Fixed yielding rate in the generator
Adk2001tech opened this issue · comments
Problem
There is a limited data yield in the generator which stops data iteration (hence no data will now yield by generator) in 1 complete cycle. Limiting developer to reassess the same data twice in a loop.
Solution and Alternatives
Making the generator yields inexhaustible data and simultaneously adding training steps in model training.
👋 @Adk2001tech! Thank you for opening your first issue in this repo. We are so happy that you have decided to contribute and value your contribution. Please read these materials before proceeding: Contributing Guide and Code of Conduct.
Thanks for raising the issue @Adk2001tech 😀
Would you like to create a PR for this?
@aniketmaurya please assign this to me✋. I am working on it😃.
Thanks
I have some questions @aniketmaurya
- does validation_data is an Object of class Dataset ? (can necessarily be the object or can be just a simple tuple of (image, label) pairs)
- same for train_data in class Learner .
As it is note mentioned in code comments.
Thanks
Hi @Adk2001tech, both validation_data
and train_data
are of type tf.data.Dataset
Hi @Adk2001tech, both
validation_data
andtrain_data
are of type tf.data.Dataset
sure 👍