Pytorch搭建CIFAR10神经网络

文章目录

• ​​模型架构​​
• ​​不使用Sequential​​
• ​​使用Sequential​​

模型架构

不使用Sequential

import torch
from torch import nn


class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=32,
                               kernel_size=5, padding=2)
        self.pool1 = nn.MaxPool2d(kernel_size=2)
        self.conv2 = nn.Conv2d(in_channels=32, out_channels=32,
                               kernel_size=5, padding=2)
        self.pool2 = nn.MaxPool2d(kernel_size=2)
        self.conv3 = nn.Conv2d(in_channels=32, out_channels=64,
                               kernel_size=5, padding=2)
        self.pool3 = nn.MaxPool2d(kernel_size=2)
        self.flatten = nn.Flatten()
        self.liner1 = nn.Linear(in_features=1024, out_features=64)
        self.liner2 = nn.Linear(in_features=64, out_features=10)

    def forward(self, input):
        x = self.conv1(input)
        x = self.pool1(x)
        x = self.conv2(x)
        x = self.pool2(x)
        x = self.conv3(x)
        x = self.pool3(x)
        x = self.flatten(x)
        x = self.liner1(x)
        output = self.liner2(x)
        return output


model = Model()
input = torch.ones(size=(64, 3, 32, 32))
output = model(input)
print(output.shape)

使用Sequential

import torch
from torch import nn
from torch.utils.tensorboard import SummaryWriter


class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.sequential = nn.Sequential(
            nn.Conv2d(in_channels=3, out_channels=32,
                      kernel_size=5, padding=2),
            nn.MaxPool2d(kernel_size=2),
            nn.Conv2d(in_channels=32, out_channels=32,
                      kernel_size=5, padding=2),
            nn.MaxPool2d(kernel_size=2),
            nn.Conv2d(in_channels=32, out_channels=64,
                      kernel_size=5, padding=2),
            nn.MaxPool2d(kernel_size=2),
            nn.Flatten(),
            nn.Linear(in_features=1024, out_features=64),
            nn.Linear(in_features=64, out_features=10)
        )

    def forward(self, input):
        output = self.sequential(input)
        return output


writer = SummaryWriter('./nn_sq/')
model = Model()
print(model)
input = torch.ones(size=(64, 3, 32, 32))
output = model(input)
writer.add_graph(model=model, input_to_model=input, verbose=True)
print(output.shape)
writer.close()