pytorch初学笔记（十三）：神经网络基本结构之Sequential层的使用以及搭建完整的小型神经网络实战


# Using Sequential to create a small model. When `model` is run,
# input will first be passed to `Conv2d(1,20,5)`. The output of
# `Conv2d(1,20,5)` will be used as the input to the first
# `ReLU`; the output of the first `ReLU` will become the input
# for `Conv2d(20,64,5)`. Finally, the output of
# `Conv2d(20,64,5)` will be used as input to the second `ReLU`
model = nn.Sequential(
          nn.Conv2d(1,20,5),
          nn.ReLU(),
          nn.Conv2d(20,64,5),
          nn.ReLU()
        )
 
# Using Sequential with OrderedDict. This is functionally the
# same as the above code
model = nn.Sequential(OrderedDict([
          ('conv1', nn.Conv2d(1,20,5)),
          ('relu1', nn.ReLU()),
          ('conv2', nn.Conv2d(20,64,5)),
          ('relu2', nn.ReLU())
        ]))

二、实战神经网络搭建以及sequential的使用

2.1 前期准备

2.1.1 神经网络模型

使用数据集为CIFAR10，其模型结构如下所示。

输入大小为3*32*32
经过3次【5*5卷积核卷积-2*2池化核池化】操作后，输出为64*4*4大小
展平后为1*1024大小
经过全连接层后输出为1*10

2.1.2 求卷积过程中的padding参数

在我们的第一个卷积过程中，输入通道数为3，输出通道数为32，卷积核大小为5，Conv2d所需的前三个参数已设置完成，因为没有使用空洞卷积，所示dilation默认为1，无需设置，步长stride默认为1，下面需要使用公式计算padding和stride的值为多少。

使用上述公式进行计算，把H，dilation，kernel_size进行代入，设置stride=1，padding求出=2。

如果保持输入输出的大小不变，则stride=1，padding=2，后面的卷积中都是使用该两个值，无需进行计算。

2.2 网络搭建

根据模型中的步骤进行卷积池化和全连接操作。


import torch.nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear
 
class Maweiyi(torch.nn.Module):
    def __init__(self):
        super(Maweiyi, self).__init__()
        self.conv1 = Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2)
        self.maxpool1 = MaxPool2d(kernel_size=2)
        self.conv2 = Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2)
        self.maxpool2 = MaxPool2d(kernel_size=2)
        self.conv3 = Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2)
        self.maxpool3 = MaxPool2d(kernel_size=2)
        self.flatten = Flatten()
        self.linear1 = Linear(in_features=1024, out_features=64)
        self.linear2 = Linear(in_features=64, out_features=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.linear1(x)
        x = self.linear2(x)
        return x

2.3 sequential的使用

可以看到上面神经网络进行搭建时非常繁琐，在init中进行了多个操作的定以后需要在forward中逐次进行调用，因此我们使用sequential方法，在init方法中直接定义一个model，然后在下面的forward方法中直接使用一次model即可。

在init方法中：

self.model1 = Sequential(

Conv2d(...)

MaxPool2d(...)

Linear(...)

)

在forward方法中：

x = self.model(x)

return x


class Maweiyi(torch.nn.Module):
    def __init__(self):
        super(Maweiyi, self).__init__()
        self.model1 = Sequential(
            Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Flatten(),
            Linear(in_features=1024, out_features=64),
            Linear(in_features=64, out_features=10)
        )
 
    def forward(self, x):
         x = self.model1(x)
         return x

2.4 检验网络正确性

创建输入的tensor,大小为神经网络中一开始输入的大小，为（64,3,32,32），经过神经网络后输出大小应为10。

使用torch.ones方法进行创建规定大小的tensor

(21条消息) torch.ones(),torch.add(),torch.zeros(),torch.squeeze()_skycrygg的博客-CSDN博客_torch.add()


input = torch.ones((64,3,32,32))
output = maweiyi(input)
print(output.shape)

输出如下：

三、完整代码

3.1 控制台输出


import torch.nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
 
 
class Maweiyi(torch.nn.Module):
    def __init__(self):
        super(Maweiyi, self).__init__()
        self.model1 = Sequential(
            Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Flatten(),
            Linear(in_features=1024, out_features=64),
            Linear(in_features=64, out_features=10)
        )
 
    def forward(self, x):
         x = self.model1(x)
         return x
 
 
maweiyi = Maweiyi()
print(maweiyi)
 
input = torch.ones((64,3,32,32))
output = maweiyi(input)
print(output.shape)

3.2 tensorboard可视化

使用SummaryWriter中的add_gragh方法生成神经网络模型。


import torch.nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriter
 
 
class Maweiyi(torch.nn.Module):
    def __init__(self):
        super(Maweiyi, self).__init__()
        self.model1 = Sequential(
            Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2),
            MaxPool2d(kernel_size=2),
            Flatten(),
            Linear(in_features=1024, out_features=64),
            Linear(in_features=64, out_features=10)
        )
 
    def forward(self, x):
         x = self.model1(x)
         return x
 
 
maweiyi = Maweiyi()
print(maweiyi)
 
input = torch.ones((64,3,32,32))
output = maweiyi(input)
print(output.shape)
 
writer = SummaryWriter("logs")
writer.add_graph(maweiyi,input)
writer.close()

输出：

相关阅读:
73个产品小白必备知识，项目管理也可看
 GPT版本通俗简单介绍
 【Andriod】使用adb命令安装和卸载apk的通用python脚本
 linux内存监控
 数千年中东文明史的五个阶段
 开发运维-常用远程桌面开源软件
 java毕业生设计医护监视系统计算机源码+系统+mysql+调试部署+lw
中小型工业企业的数字化转型之路
 log4j2的使用
 华为 Mate 60 Pro 拆解：陆制零件比率上升至47% | 百能云芯
原文地址：https://blog.csdn.net/weixin_45662399/article/details/128075680