使用卷积网络做手写数字识别

import torch
from torch import nn
import torchvision.datasets as datasets
import torchvision.transforms as transforms

torch.manual_seed(2019)

# 超参设置
EPOCH = 1  # 训练EPOCH次，这里为了测试方便只跑一次
BATCH_SIZE = 32
INIT_LR = 1e-3  # 初始学习率
DOWNLOAD_MNIST = True  # 设置是否需要下载数据集

# 使用DataLoader加载训练数据，为了演示方便，对于测试数据只取出2000个样本进行测试
train_data = datasets.MNIST(root='mnist', train=True, transform=transforms.ToTensor(), download=DOWNLOAD_MNIST)
train_loader = torch.utils.data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
test_data = datasets.MNIST(root='mnist', train=False)
test_x = test_data.test_data.type(torch.FloatTensor)[:2000] / 255.
test_x.unsqueeze_(1)  # 调整test_x的尺寸为四维，添加了一个channel维度
test_y = test_data.test_labels.numpy()[:2000]


class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 32, 5),  # 图像输出大小为24*24
            nn.MaxPool2d(2),  # 图像输出大小为12*12
            nn.ReLU(True),
            nn.Conv2d(32, 64, 5),  # 图像输出大小为8*8
            nn.Dropout2d(),
            nn.MaxPool2d(2),  # 图像输出大小为4*4
            nn.ReLU(True)
        )

        self.linear = nn.Sequential(
            nn.Linear(4 * 4 * 64, 128),
            nn.ReLU(True),
            nn.Dropout2d(),
            nn.Linear(128, 10),
            nn.Softmax(1)
        )

    def forward(self, x):
        x = self.conv(x)
        x = x.view(-1, 4 * 4 * 64)
        out = self.linear(x)
        return out


model = ConvNet()
print(model)

optimizer = torch.optim.Adam(model.parameters(), lr=INIT_LR)
loss_func = nn.CrossEntropyLoss()

# RNN训练
for epoch in range(EPOCH):
    for index, (b_x, b_y) in enumerate(train_loader):
        model.train()
        # 输入尺寸为(batch_size, channels, height, width)
        output = model(b_x)  # (64, 1, 28, 28)
        loss = loss_func(output, b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if index % 50 == 0:
            model.eval()
            prediction = model(test_x)  # 输出为(2000, 10)
            pred_y = torch.max(prediction, 1)[1].data.numpy()
            accuracy = (pred_y == test_y).sum() / float(test_y.size)
            print(f'Epoch: [{index}/{epoch}]', f'| train loss: {loss.item()}', f'| test accuracy: {accuracy}')

# 打印测试数据集中的后20个结果
model.eval()
prediction = model(test_x[:20])
pred_y = torch.max(prediction, 1)[1].data.numpy()
print(pred_y, 'prediction number')
print(test_y[:20], 'real number')