Replies: 1 comment
-
One example solution which worked is by using the below plugin, which when included as one of the plugins to an avalanche strategy helps change the evaluation from iteration to epoch after 5 epochs of training. The code was suggested by Giacomo Cignoni (https://github.com/giacomo-cgn).
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Trying to change the peval_mode after some epochs.
Initially it is set to peval_mode="iteration" for few epochs and then want to change it to peval_mode="epoch".
Example strategy = Naive(..., eval_every=1, peval_mode="iteration")
But able to access the parameter value of strategy.eval_every and not able to access the peval_mode parameter value.
Kindly suggest how to access the value and change it in between epochs.
Beta Was this translation helpful? Give feedback.
All reactions