deeplabv3+及pytorch实现

deeplab系列

DeepLabV3+ 基本原理及Pytorch版注解

以下参考：【语义分割系列】deeplabv3相关知识点以及pytorch实现（ASSP模块）

 

class ASPP(nn.Module):
    def __init__(self, num_classes):
        super(ASPP, self).__init__()

        self.conv_1x1_1 = nn.Conv2d(2048, 256, kernel_size=1)
        self.bn_conv_1x1_1 = nn.BatchNorm2d(256)

        self.conv_3x3_1 = nn.Conv2d(2048, 256, kernel_size=3, stride=1, padding=6, dilation=6)
        self.bn_conv_3x3_1 = nn.BatchNorm2d(256)

        self.conv_3x3_2 = nn.Conv2d(2048, 256, kernel_size=3, stride=1, padding=12, dilation=12)
        self.bn_conv_3x3_2 = nn.BatchNorm2d(256)

        self.conv_3x3_3 = nn.Conv2d(2048, 256, kernel_size=3, stride=1, padding=18, dilation=18)
        self.bn_conv_3x3_3 = nn.BatchNorm2d(256)

        self.avg_pool = nn.AdaptiveAvgPool2d(1)

        self.conv_1x1_2 = nn.Conv2d(2048, 256, kernel_size=1)
        self.bn_conv_1x1_2 = nn.BatchNorm2d(256)

        self.conv_1x1_3 = nn.Conv2d(1280, 256, kernel_size=1) # (1280 = 5*256)
        self.bn_conv_1x1_3 = nn.BatchNorm2d(256)

        self.conv_1x1_4 = nn.Conv2d(256, num_classes, kernel_size=1)

    def forward(self, feature_map):
        # (feature_map has shape (batch_size, 2048, h/8, w/8))

        feature_map_h = feature_map.size()[2] # (h/8)
        feature_map_w = feature_map.size()[3] # (w/8)

        out_1x1 = F.relu(self.bn_conv_1x1_1(self.conv_1x1_1(feature_map))) # (shape: (batch_size, 256, h/8, w/8)) 对应图中 E
        out_3x3_1 = F.relu(self.bn_conv_3x3_1(self.conv_3x3_1(feature_map))) # (shape: (batch_size, 256, h/8, w/8)) 对应图中 D
        out_3x3_2 = F.relu(self.bn_conv_3x3_2(self.conv_3x3_2(feature_map))) # (shape: (batch_size, 256, h/8, w/8)) 对应图中 C
        out_3x3_3 = F.relu(self.bn_conv_3x3_3(self.conv_3x3_3(feature_map))) # (shape: (batch_size, 256, h/8, w/8)) 对应图中 B

        out_img = self.avg_pool(feature_map) # (shape: (batch_size, 512, 1, 1))对应图中 ImagePooling
        out_img = F.relu(self.bn_conv_1x1_2(self.conv_1x1_2(out_img))) # (shape: (batch_size, 256, 1, 1)) 
        out_img = F.upsample(out_img, size=(feature_map_h, feature_map_w), mode="bilinear") # (shape: (batch_size, 256, h/8, w/8))对应图中 A

        out = torch.cat([out_1x1, out_3x3_1, out_3x3_2, out_3x3_3, out_img], 1) # (shape: (batch_size, 1280, h/8, w/8)) cat对应图中 F 
        out = F.relu(self.bn_conv_1x1_3(self.conv_1x1_3(out))) # (shape: (batch_size, 256, h/8, w/8)) bn_conv_1x1_3对应图中 H  out 对应图中I
        out = self.conv_1x1_4(out) # (shape: (batch_size, num_classes, h/8, w/8))out 对应图中Upsample by 4

        return out

 

感觉有用的文章：用PyTorch搞定GluonCV预训练模型，这个计算机视觉库真的很好用