Keras Training warm_start
Become part of the top 3% of the developers by applying to Toptal https://topt.al/25cXVn
--
Music by Eric Matyas
https://www.soundimage.org
Track title: Over Ancient Waters Looping
--
Chapters
00:00 Question
00:49 Accepted answer (Score 7)
01:23 Thank you
--
Full question
https://stackoverflow.com/questions/4531...
Accepted answer links:
[train_on_batch]: https://keras.io/models/model/#train_on_...
[Callbacks]: https://keras.io/callbacks/
--
Content licensed under CC BY-SA
https://meta.stackexchange.com/help/lice...
--
Tags
#python #machinelearning #scikitlearn #neuralnetwork #keras
#avk47
--
Music by Eric Matyas
https://www.soundimage.org
Track title: Over Ancient Waters Looping
--
Chapters
00:00 Question
00:49 Accepted answer (Score 7)
01:23 Thank you
--
Full question
https://stackoverflow.com/questions/4531...
Accepted answer links:
[train_on_batch]: https://keras.io/models/model/#train_on_...
[Callbacks]: https://keras.io/callbacks/
--
Content licensed under CC BY-SA
https://meta.stackexchange.com/help/lice...
--
Tags
#python #machinelearning #scikitlearn #neuralnetwork #keras
#avk47
ACCEPTED ANSWER
Score 8
Yes - it's possible. But rather cumbersome. You need to use train_on_batch function which keeps all model parameters (also optimizer ones).
This is cumbersome because you need to divide your dataset to batches on your own and you are also losing the possibility to apply Callbacks and to use automatic progbar. I hope that in new Keras version this option would be added to a fit method.