Ahmed Gad

PyGAD supports training Keras and PyTorch models regardless of the problem. So, yes it supports multi-class problems.

@xshang93, most of the time the best solution is the first solution in the population. This is why the index 0 is returned almost frequently. For some cases, it is...

@gabrieldelpozo, A new release will be pushed soon with a fix to this issue. It happens as crossover creates duplicate genes that, for sometimes , are not solved.

@SimonG85, Thanks for your suggestion and apologize for the late follow-up. The big issue with the `pickle` library is that it cannot detect the referenced object to pickle. We have...

> This is exactly what is happening. Setting `mutation_by_replacement=True` solves the issue.

The pull request https://github.com/ahmedfgad/GeneticAlgorithmPython/pull/73 suggests creating a new parameter called `args`. Then the library just passes this parameter to each call to the fitness function without changes. Since the passed...

@timorichert, So, your `args` are dynamic. You can simply create a new instance attribute to `ga_instance` and fetch it inside the fitness function. If the `args` change after each generation,...

@tearfur, Thank you. Thanks @martinandrovich for your suggestion. By setting: 1. `keep_parents=0` 2. `keep_elitism=0` 3. `save_solutions=False` (Default) Then you guarantee that no fitness is re-used. This means the fitness function...

It can train models built in Keras and PyTorch. Here you can find examples for training PyTorch models: https://github.com/ahmedfgad/GeneticAlgorithmPython/tree/master/examples/TorchGA

Do you you mean change the inputs (not the neural network itself) so that their outputs are accurate? If this is the case, then yes it can be done. Although...