fangwei123456

建议你用类似的方法修改模型的定义代码，让key和check point一致

You can get them at https://github.com/fangwei123456/Spike-Element-Wise-ResNet/blob/main/origin_logs/cifar10dvs/SEWResNet_ADD_T_16_T_train_None_SGD_lr_0.01_CosALR_64_amp/args.txt This issue is also helpful: https://github.com/fangwei123456/Spike-Element-Wise-ResNet/issues/1

没试过在新版上训练imagenet，但精度应该没什么差距。

This is the loris: https://github.com/neuromorphic-paris/loris If you want to use the old version of SJ, you need to install it. The new version does not need it. I recommend to...

Try to run `pip install spikingjelly -U`.

I just re-train this network with the current version of SJ and get 73.8 acc1. I still use the PLIF neuron. I think the accuracy around ±74 is enough. ```...

> Hello, during experiment, I found that the output of SEW block is not only 0 or 1 (i.e. pulse) If you use `ADD`, it is normal to appear int...

> On such a chip, is the multiplication operation between the 8bit spike value and the weight acceptable? I do not know much about it. > Can I take Sew...

It takes about 10 minutes for one epoch with resnet18. You can also download tensorboard logs in this repo and check the used time with tensorboard.

https://github.com/fangwei123456/Spike-Element-Wise-ResNet/tree/main/origin_logs/imagenet