pytorch代码，将窗口将窗口划分数据集 [样本数, 窗口大小, 特征数]进行张量化，输入

以下是将窗口划分数据集进行张量化并输入LSTM模型的PyTorch代码：

import torch

# 窗口划分数据集，形状为 [样本数, 窗口大小, 特征数]
data = ...

# 将数据集转换为PyTorch张量
data_tensor = torch.tensor(data, dtype=torch.float32)

# 将数据集转换为可以输入LSTM模型的三维张量形式
samples, timesteps, features = data_tensor.shape
data_tensor = data_tensor.view(samples, timesteps, features)

# 定义LSTM模型
class LSTMModel(torch.nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, output_size):
        super(LSTMModel, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = torch.nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = torch.nn.Linear(hidden_size, output_size)

    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(x.device)
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(x.device)
        out, _ = self.lstm(x, (h0, c0))
        out = self.fc(out[:, -1, :])
        return out

# 定义模型参数
input_size = features
hidden_size = 64
num_layers = 2
output_size = 1

# 创建LSTM模型实例
model = LSTMModel(input_size, hidden_size, num_layers, output_size)

# 定义损失函数和优化器
criterion = torch.nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

# 训练模型
num_epochs = 100
for epoch in range(num_epochs):
    # 前向传播
    outputs = model(data_tensor)
    loss = criterion(outputs, target_tensor)

    # 反向传播和优化
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    # 打印损失值
    print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, loss.item()))

其中，data是窗口划分数据集，形状为 [样本数, 窗口大小, 特征数]；input_size是输入数据的特征数；hidden_size是LSTM隐层单元数；num_layers是LSTM层数；output_size是LSTM输出的特征数，这里设为1；num_epochs是训练轮数。在代码中，我们首先将窗口划分数据集转换为PyTorch张量，并将其转换为可以输入LSTM模型的三维张量形式，然后定义LSTM模型、损失函数和优化器。接着，我们对模型进行训练，每轮训练输出损失值。