注:书中对代码的讲解并不详细,本文对很多细节做了详细注释。另外,书上的源代码是在Jupyter Notebook上运行的,较为分散,本文将代码集中起来,并加以完善,全部用vscode在python 3.9.18下测试通过,同时对于书上部分章节也做了整合。
Chapter7 Modern Convolutional Neural Networks
7.2 Network Using Blocks: VGG
import matplotlib.pyplot as plt
import torch
from torch import nn
from d2l import torch as d2ldef vgg_block(num_convs, in_channels, out_channels):layers = []for _ in range(num_convs):layers.append(nn.Conv2d(in_channels, out_channels,kernel_size=3, padding=1))layers.append(nn.ReLU())in_channels = out_channelslayers.append(nn.MaxPool2d(kernel_size=2,stride=2))return nn.Sequential(*layers)#可变参数#指定每个vgg块的卷积层个数和输出通道个数
conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))def vgg(conv_arch):conv_blks = []in_channels = 1# 卷积层部分for (num_convs, out_channels) in conv_arch:conv_blks.append(vgg_block(num_convs, in_channels, out_channels))in_channels = out_channelsreturn nn.Sequential(*conv_blks, nn.Flatten(),# 全连接层部分nn.Linear(out_channels * 7 * 7, 4096), nn.ReLU(), nn.Dropout(0.5),#the spatial dimensions of the input tensor after the convolutional blocks are reduced to 7x7nn.Linear(4096, 4096), nn.ReLU(), nn.Dropout(0.5),nn.Linear(4096, 10))net = vgg(conv_arch)
X = torch.randn(size=(1, 1, 224, 224))
for blk in net:X = blk(X)print(blk.__class__.__name__,'output shape:\t',X.shape)ratio = 4
small_conv_arch = [(pair[0], pair[1] // ratio) for pair in conv_arch]#由于VGG-11比AlexNet计算量更大,因此构建一个通道数较少的网络
net = vgg(small_conv_arch)#训练
lr, num_epochs, batch_size = 0.05, 10, 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())
plt.show()
训练结果:
参考文献:VGG原始论文