SNN usage problems

[enemy1205]

Once I use the spike neural network-related modules in Spike-Driven Transformer-V2, I encounter problems during training ：
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.