model.py

import torch.nn as nn
class CNN_cls(nn.Module):def __init__(self,in_dim=28*28):super(CNN_cls,self).__init__()self.conv1 = nn.Conv2d(1,32,1,1)self.pool1 = nn.MaxPool2d(2,2)self.conv2 = nn.Conv2d(32,64,1,1)self.pool2 = nn.MaxPool2d(2,2)self.conv3 = nn.Conv2d(64,128,1,1)self.lin1 = nn.Linear(128*7*7,512)self.lin2 = nn.Linear(512,64)self.lin3 = nn.Linear(64,10)self.relu = nn.ReLU()def forward(self,x):x = self.conv1(x)x = self.relu(x)x = self.pool1(x)x = self.conv2(x)x = self.relu(x)x = self.pool2(x)x = self.conv3(x)x = self.relu(x)x = x.view(-1,128*7*7)x = self.lin1(x)x = self.relu(x)x = self.lin2(x)x = self.relu(x)x = self.lin3(x)return x

main.py

import torch
import torch.nn as nn
import torchvision
from torch.utils.data import DataLoader
import torch.optim as optim
from model import CNN_clsseed = 42
torch.manual_seed(seed)
batch_size_train = 64
batch_size_test  = 64
epochs = 10
learning_rate = 0.01
momentum = 0.5
net = CNN_cls()train_loader = torch.utils.data.DataLoader(torchvision.datasets.MNIST('./data/', train=True, download=True,transform=torchvision.transforms.Compose([torchvision.transforms.ToTensor(),torchvision.transforms.Normalize((0.5,), (0.5,))])),batch_size=batch_size_train, shuffle=True)
test_loader = torch.utils.data.DataLoader(torchvision.datasets.MNIST('./data/', train=False, download=True,transform=torchvision.transforms.Compose([torchvision.transforms.ToTensor(),torchvision.transforms.Normalize((0.5,), (0.5,))])),batch_size=batch_size_test, shuffle=True)optimizer = optim.SGD(net.parameters(), lr=learning_rate,momentum=momentum)
criterion = nn.CrossEntropyLoss()print("****************Begin Training****************")
net.train()
for epoch in range(epochs):run_loss = 0correct_num = 0for batch_idx, (data, target) in enumerate(train_loader):out = net(data)_,pred = torch.max(out,dim=1)optimizer.zero_grad()loss = criterion(out,target)loss.backward()run_loss += lossoptimizer.step()correct_num  += torch.sum(pred==target)print('epoch',epoch,'loss {:.2f}'.format(run_loss.item()/len(train_loader)),'accuracy {:.2f}'.format(correct_num.item()/(len(train_loader)*batch_size_train)))print("****************Begin Testing****************")
net.eval()
test_loss = 0
test_correct_num = 0
for batch_idx, (data, target) in enumerate(test_loader):out = net(data)_,pred = torch.max(out,dim=1)test_loss += criterion(out,target)test_correct_num  += torch.sum(pred==target)
print('loss {:.2f}'.format(test_loss.item()/len(test_loader)),'accuracy {:.2f}'.format(test_correct_num.item()/(len(test_loader)*batch_size_test)))

网络设置

在CNN_cls里面查看。

注意事项及改进

1.注意第一个输入通道是1，因为是灰度图像。
2.可以考虑加入GPU

运行截图