Segnet论文阅读笔记：代码与细节理解

Segnet论文阅读笔记

代码参考：
SegNet From Scratch Using PyTorch | by Nikdenof | Medium

网络结构

编码器

CNNBlock

蓝色层：Conv+Batch Normalisation+ReLU

• cov：k=3,p=1,s=1, out channel=2*in_channel

import torch
import torch.nn as nn

class ConvBNReLU(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size=3, stride=1, padding=1):
        super(ConvBNReLU, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding)
        self.bn = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)

    def forward(self, x):
        x = self.conv(x)      # Apply convolution
        x = self.bn(x)        # Apply batch normalization
        x = self.relu(x)      # Apply ReLU activation
        return x

绿色：池化
nn.MaxPool2d(kernek_size=2,stride=2,return_indices=True)
这里的return indices=True是为了后续的池化索引。

Encoder Block

class EncoderBlock(nn.Module):  
	def __init__(self, in_c, out_c, depth=2, kernel_size=3, padding=1) -> None: