【580】PyTorch 实现 CNN 例子

参考:PyTorch 神经网络

参考:PyTorch 图像分类器

参考:深度学习框架Keras与Pytorch对比


  实现下面这个网络:

  • 第一层:卷积 5*5*6、ReLU、Max Pooling
  • 第二层:卷积 5*5*16、ReLU、Max Pooling
  • 第三层:Flatten、Linear NN
  • 第四层:Linear NN
  • 第五层:Linear NN  

  这是一个简单的前馈神经网络,它接收输入,让输入一个接着一个的通过一些层,最后给出输出。

一个典型的神经网络训练过程包括以下几点:

  1. 定义一个包含可训练参数的神经网络
  2. 迭代整个输入
  3. 通过神经网络处理输入
  4. 计算损失(loss)
  5. 反向传播梯度到神经网络的参数
  6. 更新网络的参数,典型的用一个简单的更新方法:weight weight learning_rate *gradient

定义神经网络:

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

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution kernel
        # 第一层
        self.conv1 = nn.Conv2d(in_channels=1, out_channels=6, kernel_size=5)
        # 第二层
        self.conv2 = nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5)
        # an affine operation: y = Wx + b
        # 第三层
        self.fc1 = nn.Linear(in_features=16 * 5 * 5, out_features=120)
        # 第四层
        self.fc2 = nn.Linear(in_features=120, out_features=84)
        # 第五层
        self.fc3 = nn.Linear(in_features=84, out_features=10)
        
    def forward(self, x):
        # 第一层 (conv1 -> relu -> max pooling)
        x = self.conv1(x)
        x = F.relu(x)
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(x, (2, 2))
        
        # 第二层 (conv2 -> relu -> max pooling)
        x = self.conv2(x)
        x = F.relu(x)
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(x, 2)
        
        # 第三层 (fc -> relu)
        x = x.view(-1, self.num_flat_features(x))
        x = self.fc1(x)
        x = F.relu(x) 
        
        # 第四层 (fc -> relu)
        x = self.fc2(x)
        x = F.relu(x)
        
        # 第五层 (fc -> relu)
        x = self.fc3(x)
        x = F.relu(x) 
        
        return x 
        
    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features
    
net = Net()
print(net) 

  输出:

Net(
  (conv1): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1))
  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
  (fc1): Linear(in_features=400, out_features=120, bias=True)
  (fc2): Linear(in_features=120, out_features=84, bias=True)
  (fc3): Linear(in_features=84, out_features=10, bias=True)
)

在Pytorch中训练模型包括以下几个步骤:

  1. 在每批训练开始时初始化梯度
  2. 前向传播
  3. 反向传播
  4. 计算损失并更新权重
import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

for epoch in range(2):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training') 

  通用

# 在数据集上循环多次
for epoch in range(2):  
    for i, data in enumerate(trainloader, 0):
        # 获取输入; data是列表[inputs, labels]
        inputs, labels = data 
        # (1) 初始化梯度
        optimizer.zero_grad() 

        # (2) 前向传播
        outputs = net(inputs)
        loss = criterion(outputs, labels)

        # (3) 反向传播
        loss.backward()
        # (4) 计算损失并更新权重
        optimizer.step()
原文地址:https://www.cnblogs.com/alex-bn-lee/p/14932072.html