Fedir Navruzov

I've encountered the same RuntimeError with shape mismatch when using `AggregationMetric(some_metric)` as loss. To my understanding, it was connected with the predictions and actuals shape mismatch: - actuals are of...

Have you tried "weight" argument while creating datasets? You can create a column with weights to be used in training ```python ds = TimeSeriesDataSet( data=data[train_data_filter], time_idx=time_idx_col, target=..., weight='weight', # pass...

Nice catch and workaround! I was facing the same error and was thinking of monkeypatching, but simple inheritance change solved the issue, thank you!