P1 数字识别-优快云博客

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

# 设置硬件设备，如果有GPU则使用，没有则使用cpu
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 导入数据
train_ds = torchvision.datasets.MNIST('data',
                                      train=True,
                                      transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                      download=True)

test_ds  = torchvision.datasets.MNIST('data',
                                      train=False,
                                      transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                      download=True)

# 加载数据
batch_size = 32

train_dl = torch.utils.data.DataLoader(train_ds,
                                       batch_size=batch_size,
                                       shuffle=True)

test_dl  = torch.utils.data.DataLoader(test_ds,
                                       batch_size=batch_size)

# 取一个批次查看数据格式
# 数据的shape为：[batch_size, channel, height, weight]
# 其中batch_size为自己设定，channel，height和weight分别是图片的通道数，高度和宽度。
imgs, labels = next(iter(train_dl))
print(imgs.shape)

# 数据可视化
import numpy as np

# 指定图片大小，图像大小为20宽、5高的绘图(单位为英寸inch)
plt.figure(figsize=(20, 5))
for i, imgs in enumerate(imgs[:20]):
    # 维度缩减
    npimg = np.squeeze(imgs.numpy())
    # 将整个figure分成2行10列，绘制第i+1个子图。
    plt.subplot(2, 10, i + 1)
    plt.imshow(npimg, cmap=plt.cm.binary)
    plt.axis('off')

# plt.show()  如果你使用的是Pycharm编译器，请加上这行代码

torch.Size([32, 1, 28,28])

# 构建CNN网络
import torch.nn.functional as F

num_classes = 10  # 图片的类别数


class Model(nn.Module):
    def __init__(self):
        super().__init__()
        # 特征提取网络
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3)  # 第一层卷积,卷积核大小为3*3
        self.pool1 = nn.MaxPool2d(2)  # 设置池化层，池化核大小为2*2
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)  # 第二层卷积,卷积核大小为3*3
        self.pool2 = nn.MaxPool2d(2)

        # 分类网络
        self.fc1 = nn.Linear(1600, 64)
        self.fc2 = nn.Linear(64, num_classes)

    # 前向传播
    def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))
        x = self.pool2(F.relu(self.conv2(x)))

        x = torch.flatten(x, start_dim=1)

        x = F.relu(self.fc1(x))
        x = self.fc2(x)

        return x

from torchinfo import summary
# 将模型转移到GPU中（我们模型运行均在GPU中进行）
model = Model().to(device)

summary(model)

# 设置超参数
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-2 # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

# 训练函数
# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小，一共60000张图片
    num_batches = len(dataloader)  # 批次数目，1875（60000/32）

    train_loss, train_acc = 0, 0  # 初始化训练损失和正确率

    for X, y in dataloader:  # 获取图片及其标签
        X, y = X.to(device), y.to(device)

        # 计算预测误差
        pred = model(X)  # 网络输出
        loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失

        # 反向传播
        optimizer.zero_grad()  # grad属性归零
        loss.backward()  # 反向传播
        optimizer.step()  # 每一步自动更新

        # 记录acc与loss
        train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()

    train_acc /= size
    train_loss /= num_batches

    return train_acc, train_loss

Epoch: 1, Train_acc:78.7%, Train_loss:0.740, Test_acc:93.1%，Test_loss:0.232
Epoch: 2, Train_acc:94.3%, Train_loss:0.187, Test_acc:96.6%，Test_loss:0.116
Epoch: 3, Train_acc:96.4%, Train_loss:0.116, Test_acc:97.4%，Test_loss:0.086
Epoch: 4, Train_acc:97.2%, Train_loss:0.091, Test_acc:97.5%，Test_loss:0.079
Epoch: 5, Train_acc:97.6%, Train_loss:0.076, Test_acc:97.8%，Test_loss:0.065
Done