我有一个来自十个类别各100个共1000个的信号数据，每个数据有512个特征点，存储为一个(1000,1,,512)的torch.tensor张量，现在我想将其输入一个深度NNLM网络训练分类模型用于分类这些类别，请使用pytorch实现

以下是一个简单的实现，包含数据加载、模型定义、训练和测试等步骤：

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader

# 定义数据集类
class SignalDataset(Dataset):
    def __init__(self, signals, labels):
        self.signals = signals
        self.labels = labels
    
    def __len__(self):
        return len(self.labels)
    
    def __getitem__(self, idx):
        return self.signals[idx], self.labels[idx]

# 定义模型类
class NNLM(nn.Module):
    def __init__(self):
        super(NNLM, self).__init__()
        self.fc1 = nn.Linear(512, 256)
        self.fc2 = nn.Linear(256, 128)
        self.fc3 = nn.Linear(128, 10)
        
    def forward(self, x):
        x = nn.functional.relu(self.fc1(x))
        x = nn.functional.relu(self.fc2(x))
        x = self.fc3(x)
        return x

# 加载数据
signals = torch.load('signals.pt')
labels = torch.load('labels.pt')
dataset = SignalDataset(signals, labels)
dataloader = DataLoader(dataset, batch_size=32, shuffle=True)

# 定义模型和优化器
model = NNLM()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
for epoch in range(10):
    running_loss = 0.0
    for i, data in enumerate(dataloader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = nn.functional.cross_entropy(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
    print('[Epoch %d] loss: %.3f' % (epoch+1, running_loss/len(dataset)))

# 测试模型
correct = 0
total = 0
with torch.no_grad():
    for data in dataloader:
        inputs, labels = data
        outputs = model(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy: %.2f %%' % (100 * correct / total))

其中，`SignalDataset`是一个继承自`torch.utils.data.Dataset`的数据集类，用于加载信号数据和对应的标签。`NNLM`是一个简单的三层全连接神经网络，用于分类。在训练过程中，我们使用交叉熵损失函数和Adam优化器。在测试过程中，我们使用准确率作为评估指标。