GEM in Time series dataset

[ZaidRZ]

Hello,

thanks for all your work.

I used GEM on specific Time series Dataset

The data set dimensions [ 1919, 125, 45]
model = Classifier(in_dim=45, hidden_dim=18, out_dim=4, layers=2)

Got this error
RuntimeError: The size of tensor a (4) must match the size of tensor b (70) at non-singleton dimension 1

my question is in GEM algorithm how to calculate patterns_per_exp ??

Thanks a lot in advance.