Closed taepatipol closed 4 years ago
I have founded the solution.
file = open('winner.pkl','rb')
genome = pickle.load(file)
file.close()
config = neat.Config(neat.DefaultGenome, neat.DefaultReproduction,
neat.DefaultSpeciesSet, neat.DefaultStagnation,
'config-feedforward')
net = neat.nn.recurrent.RecurrentNetwork.create(genome, config)
Are there anyway to convert a single genome (the winner genome from population.run that I pickled) to neural network? So I can use the winner neural network for another data.