《动手学深度学习》(PyTorch版)代码注释 - 30 【DenseNet_Learning】

说明

本博客代码来自开源项目：《动手学深度学习》(PyTorch版)
并且在博主学习的理解上对代码进行了大量注释，方便理解各个函数的原理和用途

配置环境

使用环境：python3.8
平台：Windows10
IDE：PyCharm

此节说明

此节对应书本上5.12节
此节功能为：稠密连接网络（DenseNet）
由于次节相对容易理解，代码注释量较少

代码

# 本书链接https://tangshusen.me/Dive-into-DL-PyTorch/#/chapter03_DL-basics/3.8_mlp
# 5.11 残差网络（ResNet）
# 注释：黄文俊
# E-mail：hurri_cane@qq.com

import time
import torch
from torch import nn, optim
import torch.nn.functional as F

import sys
sys.path.append("..")
import d2lzh_pytorch as d2l
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')


# DenseNet的主要构建模块是稠密块（dense block）和过渡层（transition layer）。
# 前者定义了输入和输出是如何连结的，后者则用来控制通道数，使之不过大。
def conv_block(in_channels, out_channels):
    blk = nn.Sequential(nn.BatchNorm2d(in_channels),
                        nn.ReLU(),
                        nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1))
    return blk


class DenseBlock(nn.Module):
    def __init__(self, num_convs, in_channels, out_channels):
        super(DenseBlock, self).__init__()
        net = []
        for i in range(num_convs):
            in_c = in_channels + i * out_channels
            net.append(conv_block(in_c, out_channels))
        self.net = nn.ModuleList(net)
        self.out_channels = in_channels + num_convs * out_channels # 计算输出通道数

    def forward(self, X):
        for blk in self.net:
            Y = blk(X)
            X = torch.cat((X, Y), dim=1)  # 在通道维上将输入和输出连结
        return X


blk1 = DenseBlock(2, 3, 10)
X = torch.rand(4, 3, 8, 8)
Y = blk1(X)
print(Y.shape)

# 5.12.2 过渡层
# 通过1×1卷积层来减小通道数，并使用步幅为2的平均池化层减半高和宽，从而进一步降低模型复杂度。
def transition_block(in_channels, out_channels):
    blk = nn.Sequential(
            nn.BatchNorm2d(in_channels),
            nn.ReLU(),
            nn.Conv2d(in_channels, out_channels, kernel_size=1),
            nn.AvgPool2d(kernel_size=2, stride=2))  # 平均池化
    return blk

blk = transition_block(23, 10)
print(blk(Y).shape)


# 构造DenseNet模型

net = nn.Sequential(
        nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
        nn.BatchNorm2d(64),
        nn.ReLU(),
        nn.MaxPool2d(kernel_size=3, stride=2, padding=1))


num_channels, growth_rate = 64, 32  # num_channels为当前的通道数
num_convs_in_dense_blocks = [4, 4, 4, 4]

for i, num_convs in enumerate(num_convs_in_dense_blocks):
    DB = DenseBlock(num_convs, num_channels, growth_rate)
    net.add_module("DenseBlosk_%d" % i, DB)
    # 上一个稠密块的输出通道数
    num_channels = DB.out_channels
    # 在稠密块之间加入通道数减半的过渡层
    if i != len(num_convs_in_dense_blocks) - 1:
        net.add_module("transition_block_%d" % i, transition_block(num_channels, num_channels // 2))
        num_channels = num_channels // 2


# 最后接上全局池化层和全连接层来输出
net.add_module("BN", nn.BatchNorm2d(num_channels))
net.add_module("relu", nn.ReLU())
net.add_module("global_avg_pool", d2l.GlobalAvgPool2d()) # GlobalAvgPool2d的输出: (Batch, num_channels, 1, 1)
net.add_module("fc", nn.Sequential(d2l.FlattenLayer(), nn.Linear(num_channels, 10)))

X = torch.rand((1, 1, 96, 96))
for name, layer in net.named_children():
    X = layer(X)
    print(name, ' output shape:\t', X.shape)

batch_size = 256
# 如出现“out of memory”的报错信息，可减小batch_size或resize
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=96)

lr, num_epochs = 0.001, 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
d2l.train_ch5(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs)



print("*"*50)