（19）语义分割（5）_FCN基于VGG16的实现

1、主要参考

（1）基础框架使用了

https://github.com/WZMIAOMIAO/deep-learning-for-image-processing

（2）VGG16使用了

Pytorch搭建FCN网络_金渐层猫的博客-CSDN博客_pytorch 实现fcn

2、VGGbackbone代码

2.1原理 

（1）原理见教程17

（17）语义分割（2）_FCN的原理_chencaw的博客-CSDN博客

（2） 

 （3）

 （4）

 2.2 骨干网络

（1）注意网络的FC6和FC7的输出在实现的时候没有使用Dropout，size也使用了1。

（2）当然我们也可以安装上图的方法去实现

from torch import nn
from torchvision.models import vgg16
 
def vgg_block(num_convs, in_channels, out_channels):
    blk = []
    for i in range(num_convs):
        if i == 0:
            blk.append(nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1))
        else:
            blk.append(nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1))
        blk.append(nn.ReLU(inplace=True))
    blk.append(nn.MaxPool2d(kernel_size=2, stride=2))  # 宽高减半
    return blk
 
class VGG16(nn.Module):
    def __init__(self, pretrained=True):
        super(VGG16, self).__init__()
        features = []
        features.extend(vgg_block(2, 3, 64))
        features.extend(vgg_block(2, 64, 128))
        features.extend(vgg_block(3, 128, 256))
        self.index_pool3 = len(features)
        features.extend(vgg_block(3, 256, 512))
        self.index_pool4 = len(features)
        features.extend(vgg_block(3, 512, 512))
        self.features = nn.Sequential(*features)
 
        self.conv6 = nn.Conv2d(512, 4096, kernel_size=1)
        self.relu = nn.ReLU(inplace=True)
        self.conv7 = nn.Conv2d(4096, 4096, kernel_size=1)
 
        # load pretrained params from torchvision.models.vgg16(pretrained=True)
        if pretrained:
            pretrained_model = vgg16(pretrained=pretrained)
            pretrained_params = pretrained_model.state_dict()
            keys = list(pretrained_params.keys())
            new_dict = {}
            for index, key in enumerate(self.features.state_dict().keys()):
                new_dict[key] = pretrained_params[keys[index]]
            self.features.load_state_dict(new_dict)
 
    def forward(self, x):
        pool3 = self.features[:self.index_pool3](x)      # 1/8
        pool4 = self.features[self.index_pool3:self.index_pool4](pool3)  # 1/16
        pool5 = self.features[self.index_pool4:](pool4)  # 1/32
 
        conv6 = self.relu(self.conv6(pool5))  # 1/32
        conv7 = self.relu(self.conv7(conv6))  # 1/32
 
        return pool3, pool4, conv7

3、FCN-32s的实现

（1）注意接在了conv7的输出上

（2）代码实现，注意输入图像的尺寸必须是32 的整数倍

from operator import imod
from src.vgg_backbone import VGG16
import torch.nn as nn
 
 
class FCN_32S(nn.Module):
    def __init__(self, num_classes, backbone='vgg'):
        super(FCN_32S, self).__init__()
        if backbone == 'vgg':
            self.features = VGG16()
 
        self.scores1 = nn.Conv2d(4096, num_classes, kernel_size=1)
        self.relu = nn.ReLU(inplace=True)
        self.scores2 = nn.Conv2d(512, num_classes, kernel_size=1)
        self.scores3 = nn.Conv2d(256, num_classes, kernel_size=1)
       
        # torch.nn.ConvTranspose2d(in_channels, out_channels, kernel_size,
        #                   stride=1, padding=0, output_padding=0,
        #                   groups=1, bias=True, dilation=1, padding_mode='zeros')
 
        #输入图像是32的整数倍，如：224  输入模块前的h = 8 ,w = 8
        #公式：h_out=(h−1)×stride[0]−2×padding[0]+dilation[0]×(kernel_size[0]−1)+output_padding[0]+1
        # 计算   h_out = (h-1)*stride  + kernel
 
        self.upsample_32x = nn.ConvTranspose2d(num_classes, num_classes, kernel_size=32, stride=32)
        self.upsample_8x = nn.ConvTranspose2d(num_classes, num_classes, kernel_size=8, stride=8)
        self.upsample_4x = nn.ConvTrans