = torch.mean(global_feature,3,True)
		global_feature = self.branch5_conv(global_feature)
		global_feature = self.branch5_bn(global_feature)
		global_feature = self.branch5_relu(global_feature)
		global_feature = F.interpolate(global_feature, (row, col), None, 'bilinear', True)
		
        #-----------------------------------------#
        #   将五个分支的内容堆叠起来
        #   然后1x1卷积整合特征。
        #-----------------------------------------#
		feature_cat = torch.cat([conv1x1, conv3x3_1, conv3x3_2, conv3x3_3, global_feature], dim=1)
		result = self.conv_cat(feature_cat)
		return result

• 将16倍下采样高阶特征进行4倍上采样，调整为和4倍下采样低阶特征同样的尺寸

x = F.interpolate(x, size=(low_level_features.size(2), low_level_features.size(3)), mode='bilinear', align_corners=True)

(4)将高，低阶特征进行Cat拼接

x = self.cat_conv(torch.cat((x, low_level_features), dim=1))

        self.cat_conv = nn.Sequential(
            nn.Conv2d(48+256, 256, 3, stride=1, padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(inplace=True),
            nn.Dropout(0.5),

            nn.Conv2d(256, 256, 3, stride=1, padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(inplace=True),

            nn.Dropout(0.1),
        )

（5）将拼接后的特征进行降维为分割的类别数通道

x = self.cls_conv(x)

self.cls_conv = nn.Conv2d(256, num_classes, 1, stride=1)

（6）将得到的特征图进行4倍上采样，还原到和模型输入尺寸同样的大小，并返回

x = F.interpolate(x, size=(H, W), mode='bilinear', align_corners=True)
return x