(入门) 深度学习之“Hello World“——MINST数据集手写数字识别

MINST数据集手写数字识别

学习课程：
吴恩达深度学习课程Deeplearning.ai
刘二大人PyTorch深度学习实践

1.导入模块

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

2.加载数据集

transform = transforms.Compose([
    transforms.ToTensor(),  # 将其转换为tensor类型
    transforms.Normalize((0.1307,), (0.3081,))  # 将其压缩至0-1之间
])

# 加载数据准备
train_dataset = datasets.MNIST(root='../dataset/minst', train=True, transform=transform, download=True);

test_dataset = datasets.MNIST(root='../dataset/minst', train=False, transform=transform, download=True);

train_loader = DataLoader(dataset=train_dataset, batch_size=64, shuffle=True);

test_loader = DataLoader(dataset=train_dataset, batch_size=64, shuffle=False);

3.构建网络

# 构建网络
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__();
        self.l1 = torch.nn.Linear(784, 512);
        self.l2 = torch.nn.Linear(512, 256);
        self.l3 = torch.nn.Linear(256, 128);
        self.l4 = torch.nn.Linear(128, 64);
        # 输出层
        self.l5 = torch.nn.Linear(64, 10);
    def forward(self, x):
        x = x.view(-1, 784);
        x = F.relu(self.l1(x));
        x = F.relu(self.l2(x));
        x = F.relu(self.l3(x));
        x = F.relu(self.l4(x));
        return self.l5(x);

4.损失函数、梯度下降

# 实例化网络
model = Net();

# 损失函数及其优化
# ‘多分类’交叉熵损失函数   CrossEntropyLoss() = softmax + log + NLLLoss() = log_softmax + NLLLoss()
loss1 = torch.nn.CrossEntropyLoss(); 

# 梯度下降
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5);

5.训练模型

# 训练模型
def train(epoch):
    loss_running = 0.0;
    # enumerate返回值有两个,一个是序号，一个是数据（包含训练数据和标签）
    for batch_index, data in enumerate(train_loader, 0):
        batch_x, batch_y = data;
        optimizer.zero_grad();
        # 损失函数 前馈 反馈
        output = model(batch_x);  # output 就是y-hat
        loss = loss1(output, batch_y);
        loss.backward();
        optimizer.step();

        loss_running += loss.item();
        if batch_index % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_index + 1, loss_running / 300))
            loss_running = 0.0

6.测试模型

def test():
    correct = 0;
    total = 0;
    with torch.no_grad():
        for data in test_loader:
            t_images, t_labels = data;
            t_output = model(t_images);
            _, predicted = torch.max(t_output, dim=1);
            total += t_labels.size(0);
            correct += (predicted == t_labels).sum().item();
        print('Accuracy on test set: %d %%' % (100 * correct / total));

7.执行

if __name__ == '__main__':
    for epoch in range(10):
        train(epoch);
        test();

8.保存模型

Path = "MINST_MY_Model.pt";

torch.save(model,Path);
saveModel = torch.load(Path);
saveModel.eval();