KerasGA (from PyGad) doesn't work with TF/Keras?

TensorFlow General Discussion
, ,
1

i modeled some regression test cases with TF/Keras (in a Python environment) and tried to train the resulting NNs with “KerasGA” from PyGad. But I was not successful:

For any test case, KerasGA converged (fast) to something like the mean value of the desired outputs, but there was no tendency for the individual output / example to be modelled…

So my questions are:

What might be the reason for this insufficient GA-based training?
Where should I look at to identify my mistake?
Are there other Python -based packages (for the GA-based training of Keras models) which I should try?

Any hints is welcome…

4

Hello @rudel_s

Thank you for using TensorFlow
There may be few reasons for this issue, if the population of the single generation is too low or the number of generations considered is less, some times it would be about model is not complex enough to understand the patterns.