CIFAR-10 model structure
![神经网络-搭建小实战和Sequential的使用_第1张图片](http://img.e-com-net.com/image/info8/106dd6022546422db4aa925dbe5bf625.jpg)
通过已知参数(高、宽、dilation=1、kernel_size)推断stride和padding的大小
![神经网络-搭建小实战和Sequential的使用_第2张图片](http://img.e-com-net.com/image/info8/6f69fd322fb245eaa5118ebb9e3304db.jpg)
网络
import torch
from torch import nn
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.conv1 = nn.Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2)
self.maxpool1 = nn.MaxPool2d(kernel_size=2)
self.conv2 = nn.Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2)
self.maxpool2 = nn.MaxPool2d(2)
self.conv3 = nn.Conv2d(32, 64, 5,padding=2)
self.maxpool3 = nn.MaxPool2d(2)
self.flatten = nn.Flatten()
self.linear1 = nn.Linear(1024, 64)
self.linear2 = nn.Linear(64, 10)
def forward(self, x):
x = self.conv1(x)
x = self.maxpool1(x)
x = self.conv2(x)
x = self.maxpool2(x)
x = self.conv3(x)
x = self.maxpool3(x)
x = self.flatten(x)
x = self.linear1(x)
x = self.linear2(x)
return x
tudui = Tudui()
print(tudui)
![神经网络-搭建小实战和Sequential的使用_第3张图片](http://img.e-com-net.com/image/info8/975c2e266909430da03bfd1894567c8e.jpg)
对网络进行检验
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)
![在这里插入图片描述](http://img.e-com-net.com/image/info8/30080b003fd44386aee0a09fb624ab4f.jpg)
线性层如果不知道输入特征是多少,注释掉线性层,查看输入特征(这里是1024)
![在这里插入图片描述](http://img.e-com-net.com/image/info8/aa16814003d44c399c62ed654df6ed40.jpg)
使用nn.Sequential
import torch
from torch import nn
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model1 = nn.Sequential(
nn.Conv2d(in_channels=3, out_channels=32, kernel_size=5, stride=1, padding=2),
nn.MaxPool2d(kernel_size=2),
nn.Conv2d(in_channels=32, out_channels=32, kernel_size=5, stride=1, padding=2),
nn.MaxPool2d(2),
nn.Conv2d(32, 64, 5, padding=2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(1024, 64),
nn.Linear(64, 10)
)
def forward(self, x):
x = self.model1(x)
return x
tudui = Tudui()
print(tudui)
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)
![神经网络-搭建小实战和Sequential的使用_第4张图片](http://img.e-com-net.com/image/info8/e6e682da7e85490cbb2fb63cc0a75bd2.jpg)
可视化模型结构
writer = SummaryWriter('logs_seq')
writer.add_graph(tudui, input)
writer.close()
![神经网络-搭建小实战和Sequential的使用_第5张图片](http://img.e-com-net.com/image/info8/7cfe76c4761e4cf1a9217e8cc1f0c530.jpg)