Pytorch LSTM grad仅适用于上一次输出

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

class SimpleLSTM(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, output_size):
        super(SimpleLSTM, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = 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

# 参数设置
input_size = 10
hidden_size = 20
num_layers = 2
output_size = 1
learning_rate = 0.01
num_epochs = 10

model = SimpleLSTM(input_size, hidden_size, num_layers, output_size)
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# 模拟输入数据
inputs = torch.randn(32, 5, input_size)  # batch_size, sequence_length, input_size
targets = torch.randn(32, output_size)

for epoch in range(num_epochs):
    model.train()
    optimizer.zero_grad()
    outputs = model(inputs)
    loss = criterion(outputs, targets)
    loss.backward()
    
    # 梯度裁剪
    torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
    
    optimizer.step()
    print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')