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. about conv_snn HOT 4 OPEN

it is my job ;)
well it appears there is a difference in view function of newer pytorch versions,
the second problem is odd!!
ok, i don't have access to my laptop now, it will take approx 12 hours to check this.
I will inform you about the problem and the possible fix.

from conv_snn.

what is the dataset?! what are the shapes?! is this the default dataset?!
please also provide the pytorch version.

from conv_snn.

thanks for reply so fast.
Training dvs-cifar10 and all settings were default, just following the readme.

pytorch version is 1.7.1

from conv_snn.

I add contiguous() to line30 in conv_snn/CIFAR10-DVS/utils.py/ and start to train
correct_k = correct[:k].contiguous().view(-1).float().sum(0)

but got another error FileNotFoundError: [Errno 2] No such file or directory: 'record/spatial/rgb_train.csv'

from conv_snn.