Loydian
Loydian
The document should be updated. The MNIST example is not usable for the latest spikingjelly.
Yes, I use the 0.0.0.10 version. And I am pretty sure the training script is right. When using other models or replace the act_layer with the ReLU, the code work...
No. I just try it. Everything works fine.
I have done this before. The parameter w's device is `cuda:1`. `residual_function.1.1.w : torch.Size([]) cuda:1` `shortcut.1.1.w : torch.Size([]) cuda:1`
When proposing this issue, I have tried to provide a minimul code. But the rest of the model is a new architecture. After removing the proposed block, the problem somehow...
It seems that you transform poses into opencv format. What is this for?