动手学PyTorch（李沐）16 ---- 使用块的网络VGG

最新推荐文章于 2024-10-02 08:41:51 发布

qq_46381729

最新推荐文章于 2024-10-02 08:41:51 发布

阅读量51

点赞数

分类专栏：深度学习文章标签： pytorch 人工智能 python 机器学习深度学习

本文链接：https://blog.csdn.net/qq_46381729/article/details/133275953

版权

深度学习专栏收录该内容

24 篇文章 4 订阅

订阅专栏

本文介绍了VGG网络的设计原理，它是基于AlexNet的扩展，通过vgg_block构建更深更大的卷积结构。通过实例展示了如何使用PyTorch实现VGG网络并进行Fashion-MNIST数据集的训练。

摘要由CSDN通过智能技术生成

在这里插入图片描述
VGG的设计思路就是比AlexNet更深更大。

VGG块就是封装了AlexNet的三个卷积层加上一个池化层

VGG可以理解为一个更大更深的AlexNet

使用块的网络

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

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

  return 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))

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)

在这里插入图片描述
模型训练

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())