Trying to backward through the graph a second time, but the saved intermediate results have already been freed. Specify retain_graph=True when calling backward the first time.

[chensjtu]

when I use the config, fern_ngp, it raise error, I add retain_graph, but still _module_function_backwardBackward.forward: expected Tensor or tuple of Tensor (got NoneType) for return value 0 may you tell me how to fix it? torch 1.7.1 cu11