# VGG
论文: very deep convolutional networks for large-scale image recognition by Karen Simonyan, et al
1. 模型:
图片来源:动手学深度学习
2. 代码:
# 代码来自动手学深度学习 by 李沐
import torch
from torch import nn
from d2l import torch as d2l
def 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_channels
layers.append(nn.MaxPool2d(2, stride=2))
return nn.Sequential(*layers)
conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))
def vgg_my(conv_arch):
conv_blocks = []
in_channels = 1
for num_convs, out_channels in conv_arch:
conv_blocks.append(vgg_block(num_convs, in_channels, out_channels))
in_channels = out_channels
return nn.Sequential(*conv_blocks, nn.Flatten(),
nn.Linear(out_channels * 7 * 7, 4096), nn.ReLU(), nn.Dropout(0.5),
nn.Linear(4096, 4096), nn.ReLU(), nn.Dropout(0.5),
nn.Linear(4096, 10)
)
X = torch.rand((1, 1, 224, 224)) #高宽减半,通道数翻倍
for layer in vgg_my(conv_arch):
X = layer(X)
print(layer.__class__.__name__,":", X.shape)
net = vgg_my(conv_arch)
ratio = 4 #因通道数过大,故设计一个较小的VGG
small_conv_arch = [(pair[0], pair[1] // ratio) for pair in conv_arch]
net = vgg_my(small_conv_arch)
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())