RAM consumption on GPU Grows Infinitely

[hyang0129]

https://github.com/PaulPauls/Tensorflow-Neuroevolution/blob/55c76f08ee4e4206d842565902b3d11c517c3756/tfne/environments/cifar10_environment.py#L64

This isn't about the VRAM, which seems to be cleared properly. The problem lies with the system RAM when running the _eval_genome_fitness_weight_training method when using a GPU. The RAM usage balloons over time.

This can be fixed by implementing a clear session before or after the evaluation method.

def _eval_genome_fitness_weight_training(self, genome) -> float:
    K.clear_session()
    
    model = genome.get_model()
    optimizer = genome.get_optimizer()

    do stuff