上传网站需要什么软件,东莞互联网推广,微信订阅号怎么做网站,建公司网站VGG首先引入块的思想将模型通用模板化
VGG模型的特点
与AlexNet#xff0c;LeNet一样#xff0c;VGG网络可以分为两部分#xff0c;第一部分主要由卷积层和汇聚层组成#xff0c;第二部分由全连接层组成。
VGG有5个卷积块#xff0c;前两个块包含一个卷积层#xff0c…VGG首先引入块的思想将模型通用模板化
VGG模型的特点
与AlexNetLeNet一样VGG网络可以分为两部分第一部分主要由卷积层和汇聚层组成第二部分由全连接层组成。
VGG有5个卷积块前两个块包含一个卷积层后三个块包含两个卷积层。 2 * 1 3 * 2 8个卷积层和后面3个全连接层所以它被称为VGG11
AlexNet模型架构与VGG模型架构对比 import torch
from torch import nn
from d2l import torch as d2l
import time
# 卷积块函数
def vgg_block(num_convs,in_channels,out_channels):layers []for _ in range(num_convs):layers.append(nn.Conv2d(in_channels,out_channels,kernel_size3,padding1))layers.append(nn.ReLU())in_channels out_channelslayers.append(nn.MaxPool2d(kernel_size2,stride2))nn.Sequential(*layers)中的*layers将会展开layers列表将其中的每个层作为单独的参数传递给nn.Sequential函数以便构建一个顺序模型。return nn.Sequential(*layers)# 定义卷积块的输入输出
conv_arch ((1,64),(1,128),(2,256),(2,512),(2,512))# VGG有5个卷积块前两个块包含一个卷积层后三个块包含两个卷积层。 2 * 1 3 * 2 8个卷积层和后面3个全连接层所以它被称为VGG11
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(# 5个卷积块部分*conv_blks,nn.Flatten(),# 3个全连接部分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)
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])为了使用Fashion-MNIST数据集使用缩小VGG11的通道数的VGG11
# 由于VGG11比AlexNet计算量更大所以构建一个通道数校小的网络
ratio 4
# 样本数pair[0]不变通道数pair[1]缩小四倍
small_conv_arch [(pair[0],pair[1] // ratio) for pair in 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)Sequential output shape: torch.Size([1, 16, 112, 112])
Sequential output shape: torch.Size([1, 32, 56, 56])
Sequential output shape: torch.Size([1, 64, 28, 28])
Sequential output shape: torch.Size([1, 128, 14, 14])
Sequential output shape: torch.Size([1, 128, 7, 7])
Flatten output shape: torch.Size([1, 6272])
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])开始计时
start_time time.time()
lr,num_epochs,batch_size 0.05,10,128
train_iter,test_iter d2l.load_data_fashion_mnist(batch_size,resize224)
d2l.train_ch6(net,train_iter,test_iter,num_epochs,lr,d2l.try_gpu())
时间结束
end_time time.time()
run_time end_time - start_time
# 将输出的秒数保留两位小数
print(f{round(run_time,2)}s)
