Closed ncolella-mghpcc closed 3 years ago
There are NaN
s because there are different decoder lengths. You can use a min_prediction_length=max_prediction_length
to ensure that the decoder length is always the same. This way, there will be no NaNs.
I have a single data series (i.e. only 1 'label') that I would like to train with validation.
if max_prediction_length > 1, then the last (max_prediction_length - 1) * 2) predictions contain nan.
e.g. if max_prediction_length = 4
How should one do multi-length predictions on a single series with validation?
Similarly, as a more direct modification of the tutorial:
Output: