pytorch0.4版的CNN对minist分类

卷积神经网络(Convolutional Neural Network, CNN)是深度学习技术中极具代表的网络结构之一，在图像处理领域取得了很大的成功，在国际标准的ImageNet数据集上，许多成功的模型都是基于CNN的。

卷积神经网络CNN的结构一般包含这几个层：

1. 输入层：用于数据的输入
2. 卷积层：使用卷积核进行特征提取和特征映射
3. 激励层：由于卷积也是一种线性运算，因此需要增加非线性映射
4. 池化层：进行下采样，对特征图稀疏处理，减少数据运算量。
5. 全连接层：通常在CNN的尾部进行重新拟合，减少特征信息的损失
6. 输出层：用于输出结果

用pytorch0.4 做的cnn网络做的minist 分类，代码如下：

 import torch
 import torch.nn as nn
 import torch.nn.functional as F
 import torch.optim as optim
 from torchvision import datasets, transforms
 from torch.autograd import Variable

 # Training settings
 batch_size = 64

 # MNIST Dataset
 train_dataset = datasets.MNIST(root='./data/',train=True,transform=transforms.ToTensor(),download=True)
 test_dataset = datasets.MNIST(root='./data/',train=False,transform=transforms.ToTensor())

 # Data Loader (Input Pipeline)
 train_loader = torch.utils.data.DataLoader(dataset=train_dataset,batch_size=batch_size,shuffle=True)
 test_loader = torch.utils.data.DataLoader(dataset=test_dataset,batch_size=batch_size,shuffle=False)

 class Net(nn.Module):
     def __init__(self):
         super(Net, self).__init__()
         # 输入1通道，输出10通道，kernel 5*5
         self.conv1 = nn.Conv2d(1, 10, kernel_size=5) # 定义conv1函数的是图像卷积函数：输入为图像（1个频道，即灰度图）,输出为 10张特征图, 卷积核为5x5正方形
         self.conv2 = nn.Conv2d(10, 20, kernel_size=5) # # 定义conv2函数的是图像卷积函数：输入为10张特征图,输出为20张特征图, 卷积核为5x5正方形
         self.mp = nn.MaxPool2d(2)
         # fully connect
         self.fc = nn.Linear(320, 10)

     def forward(self, x):
         # in_size = 64
         in_size = x.size(0)  # one batch
         # x: 64*10*12*12
         x = F.relu(self.mp(self.conv1(x)))
         # x: 64*20*4*4
         x = F.relu(self.mp(self.conv2(x)))
         # x: 64*320
         x = x.view(in_size, -1)  # flatten the tensor
         # x: 64*10
         x = self.fc(x)
         return F.log_softmax(x,dim=0)

 model = Net()
 optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

 def train(epoch):
     for batch_idx, (data, target) in enumerate(train_loader):
         data, target = Variable(data), Variable(target)
         optimizer.zero_grad()
         output = model(data)
         loss = F.nll_loss(output, target)
         loss.backward()
         optimizer.step()
         if batch_idx % 200 == 0:
             print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                 epoch, batch_idx * len(data), len(train_loader.dataset),
                        100. * batch_idx / len(train_loader), loss.item()))

 def test():
     test_loss = 0
     correct = 0
     for data, target in test_loader:
         data, target = Variable(data), Variable(target)
         output = model(data)
         # sum up batch loss
         #test_loss += F.nll_loss(output, target, size_average=False).item()
         test_loss += F.nll_loss(output, target, reduction = 'sum').item()
         # get the index of the max log-probability
         pred = output.data.max(1, keepdim=True)[1]
         correct += pred.eq(target.data.view_as(pred)).cpu().sum()

     test_loss /= len(test_loader.dataset)
     print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
         test_loss, correct, len(test_loader.dataset),
         100. * correct / len(test_loader.dataset)))

 if __name__=="__main__":
     for epoch in range(1, 4):
       train(epoch)
       test()

运行效果如下：

Train Epoch:  [/ (%)]    Loss: 4.163342
Train Epoch:  [/ (%)]    Loss: 2.689871
Train Epoch:  [/ (%)]    Loss: 2.553686
Train Epoch:  [/ (%)]    Loss: 2.376630
Train Epoch:  [/ (%)]    Loss: 2.321894

Test set: Average loss: 2.2703, Accuracy: / (%)

Train Epoch:  [/ (%)]    Loss: 2.321601
Train Epoch:  [/ (%)]    Loss: 2.293680
Train Epoch:  [/ (%)]    Loss: 2.377935
Train Epoch:  [/ (%)]    Loss: 2.150829
Train Epoch:  [/ (%)]    Loss: 2.201805

Test set: Average loss: 2.1848, Accuracy: / (%)

Train Epoch:  [/ (%)]    Loss: 2.238524
Train Epoch:  [/ (%)]    Loss: 2.224833
Train Epoch:  [/ (%)]    Loss: 2.240626
Train Epoch:  [/ (%)]    Loss: 2.217183
Train Epoch:  [/ (%)]    Loss: 2.357141

Test set: Average loss: 2.1426, Accuracy: / (%)