Pytorch框架下的语义分割实战（二，网络搭建）

接上一篇

Pytorch框架下的语义分割实战（数据集处理）

接着聊聊FCN.py中的小细节的吧。。。

先附上代码

# -*- coding: utf-8 -*-
"""
FCN.py
"""
import torch.nn as nn
from torchvision.models.vgg import VGG

#继承nn.Module，撰写自己的网络层
class FCNs(nn.Module):
    '''
    类FCNs：将最后一个特征图直接上采样32倍(5次步长为2、卷积核为3*3的反卷积操作)得到的最终
    分割结果。
    '''
    def __init__(self, pretrained_net, n_class):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        
        self.relu = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, 
                                          padding=1, dilation=1, 
                                          output_padding=1)
        self.bn1 = nn.BatchNorm2d(512)
       
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, 
                                          padding=1, dilation=1, 
                                          output_padding=1)
        self.bn2 = nn.BatchNorm2d(256)
        
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, 
                                          padding=1, dilation=1, 
                                          output_padding=1)
        self.bn3 = nn.BatchNorm2d(128)
        
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, 
                                          padding=1, dilation=1, 
                                          output_padding=1)
        self.bn4 = nn.BatchNorm2d(64)
        
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, 
                                          padding=1, dilation=1, 
                                          output_padding=1)
        self.bn5 = nn.BatchNorm2d(32)
        
        #分类器是1*1大小的卷积，将channel个数从32减小到n_class
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1) 

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  
        x4 = output['x4']  
        x3 = output['x3']  
        x2 = output['x