pytorch实现mnist手写数字识别

需要用到的import

import os
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.optim.lr_scheduler import StepLR

加载mnist数据

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307), (0.3015))
])

train_data = datasets.MNIST(
    root='mnist',
    train=True,
    download=True,
    transform=transform
)

test_data = datasets.MNIST(
    root='mnist',
    train=False,
    download=True,
    transform=transform
)

batch_size = 64

train_loader = torch.utils.data.DataLoader(
    train_data,
    batch_size=batch_size,
    shuffle=True
)

test_loader = torch.utils.data.DataLoader(
    test_data,
    batch_size=batch_size
)

模型

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.pool = nn.MaxPool2d(2, 2)
        self.dropout1 = nn.Dropout(0.25)
        self.dropout2 = nn.Dropout(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = self.pool(x)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output

加载上一次训练的参数（如果参数文件存在）

model = Net()
path = 'mnist_state.pth'
if os.path.exists(path):
    model.load_state_dict(torch.load(path))

优化器

optimizer = optim.Adadelta(model.parameters(), lr=1.)
scheduler = StepLR(optimizer, step_size=1, gamma=0.7)

训练和测试方法

def train(model, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()

        if batch_idx % 100 == 0:
            print('epoch', epoch)
            print('loss', loss.item())


def test(model, test_loader):
    model.eval()
    test_loss = 0
    correct = 0

    with torch.no_grad():
        for data, target in test_loader:
            output = model(data)
            test_loss += F.nll_loss(output, target).sum().item()
            pred = torch.argmax(output, 1)
            correct += pred.eq(target).sum().float().item()

    test_loss /= len(test_loader.dataset)
    correct /= len(test_loader.dataset)

    print('test loss: ', test_loss)
    print('acc', correct * 100)

开始训练

for i in range(2):
    train(model, train_loader, optimizer, i)
    test(model, test_loader)
    scheduler.step()

保存训练参数

torch.save(model.state_dict(), path)

完结，做个笔记。