pytorch：cnn（卷积神经网络）

用pytorch-python通过cnn实现mnist手写字体的识别。

程序：

import torch
import torch.nn as nn
import torch.utils.data as data
import torchvision
import matplotlib.pyplot as plt

# Hyper Parameter
EPOCH = 1  # 训练整批数据的次数
BATCH_SIZE = 50  # 批训练的数据数量
LR = 0.001  # 学习率
DOWNLOAD_MNIST = False  # 如果下载好了mnist数据库就写False

# mnist手写数字
train_data = torchvision.datasets.MNIST(
    root='./mnist/',  # 保存或提取的位置
    train=True,  # 是否为训练数据
    transform=torchvision.transforms.ToTensor(),  # 转换plt.image or numpy.ndarray 成torch.FloatTensor(C*H*W)，训练时normalize成[0.0, 0.1]区间
    download=DOWNLOAD_MNIST  # 是否为下载好
)

test_data = torchvision.datasets.MNIST(root='./mnist', train=False)

# 批训练 50 samples,1 channel, 28*28 (50,1,28,28)
train_loader = data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

# 为了节约时间， 只测试前2000个
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255.  # 把[0,255]转换成[0.0,1.0]
test_y = test_data.test_labels[:2000]


# 创建cnn网络
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(                # input shape (1,28,28)
            nn.Conv2d(
                in_channels=1,  # 输入数据的通道数（channels）
                out_channels=16,  # 输出数据的通道数（channels）
                kernel_size=5,  # 卷积核的大小
                stride=1,  # 步长
                padding=2,  # 外部填充， padding = (kernel_size - 1) / 2
            ),                                     # output shape (16,28,28)
            nn.ReLU(),  # 激活函数
            nn.MaxPool2d(kernel_size=2)  # 池化层，向下采样步长为2       # output shape (16,14,14)
        )
        self.conv2 = nn.Sequential(                # input shape (16,14,14)
            nn.Conv2d(16, 32, 5, 1, 2),            # output shape (32,14,14)
            nn.ReLU(),
            nn.MaxPool2d(2)                        # output shape (32,7,7)
        )
        self.out = nn.Linear(32*7*7, 10)  # 输出层为全连接层

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)
        output = self.out(x)
        return output


cnn = CNN()

# 训练
optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()

for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):
        output = cnn(b_x)
        loss = loss_func(output, b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 50 == 0:
            test_output = cnn(test_x)
            pred_y = torch.max(test_output, 1)[1].data.squeeze()
            accuracy = (sum(pred_y == test_y)).numpy() / test_y.size(0)
            print('step:', step, 'accuracy: %.2f' % accuracy)

结果：