PINN模型中使用torch.autograd.grad计算梯度时触发RuntimeError的问题排查求助

各位大佬好，我现在在开发PINN模型的代码，在为PDE损失项计算梯度时使用了torch.autograd.grad()，但运行时触发了如下错误：

RuntimeError: One of the differentiated Tensors appears to not have been used in the graph. Set allow_unused=True if this is the desired behavior.

出错的代码行是：

dphidx = torch.autograd.grad(train_output[:, 0], X_train_tensor[:,0], torch.ones_like(train_output[:, 0]), create_graph=True)[0]

我已经检查过train_output[:, 0]和X_train_tensor[:,0]的requires_grad属性都是True，但还是搞不清楚问题到底出在哪，实在有点困惑。

为了方便大家排查，我附上模型的代码片段：

import torch.nn as nn

class PINNFP(nn.Module):
    def __init__(self):
        super().__init__()
        self.manual_layers = nn.Sequential(
            nn.Linear(in_features = 3, out_features = 5),
            nn.Linear(in_features = 5, out_features = 5),
            nn.Linear(in_features = 5, out_features = 5),
            nn.Linear(in_features = 5, out_features = ...)  # 原代码此处内容截断
        )

备注：内容来源于stack exchange，提问作者Nafisa Mehtaj