conv_snn

conv_snn copied to clipboard

about the hybrid training method proposed in the paper

2

Hello author, it seems that there is no hybrid training method proposed in the paper (STS-ResNet on the CIFAR10-DVS dataset) in the code implementation. Is this the final version of...

zhangyu199802

NameError: name 'lr_scheduler' is not defined

1

Running the code in folder Tests_1-3_and_5. It seens that all the code had the same error below. ``` 8192it [00:02, 3912.96it/s] 9920512it [00:19, 1117448.86it/s] Epoch [1/10], Step [100/600], Loss: nan...

meltingCat

Thanks for sharing the code of this paper. I am still wondering if the current code is the latest for the paper? As I find that some people find some...

wangxiao5791509

about seq5 in synthetic dataset

3

In you paper, the seq5 example in Figure 4 is rotated with a random degree between 0 and 360 degrees. but it can't be distinguished between clockwise or counterclockwise. Because...

edwardzcl

RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

4

Got an error in **Training & Testing** ``` (conv_snn) test@test-dual1060:~/Desktop/project/conv_snn/CIFAR10-DVS$ python3 main.py device cuda 0%| | 0/1750 [00:00

meltingCat

First convolution is on input instead of synapse output

2

The first convolution at here: https://github.com/aa-samad/conv_snn/blob/master/CIFAR10-DVS/network.py#L158 is on input spikes. Figure 3 in the paper shows that it should be on the synapse output: https://arxiv.org/pdf/2003.12346.pdf

arkhodamoradi

Parameter or weight for high accuracy

1

Hi, We are trying to make some further developments based on your methods. Is it possible to share the training parameters to achieve the high accuracy or even the trained...

zhoujuncc1

c1_mem and c1_spike and output

2

I am trying to understand how c1_spike and c1_mem affect the output. Between https://github.com/aa-samad/conv_snn/blob/master/CIFAR10-DVS/network.py#L163 and https://github.com/aa-samad/conv_snn/blob/master/CIFAR10-DVS/network.py#L76 It seems that they do get updated by the input but do not affect...

arkhodamoradi

Hello author, it looks like the latest code hasn't been uploaded yet. If possible, could you upload it? This will be very helpfu to me. Thanks!

zzxhwkq

@meltingCat from torch.optim import lr_scheduler _Originally posted by @wangxiao5791509 in https://github.com/aa-samad/conv_snn/issues/11#issuecomment-918962797_ after importing am getting the following error 'module' object is not callable

venki-11