RuntimeError：梯度计算所需的变量之一已被就地操作修改：PyTorch 错误

问：

我正在尝试在PyTorch中运行一些代码，但此时我被堆积起来了：

在第一次迭代中，鉴别器和生成器的向后操作都运行良好

....

self.G_loss.backward(retain_graph=True)

self.D_loss.backward()

...

在第二次迭代中，执行时，我收到以下错误：self.G_loss.backward(retain_graph=True)

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [8192, 512]] is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!

根据 ，鉴别器网络中以下最后一行对此负责：torch.autograd.set_detect_anomaly

    bottleneck = bottleneck[:-1]
    self.embedding = x.view(x.size(0), -1)
    self.logit = self.layers[-1](self.embedding)

奇怪的是，我在其他代码中使用了该网络架构，并且它正常工作。有什么建议吗？

完整的错误：

    site-packages\torch\autograd\__init__.py", line 127, in backward
    allow_unreachable=True)  # allow_unreachable flag
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [8192, 512]] is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!