MNIST.py

import torch
from torchvision import transforms, datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

######################
##1. Prepare Dataset##
######################
batch_size = 64
#使用MiniBatch时,GPU并行计算64个sample得到64个loss,取平均得到1个loss，再根据这个loss反向传播
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,),(0.3801,))])
train_dataset =  datasets.MNIST(root=r'C:\Users\Ctrom\OneDrive\Documents\ai\《PyTorch深度学习实践》完结合集', train = True, download = True, transform = transform)
train_loader = DataLoader(train_dataset, shuffle = True, batch_size = batch_size)
test_dataset = datasets.MNIST(root = r'C:\Users\Ctrom\OneDrive\Documents\ai\《PyTorch深度学习实践》完结合集', train = False, download = True, transform = transform)
test_loader = DataLoader(test_dataset, shuffle = True, batch_size = batch_size)

###################
##2. Design Model##
###################
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size = 3, padding = 3)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size = 3, padding = 1)
        self.conv3 = torch.nn.Conv2d(20, 30, kernel_size=3, padding = 1)
        self.pooling = torch.nn.MaxPool2d(kernel_size = 2, stride = 2)
        self.fc = torch.nn.Linear(30*2*2, 10)
    def forward(self, x):
        batch_size = x.size(0)
        x = self.pooling(F.relu(self.conv1(x)))
        x = self.pooling(F.relu(self.conv2(x)))
        x = self.pooling(F.relu(self.conv3(x)))
        x = self.pooling(x)
        x = self.fc(x.view(batch_size, -1))
        return x
model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

#################################
##3. Construct Loss & Optimizer##
#################################
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr = 0.01)

#####################
##4. Train and test##
#####################
def train(epoch):
    running_loss = 0
    for batch_idx, (inputs, targets) in enumerate(train_loader, 0):
        inputs, targets = inputs.to(device), targets.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            inputs, targets = data
            inputs, targets = inputs.to(device), targets.to(device)
            outputs = model(inputs)
            _, predicted = torch.max(outputs.data, dim = 1)
            total += targets.size(0)
            correct += (predicted == targets).sum().item()
    print(f'Accuracy on test set: {100 * correct / total:.0f} % ({correct} correct out of {total})')

########
##Main##
########
if __name__ == '__main__':
    for epoch in range(20):
        train(epoch)
        if (epoch+1) % 5 == 0:
            test()