You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The data is pairs of time, price, yet the future_predictions is a tensor of 36x37. 36 is the forecasting length.
Struggling to understand what this represents. With an ordinary model, you would expect 36x1 perhaps; I know that DeepAR predicts a range, is it the case that each time index just so happens to include as many predictions as there are time indexes?
The text was updated successfully, but these errors were encountered:
I couldn't reproduce your problem. I tried a small dataframe, the DeepAR model from the sample and your settings, and got a sequence of scalar predictions. Do you mind testing with a small dataframe and, if the problem persists, copy the entire reproducible code snippet here?
Hint: adding the word "Python" after your "```" makes your code snippet more legible.
I have a DeepAR model that I have built from the sample. I am not really sure how to interpret the results of the
predict()
method though:The data is pairs of time, price, yet the
future_predictions
is a tensor of 36x37. 36 is the forecasting length.Struggling to understand what this represents. With an ordinary model, you would expect 36x1 perhaps; I know that DeepAR predicts a range, is it the case that each time index just so happens to include as many predictions as there are time indexes?
The text was updated successfully, but these errors were encountered: