Keras Training warm_start
--------------------------------------------------
Hire the world's top talent on demand or became one of them at Toptal: https://topt.al/25cXVn
--------------------------------------------------
Music by Eric Matyas
https://www.soundimage.org
Track title: Digital Sunset Looping
--
Chapters
00:00 Keras Training Warm_start
00:37 Accepted Answer Score 8
01:04 Thank you
--
Full question
https://stackoverflow.com/questions/4531...
--
Content licensed under CC BY-SA
https://meta.stackexchange.com/help/lice...
--
Tags
#python #machinelearning #scikitlearn #neuralnetwork #keras
#avk47
Hire the world's top talent on demand or became one of them at Toptal: https://topt.al/25cXVn
--------------------------------------------------
Music by Eric Matyas
https://www.soundimage.org
Track title: Digital Sunset Looping
--
Chapters
00:00 Keras Training Warm_start
00:37 Accepted Answer Score 8
01:04 Thank you
--
Full question
https://stackoverflow.com/questions/4531...
--
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.