李沐25_使用块的网络VGG——自学笔记

VGG架构

1.多个VGG块后接全连接层

2.不同次数的重复块得到不同的架构 VGG-16、VGG-19

3.更大更深的AlexNet

##经典卷积神经网络的基本组成部分是下面的这个序列：

1.带填充以保持分辨率的卷积层；

2.非线性激活函数，如ReLU；

3.汇聚层，如最大汇聚层。

代码实现VGG块

定义了一个名为vgg_block的函数来实现一个VGG块，3X3卷积核、填充为1（保持高度和宽度）的卷积层，和带有2X2汇聚窗口、步幅为2（每个块后的分辨率减半）的最大汇聚层。

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(kernel_size=2,stride=2))
    return nn.Sequential(*layers)

VGG网络

5大块：每一块相当于高宽减半.(卷积，通道数)

conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))

VGG-11

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_channels

    return 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),
        nn.Linear(4096, 4096), nn.ReLU(), nn.Dropout(0.5),
        nn.Linear(4096, 10))

net = vgg(conv_arch)

构建一个高度和宽度为224的单通道数据样本，以观察每个层输出的形状。

X = torch.randn(size=(1, 1, 224, 224))
for blk in net:
    X = blk(X)
    print(blk.__class__.__name__,'output shape:\t',X.shape)

Sequential output shape:	 torch.Size([1, 64, 112, 112])
Sequential output shape:	 torch.Size([1, 128, 56, 56])
Sequential output shape:	 torch.Size([1, 256, 28, 28])
Sequential output shape:	 torch.Size([1, 512, 14, 14])
Sequential output shape:	 torch.Size([1, 512, 7, 7])
Flatten output shape:	 torch.Size([1, 25088])
Linear output shape:	 torch.Size([1, 4096])
ReLU output shape:	 torch.Size([1, 4096])
Dropout output shape:	 torch.Size([1, 4096])
Linear output shape:	 torch.Size([1, 4096])
ReLU output shape:	 torch.Size([1, 4096])
Dropout output shape:	 torch.Size([1, 4096])
Linear output shape:	 torch.Size([1, 10])

训练模型

由于VGG-11比AlexNet计算量更大，因此我们构建了一个通道数较少的网络，足够用于训练Fashion-MNIST数据集

ratio = 4
small_conv_arch = [(pair[0], pair[1] // ratio) for pair in conv_arch] # 所有通道数都➗4，计算量减少16倍，但是计算时间更长
net = vgg(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())

loss 0.178, train acc 0.934, test acc 0.904
791.2 examples/sec on cuda:0