能不能帮我写一个pytorch环境的神经网络代码

当然可以！以下是一个简单的神经网络代码示例，使用PyTorch框架：

import torch
import torch.nn as nn
import torch.optim as optim

# 定义神经网络模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(784, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = nn.functional.relu(x)
        x = self.fc2(x)
        output = nn.functional.log_softmax(x, dim=1)
        return output

# 定义损失函数和优化器
model = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)

# 训练模型
for epoch in range(10):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        
        optimizer.zero_grad()
        
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 1000 == 999:
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 1000))
            running_loss = 0.0

print('Finished Training')

这个示例代码将创建一个包含两个线性层的神经网络，用于对手写数字进行分类。训练过程将使用SGD优化器和交叉熵损失函数。你可以根据你的需求修改模型结构、优化器和损失函数等。