Replay strategy (mem_size= ?? , train_mb_size=?? )

[ZaidRZ]

Hi Everyone,

I have a time series Datase, with Dimention [batchsize, 125, 45].
Trying to execute Replay Strategy.
My model is: model = Classifier(in_dim=45, hidden_dim=18, out_dim=4, layers=2).
what is the ( mem_size= , train_mb_size= ) should I use ??

i used the default and get the error:
File "/home/zaid/miniconda3/envs/zaid_ts/lib/python3.8/site-packages/torch/functional.py", line 72, in broadcast_tensors
return _VF.broadcast_tensors(tensors) # type: ignore[attr-defined]
RuntimeError: The size of tensor a (4) must match the size of tensor b (2) at non-singleton dimension 1