简单的pycharm深度学习代码，可以直接运行不出现错误，只用pytorch库，，训练100个epoch，得到训练集和验证集的准确率曲线、损失函数曲线以及交叉熵函数曲线

以下是一个简单的pycharm深度学习代码，可以直接运行不出现错误，只用pytorch库，训练100个epoch，得到训练集和验证集的准确率曲线、损失函数曲线以及交叉熵函数曲线。这个代码使用了MNIST数据集进行训练和测试。

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

# 超参数设置
batch_size = 64
learning_rate = 0.01
num_epochs = 100

# 数据预处理
transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.1307,), (0.3081,))])

# 加载数据集
train_dataset = datasets.MNIST(root='./data', train=True, transform=transform, download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=transform, download=True)

train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)

# 定义模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=5)
        self.maxpool1 = nn.MaxPool2d(kernel_size=2)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=5)
        self.maxpool2 = nn.MaxPool2d(kernel_size=2)
        self.fc1 = nn.Linear(1024, 512)
        self.fc2 = nn.Linear(512, 10)

    def forward(self, x):
        x = self.maxpool1(torch.relu(self.conv1(x)))
        x = self.maxpool2(torch.relu(self.conv2(x)))
        x = x.view(-1, 1024)
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# 定义模型、损失函数和优化器
model = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)

train_losses = []
train_accs = []
test_losses = []
test_accs = []

# 训练模型
for epoch in range(num_epochs):
    train_loss = 0
    train_acc = 0
    test_loss = 0
    test_acc = 0
    # 训练模式
    model.train()
    for i, (inputs, targets) in enumerate(train_loader):
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()

        train_loss += loss.item()
        _, predicted = torch.max(outputs.data, 1)
        train_acc += (predicted == targets).sum().item()

    # 测试模式
    model.eval()
    with torch.no_grad():
        for inputs, targets in test_loader:
            outputs = model(inputs)
            loss = criterion(outputs, targets)

            test_loss += loss.item()
            _, predicted = torch.max(outputs.data, 1)
            test_acc += (predicted == targets).sum().item()

    # 记录训练和测试的损失和准确率
    train_loss /= len(train_loader.dataset)
    train_acc /= len(train_loader.dataset)
    test_loss /= len(test_loader.dataset)
    test_acc /= len(test_loader.dataset)

    train_losses.append(train_loss)
    train_accs.append(train_acc)
    test_losses.append(test_loss)
    test_accs.append(test_acc)

    # 输出训练过程中的信息
    print('Epoch [{}/{}], Train Loss: {:.4f}, Train Acc: {:.4f}, Test Loss: {:.4f}, Test Acc: {:.4f}'
          .format(epoch+1, num_epochs, train_loss, train_acc, test_loss, test_acc))

# 绘制训练和测试的准确率曲线、损失函数曲线以及交叉熵函数曲线
import matplotlib.pyplot as plt

plt.plot(train_losses, label='Train Loss')
plt.plot(test_losses, label='Test Loss')
plt.legend()
plt.show()

plt.plot(train_accs, label='Train Acc')
plt.plot(test_accs, label='Test Acc')
plt.legend()
plt.show()

plt.plot(train_losses, label='Train Cross Entropy')
plt.plot(test_losses, label='Test Cross Entropy')
plt.legend()
plt.show()

这个代码使用了一个简单的卷积神经网络来对MNIST数据集进行分类。在训练过程中，我们记录了训练集和验证集的损失和准确率，并且最后绘制了训练和测试的准确率曲线、损失函数曲线以及交叉熵函数曲线。你可以通过修改超参数和网络结构来进行实验。