Pytorch报错：Variable._execution_engine.run_backward( # Calls into the C++ engine...

Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass

RuntimeError: Trying to backward through the graph a second time (or directly access saved tensors after they have already been freed). Saved intermediate values of the graph are freed when you call .backward() or autograd.grad(). Specify retain_graph=True if you need to backward through the graph a second time or if you need to access saved tensors after calling backward.

遇到该问题从头检查pytorch反向传播对应的图，每个属性requires_grad=True的参数都要重新计算一遍，不能遗漏。