Pytorch之三层全连接神经网络实现MNIST手写数字分类

net.py :

from torch import nn

class SimpleNet(nn.Module):
    def __init__(self, in_dim, n_hidden_1, n_hidden_2, out_dim):
        super(SimpleNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Linear(in_dim, n_hidden_1),
            nn.BatchNorm1d(n_hidden_1), nn.ReLU(True))
        self.layer2 = nn.Sequential(
            nn.Linear(n_hidden_1, n_hidden_2),
            nn.BatchNorm1d(n_hidden_2), nn.ReLU(True))
        self.layer3 = nn.Sequential(nn.Linear(n_hidden_2, out_dim))

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return x

MNIST 手写数字数据集已下载到当前目录mnist文件夹下
simpleNet.py :

import torch
from torch import nn, optim
from torch.autograd import Variable
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
import net

# (Hyper parameters)
batch_size = 64
learning_rate = 1e-2
num_epochs = 20

if __name__ == '__main__':
    data_tf = transforms.Compose(
        [transforms.ToTensor(),
         transforms.Normalize([0.5], [0.5])])
    train_dataset = datasets.MNIST(
        root='./mnist', train=True, transform=data_tf, download=False)
    test_dataset = datasets.MNIST(root='./mnist', train=False, transform=data_tf)

    train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
    test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

    model = net.SimpleNet(28 * 28, 300, 100, 10)
    if torch.cuda.is_available():
        model = model.cuda()

    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(model.parameters(), lr=learning_rate)

    epoch = 0
    for data in train_loader:
        img, label = data
        img = img.view(img.size(0), -1)
        if torch.cuda.is_available():
            img = img.cuda()
            label = label.cuda()
        else:
            img = Variable(img)
            label = Variable(label)
        out = model(img)
        loss = criterion(out, label)
        print_loss = loss.data.item()

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        epoch+=1
        if epoch%100==0:
            print('epoch: {}, loss: {:.4}'.format(epoch, loss.data.item()))

    model.eval()
    eval_loss = 0
    eval_acc = 0
    for data in test_loader:
        img, label = data
        img = img.view(img.size(0), -1)
        if torch.cuda.is_available():
            img = img.cuda()
            label = label.cuda()

        out = model(img)
        loss = criterion(out, label)
        eval_loss+=loss.data.item()*label.size(0)
        _, pred = torch.max(out, 1)
        num_correct = (pred == label).sum()
        eval_acc += num_correct.item()
    print('Test Loss: {:.6f}, Acc: {:.6f}'.format(
        eval_loss / (len(test_dataset)),
        eval_acc / (len(test_dataset))
    ))

输出结果，如下：
epoch: 100, loss: 1.334
epoch: 200, loss: 0.9188
epoch: 300, loss: 0.7004
epoch: 400, loss: 0.5332
epoch: 500, loss: 0.5584
epoch: 600, loss: 0.3472
epoch: 700, loss: 0.3597
epoch: 800, loss: 0.2599
epoch: 900, loss: 0.2219
Test Loss: 0.267712, Acc: 0.939600

Process finished with exit code 0