Pytorch学习（二）定义神经网络

Pytorch中定义神经网络

深度学习使用人工神经网络(模型)，它是由许多层相互连接的单元组成的计算系统。通过将数据传递给这些相互连接的单元，神经网络能够学习如何近似计算将输入转换成输出。在PyTorch中，神经网络能够使用torch.nn包来构建。

介绍

Pytorch提供了优雅设计的模块和类，包括torch.nn，帮助我们创建和训练神经网络。一个nn.Module 包括layers，和forward(input)方法,然后返回一个输出。

步骤

1. 导入包

2. 定义和初始化神经网络

3. 指定数据如何贯穿模型

4. 测试

1. Import necessary libraries for loading our data

import torch
import torch.nn as nn
import torch.nn.functional as F

2. Define and intialize the neural network

我们的网络可以识别图像。我们将使用PyTorch内置的一个叫做卷积的过程。卷积是将图像中的每个元素与它的局部邻居相加，由一个核函数或一个小的martrix加权，帮助我们从输入图像中提取某些特征(如边缘检测、锐度、模糊度等)。

class Net(nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        # First 2D convolutional layer, taking in 1 input channel (image),
        # outputting 32 convolutional features, with a square kernel size of 3
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        # Second 2D convolutional layer, taking in the 32 input layers,
        # outputting 64 convolutional features, with a square kernel size of 3
        self.conv2 = nn.Conv2d(32, 64 ,3 , 1)
        # Designed to ensure that adjacent pixels are either all 0s or all active
        # with an input probability
        self.dropout1 = nn.Dropout2d(0.25)
        self.dropout2 = nn.Dropout2d(0.5)

        #First fully connected layer
        self.fc1 = nn.Linear(9216, 128)
        #Second fully connected layer that outputs our labels
        self.fc2 = nn.Linear(128, 10)
my_nn = Net()
print(my_nn)
        

3. Specify how data will pass through your model

当您使用PyTorch构建模型时，您只需定义forward函数，它将数据传递到计算图(即我们的神经网络)。这代表了我们的前馈（feed-forward）算法。

class Net(nn.Module):
    def __init__(self):
      super(Net, self).__init__()
      self.conv1 = nn.Conv2d(1, 32, 3, 1)
      self.conv2 = nn.Conv2d(32, 64, 3, 1)
      self.dropout1 = nn.Dropout2d(0.25)
      self.dropout2 = nn.Dropout2d(0.5)
      self.fc1 = nn.Linear(9216, 128)
      self.fc2 = nn.Linear(128, 10)

    # x represents our data
    def forward(self, x):
        # Pass data through conv1
        x = self.conv1(x)
        # Use the rectified-linear activation function over x
        x = F.relu(x)
        x = self.conv2(x)
        x = F.relu(x)
        
        # Run max pooling over x
        x = F.max_pool2d(x,2)
        # Pass data through dropout1
        x = self.dropout1(x)
        # Flatten x with start_dim=1
        x = torch.flatten(x, 1)
        # Pass data through fc1
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)

        # Apply softmax to x
        output = F.log_softmax(x, dim=1)
        return output

4. [Optional] Pass data through your model to test

为了确保我们收到我们想要的输出，让我们通过传递一些随机数据来测试我们的模型。

# Equates to one random 28x28 image
random_data = torch.rand((1,1,28,28))

my_nn = Net()
result = my_nn(random_data)
print(result)