PyTorch学习笔记——cnn训练测试mnist手写数字数据集

学习资料：https://www.bilibili.com/video/av62138405?p=5

源代码：

'''
mnist数据集
60000张训练图片
10000张测试图片
'''

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
print("PyTorch Version: ", torch.__version__)
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5, 1)  # 28+1-5 = 24
        self.conv2 = nn.Conv2d(20, 50, 5, 1)
        self.fc1 = nn.Linear(4*4*50, 500)
        self.fc2 = nn.Linear(500, 10)

    def forward(self, x):
        # x: 1 * 28 * 28
        x = F.relu(self.conv1(x))  # 20 * 24 * 24
        x = F.max_pool2d(x, 2, 2)  # 20 * 12 * 12
        x = F.relu(self.conv2(x))  # 50 * 8 * 8
        x = F.max_pool2d(x, 2, 2)  # 50 * 4 * 4
        x = x.view(-1, 4*4*50) #reshape  (5*2*10),view(5*20) -> (5*20)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)
mnist_data = datasets.MNIST("./mnist_data", train=True, download=True,
                            transform=transforms.Compose([
                                transforms.ToTensor(),
                            ]))
data = [d[0].data.cpu().numpy() for d in mnist_data]
# np.mean(data) = 0.1306062
# np.std(data) = 0.30810776

def train(model, device, train_loader, optimizer, epoch):
    model.train()
    for idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)

        pred = model(data) # batch_size *10
        loss = F.nll_loss(pred, target)

        #SGD
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if idx % 100 ==0:
            print ("Train Epoch:{}, iteration:{}, Loss:{}".format(
                epoch, idx, loss.item()))

def test(model, device, test_dataloader):
    model.eval()
    total_loss = 0.
    correct = 0.

    with torch.no_grad():
        for idx, (data, target) in enumerate(test_dataloader):
            data, target = data.to(device), target.to(device)

            output = modetl(data) # batch_size *10
            total_loss += F.nll_loss(output, target, reduction="sum").item()
            pred = output.argmax(dim =1)
            correct += pred.eq(target.view_as(pred)).sum().item()

    total_loss /= len(test_dataloader.dataset)
    acc = correct/len(test_dataloader.dataset) * 100.
    print("Test loss:{}, Accuracy:{}".format(total_loss, acc))


device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
batch_size = 32
train_dataloader = torch.utils.data.DataLoader(
    datasets.MNIST("./mnist_data", train=True, download=False,
                            transform=transforms.Compose([
                                transforms.ToTensor(),
                                transforms.Normalize((0.1307, ), (0.3081, ))
                            ])),
    batch_size=batch_size, shuffle=True,
     pin_memory=True #pip_memory 和加速计算有关
)
test_dataloader = torch.utils.data.DataLoader(
    datasets.MNIST("./mnist_data", train=False, download=False,
                            transform=transforms.Compose([
                                transforms.ToTensor(),
                                transforms.Normalize((0.1307, ), (0.3081, ))
                            ])),
    batch_size=batch_size, shuffle=True,
     pin_memory=True #pip_memory 和加速计算有关
)

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

num_epochs = 2
for epoch in range(num_epochs):
    train(model, device, train_dataloader, optimizer, epoch)
    test(model, device, test_dataloader)

torch.save(model.state_dict(), "mnist_cnn.pt")

运行结果：