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
Thanks for the implementation of Keras gru4rec.
I notify some issues in your code:
The get_metric function does not take use of mask variable to reset the state after each session, thus the evaluation results may be wrong.
Issue with SessionDataLoader. Since every session is varied in length, all the remaining events in the last batch_size sessions will not be processed as soon as one of this session finishes (while loop stops when maxiter >= len(click_offsets) - 1 but maxiter starts from max(batch_size), apparently we did not process all events). You can confirm it by comparing the total number of generated feat with (the total number of events - the total number of unique session).
This can affect the evaluation result where number of batch_size is large and number of unique session is small. One potential fix is to use zero masking.
The text was updated successfully, but these errors were encountered:
I haven't looked into (2), nor evaluated the potential impact on evaluation metrics. Your comment has been a good reminder of this issue. I'll try to address it in the coming weeks, but no promises.
If you want to take a stab at it, I'd also be happy to review any pull requests 👍
@paxcema thank you for giving a schedule.
btw, I has completed training my models using your setup, but I am not sure how can I use the h5 files for a recommender system. Can I receive some advices?
Thanks for the implementation of Keras gru4rec.
I notify some issues in your code:
This can affect the evaluation result where number of batch_size is large and number of unique session is small. One potential fix is to use zero masking.
The text was updated successfully, but these errors were encountered: