Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information

[Precola]

RSet TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information

We are glad to add new developers who are volunteering to help solve issues to the above table.

Issue type

• [x ] Bug Report
• Feature Request
• Help wanted
• Other

SpikingJelly version

0.0.0.0.14

Description

...

Minimal code to reproduce the error/bug

from spikingjelly.activation_based.neuron import LIFNode, IFNode

...

self.lif = IFNode(step_mode='m', detach_reset=True, backend='torch', v_threshold=0.1)

Error

    spike_seq, self.v = self.jit_eval_multi_step_forward_hard_reset(x_seq, self.v, self.v_threshold,

Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information


You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True

Although "import torch._dynamo
torch._dynamo.config.suppress_errors = True"
works, I still want to know how to avoid this issue without using "torch._dynamo.config.suppress_errors = True".