《动手学深度学习》(PyTorch版)代码注释 - 24 【VGG_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5.7节
此节功能为：使用重复元素的网络（VGG）
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
# 5.7 使用重复元素的网络（VGG）
#注释：黄文俊
#邮箱：hurri_cane@qq.com


import time
import torch
from torch import nn, optim

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

def vgg_block(num_convs, in_channels, out_channels):    # 卷积层个数和输入输出通道数
    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())
    blk.append(nn.MaxPool2d(kernel_size=2, stride=2)) # 这里会使宽高减半
    return nn.Sequential(*blk)

conv_arch = ((1, 1, 64), (1, 64, 128), (2, 128, 256), (2, 256, 512), (2, 512, 512))
# 经过5个vgg_block, 宽高会减半5次, 变成 224/32 = 7
fc_features = 512 * 7 * 7 # c * w * h
fc_hidden_units = 4096 # 任意

def vgg(conv_arch, fc_features, fc_hidden_units=4096):
    net = nn.Sequential()
    # 卷积层部分
    for i, (num_convs, in_channels, out_channels) in enumerate(conv_arch):
        # 每经过一个vgg_block都会使宽高减半
        net.add_module("vgg_block_" + str(i+1), vgg_block(num_convs, in_channels, out_channels))
    # 全连接层部分
    net.add_module("fc", nn.Sequential(d2l.FlattenLayer(),
                                 nn.Linear(fc_features, fc_hidden_units),
                                 nn.ReLU(),
                                 nn.Dropout(0.5),
                                 nn.Linear(fc_hidden_units, fc_hidden_units),
                                 nn.ReLU(),
                                 nn.Dropout(0.5),
                                 nn.Linear(fc_hidden_units, 10)
                                ))
    return net

net = vgg(conv_arch, fc_features, fc_hidden_units)
X = torch.rand(1, 1, 224, 224)

# named_children获取一级子模块及其名字(named_modules会返回所有子模块,包括子模块的子模块)
for name, blk in net.named_children():
    X = blk(X)
    print(name, 'output shape: ', X.shape)



# 因为VGG-11计算上比AlexNet更加复杂，出于测试的目的我们构造一个通道数更小
# 或者说更窄的网络在Fashion-MNIST数据集上进行训练。

ratio = 8
small_conv_arch = [(1, 1, 64//ratio), (1, 64//ratio, 128//ratio), (2, 128//ratio, 256//ratio),
                   (2, 256//ratio, 512//ratio), (2, 512//ratio, 512//ratio)]
net = vgg(small_conv_arch, fc_features // ratio, fc_hidden_units // ratio)
print(net)


# 正式训练模型
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=224)

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)