Closed Snow-Crash closed 1 year ago
The default parameters are shown in codes:
The hyper-parameters need to be fine-tuned with batch_size
, lr
and n-gpus
. Thus, I can not give the "best" hyper-parameters. In most cases, you can try batch_size=32
and lr=0.1
.
Does loading a pretrianed dnn resnet really help?
Yes.
Hi, thanks for open sourcing this great library. I'm using version 0.0.0.0.12 to run some experiments with sewresnet. I followed the traing code from https://spikingjelly.readthedocs.io/zh_CN/0.0.0.0.12/clock_driven_en/16_train_large_scale_snn.html The only change is below, i.e. use sewresent instead of spiking_resnet
net = sew_resnet.multi_step_sew_resnet18(T=4, pretrained=True, multi_step_neuron=neuron.MultiStepIFNode, surrogate_function=surrogate.ATan(), detach_reset=True, backend='cupy', cnf='ADD')
Thanks!