1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
|
import time
import torch
from torch import nn, optim
def vgg_block(num_convs,in_channels,out_channels):
"""定义vgg块
Args:
num_convs (int): 需要卷积层数量
in_channels (int): 输入通道数
out_channels (int): 输出通道数
"""
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(kernel_size=2,stride=2))
return nn.Sequential(*layers)
# 实现vgg架构,vgg含有5个vgg块
conv_arch = (
(1,64),
(1,128),
(2,256),
(2,512),
(2,512),
)
def vgg(conv_arch):
conv_blks = []
in_channels = 1
for (num_convs,out_channels) in conv_arch:
conv_blks.append(
vgg_block(num_convs,in_channels,out_channels)
)
in_channels = out_channels
net = nn.Sequential(
*conv_blks,
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)
)
return net
net = vgg(conv_arch)
# 经典设计模式，每次图片大小缩小一半 通道数增加一杯
X = torch.randn(size=(1, 1, 224, 224))
for blk in net:
X = blk(X)
print(blk.__class__.__name__,'output shape:\t',X.shape)
# 这里是作为演示，因为VGG-11比AlexNet计算量更大，因此我们构建一个通道数较少的神经网络
ratio = 4
small_conv_arch = [(pair[0], pair[1] // ratio) for pair in conv_arch]
print(small_conv_arch)
net = vgg(small_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)
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())
|
