spikingjelly
spikingjelly copied to clipboard
fangwei123456
SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
我自定义了一个神经元模型，使用MNISTNet()训练，设了1024epoch，epoch0~7的训练结果都正常，从epoch8开始精度突然从0.9922下降到0.098，发现是神经元的输入x变为0导致，但是我不清楚输入变为0从哪里找原因，请指点一下！多谢！
您好： 我将代码下载到本机后，使用pycharm + anaconda进行编译 运行lif_fc_mnist.py出现下面的错误 C:\Program Files (x86)\Anaconda3\python.exe" C:/SNN/spikingjelly/spikingjelly/activation_based/examples/lif_fc_mnist.py -tau 2.0 -T 100 -device cpu -b 64 -epochs 100 -data-dir .\dataset\MNIST -amp -opt adam -lr 1e-3 -j 8 Traceback (most...
QIF and EIF seem unstable under fp16 so far. It's particularly severe on QIF. I suggest not to use cupy backend and fp16 together for these models. # QIF ```python...
I have removed spikingjelly installed before,(0.0.0.0.12) and reinstall through pip. However, I cannot load module in newest version.
I use the latest version of SJ, but I find neither the 'LIFNode' or 'MultiStepLIFNode' object has attribute 'spike' when I try to use the 'visualizing' function.
Hi @fangwei123456 , How I can plot training and validation curves for this model?. Please guide. Best
I have checked the documentation and I realized that many surrogate functions exist. My question is, is there anyway to have the one used by SLAYER https://arxiv.org/pdf/1810.08646.pdf ?
您好！我最近在了解resnet的ann2snn的工作，我跑了spikingjelly中的示例，取得了不错的效果，但是我对其内部工作原理还不是很清楚。示例中用到的是最大激活归一化，但是对shortcut是如何处理的呢？十分期待您的解答！
When Implementing the SEW block in my own model, I met a problem as blow. ``` Traceback (most recent call last): File "/home/lyd/spikeformer/spikeformer.py", line 612, in loss.backward() File "/home/snn/anaconda3/envs/torch17/lib/python3.6/site-packages/torch/tensor.py", line...
Metadata
Owner
Metadata
SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.