Accuracy not improving on CIFAR-10 dataset

[sauravtii]

Hello!

I am trying out tutorial_6 (https://colab.research.google.com/github/jeshraghian/snntorch/blob/master/examples/tutorial_6_CNN.ipynb) but the only difference is I am using CIFAR-10 dataset instead of MNIST. I trained it for 10 epochs but the accuracy wasn't good, so I tried training for 50 epochs and the accuracy is still around 35-40 %. Can anyone please guide me on resolving this issue ?

[ahenkes1]

Have you tried a larger network?

[jeshraghian]

Converted to a discussion.

I've been able to train a dense SNN with one hidden layer to hit around 50%, so a CSNN should exceed that. Consider a larger model, more time steps, adding batchnorm, using a learning rate schedule, etc.