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
{{ message }}
This repository has been archived by the owner on Dec 29, 2022. It is now read-only.
What is the best way to implement model ensembling per time step in Tensorflow? Models are ensembled by averaging the output probabilities at each decoding step. Is there a way to do this using raw_rnn?
The text was updated successfully, but these errors were encountered:
Second that. I need the same feature too. Right now I couldn't figure out a way more elegant than just using vanilla tf.while_loop() to achieve the ensemble.
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
What is the best way to implement model ensembling per time step in Tensorflow? Models are ensembled by averaging the output probabilities at each decoding step. Is there a way to do this using
raw_rnn
?The text was updated successfully, but these errors were encountered: