rnn

Hi I would like to propose a better implementation for 'test_indices':

We can remove the unneeded np.array casting:

Cleaner/New:
test_indices = list(set(range(len(texts))) - set(train_indices))

Old:
test_indices = np.array(list(set(range(len(texts))) - set(train_indices)))

Hi,

Thanks for this great project! I encounter a problem when I try to reproduce the result from the MiniRocket tutorial notebook. In the Offline Pytorch implementation section, I find that the predicted label does not match the one in y. For example:

Here the preds are actually r