def getbest(i):
g = NEAT.Genome(0, substrate.GetMinCPPNInputs(), 2,
substrate.GetMinCPPNOutputs(), False,
NEAT.ActivationFunction.TANH, NEAT.ActivationFunction.TANH,
0, params)
pop = NEAT.Population(g, params, True, 1.0, i)
pop.RNG.Seed(i)
for generation in range(2000):
genome_list = NEAT.GetGenomeList(pop)
# if sys.platform == 'linux':
# fitnesses = EvaluateGenomeList_Parallel(genome_list, evaluate, display=False)
# else:
fitnesses = EvaluateGenomeList_Serial(genome_list,
evaluate,
display=False)
[
genome.SetFitness(fitness)
for genome, fitness in zip(genome_list, fitnesses)
]
print('Gen: %d Best: %3.5f' % (generation, max(fitnesses)))
best = max(fitnesses)
pop.Epoch()
generations = generation
if best > 15.0:
break
return generations
def getbest(i):
g = NEAT.Genome(0, 3, 0, 1, False, NEAT.ActivationFunction.UNSIGNED_SIGMOID,
NEAT.ActivationFunction.UNSIGNED_SIGMOID, 0, params, 0)
pop = NEAT.Population(g, params, True, 1.0, i)
# pop.RNG.Seed(int(time.clock()*100))
pop.RNG.Seed(1234)
generations = 0
for generation in range(max_generations):
genome_list = NEAT.GetGenomeList(pop)
fitness_list = EvaluateGenomeList_Serial(genome_list, evaluate, display=False)
# fitness_list = EvaluateGenomeList_Parallel(genome_list, evaluate, display=False)
NEAT.ZipFitness(genome_list, fitness_list)
pop.Epoch()
generations = generation
best = max(fitness_list)
if best > 15.0:
break
net = NEAT.NeuralNetwork()
pop.GetBestGenome().BuildPhenotype(net)
# img = NEAT.viz.Draw(net)
# cv2.imshow("current best", img)
# cv2.waitKey(1)
return generations, net.NumHiddenNeurons(), net.NumConnections()
def run_experiment(config_file, trial_id, n_generations, out_dir, view_results=False, save_results=True):
"""
The function to run the experiment against hyper-parameters
defined in the provided configuration file.
The winner genome will be rendered as a graph as well as the
important statistics of neuroevolution process execution.
Arguments:
config_file: The path to the file with experiment
configuration
trial_id: The ID of current trial
n_generations: The number of evolutionary generations
out_dir: The directory to save intermediate results.
view_results: The flag to control if intermediate results should be displayed after each trial
save_results: The flag to control whether intermediate results should be saved after each trial.
Returns:
The tuple (solution_found, generation, complexity, best_genome_fitness) that has flag indicating whether
solution was found, the generation when solution was found, the complextity of best genome, and the fitness
of best genome.
"""
g = NEAT.Genome(0, 4+1, 0, 1+1, False, NEAT.ActivationFunction.TANH,
NEAT.ActivationFunction.TANH, 0, params, 0)
pop = NEAT.Population(g, params, True, 1.0, trial_id)
# set random seed
seed = int(time.time())
pop.RNG.Seed(seed)
generations = 0
solved = False
best_trial_fitness = 0
best_trial_complexity = 0
for generation in range(n_generations):
genome_list = NEAT.GetGenomeList(pop)
fitness_list = EvaluateGenomeList_Serial(genome_list, evaluate, display=view_results)
NEAT.ZipFitness(genome_list, fitness_list)
generations = generation
best = max(genome_list, key=get_fitness)
best_fitness = best.GetFitness()
complexity = best.NumNeurons() + best.NumLinks()
solved = best_fitness >= cart.MAX_FITNESS # Changed to correspond limit used with other tested libraries
if solved:
best_trial_fitness = best_fitness
best_trial_complexity = complexity
print("Trial: %2d\tgeneration: %d\tfitness: %f\tcomplexity: %d\tseed: %d" %
(trial_id, generations, best_trial_fitness, complexity, seed))
break
# check if best fitness in this generation is better than current maximum
if best_fitness > best_trial_fitness:
best_trial_complexity = complexity
best_trial_fitness = best_fitness
# move to the next epoch
pop.Epoch()
if not solved:
print("Trial: %2d\tFAILED\t\tfitness: %f\tcomplexity: %d\tseed: %d" %
(trial_id, best_trial_fitness, best_trial_complexity, seed))
return solved, generations, best_trial_complexity, best_trial_fitness
def getbest(run):
g = NEAT.Genome(0, substrate.GetMinCPPNInputs(), 0,
substrate.GetMinCPPNOutputs(), False,
NEAT.ActivationFunction.TANH, NEAT.ActivationFunction.TANH,
0, params)
pop = NEAT.Population(g, params, True, 1.0, run)
for generation in range(1000):
# Evaluate genomes
genome_list = NEAT.GetGenomeList(pop)
fitnesses = EvaluateGenomeList_Serial(genome_list,
evaluate_xor,
display=False)
[
genome.SetFitness(fitness)
for genome, fitness in zip(genome_list, fitnesses)
]
print('Gen: %d Best: %3.5f' % (generation, max(fitnesses)))
# Print best fitness
# print("---------------------------")
# print("Generation: ", generation)
# print("max ", max([x.GetLeader().GetFitness() for x in pop.Species]))
# Visualize best network's Genome
net = NEAT.NeuralNetwork()
pop.Species[0].GetLeader().BuildPhenotype(net)
img = np.zeros((500, 500, 3), dtype=np.uint8)
img += 10
NEAT.DrawPhenotype(img, (0, 0, 500, 500), net)
cv2.imshow("CPPN", img)
# Visualize best network's Pheotype
net = NEAT.NeuralNetwork()
pop.Species[0].GetLeader().BuildESHyperNEATPhenotype(
net, substrate, params)
img = np.zeros((500, 500, 3), dtype=np.uint8)
img += 10
NEAT.DrawPhenotype(img, (0, 0, 500, 500), net, substrate=True)
cv2.imshow("NN", img)
cv2.waitKey(1)
if max(fitnesses) > 15.0:
break
# Epoch
generations = generation
pop.Epoch()
return generations
def getbest(i):
g = NEAT.Genome(0, 3, 0, 1, False, NEAT.ActivationFunction.UNSIGNED_SIGMOID,
NEAT.ActivationFunction.UNSIGNED_SIGMOID, 0, params)
pop = NEAT.Population(g, params, True, 1.0, i)
pop.RNG.Seed(int(time.clock()*100))
generations = 0
for generation in range(1000):
genome_list = NEAT.GetGenomeList(pop)
fitness_list = EvaluateGenomeList_Serial(genome_list, evaluate, display=False)
NEAT.ZipFitness(genome_list, fitness_list)
pop.Epoch()
generations = generation
best = max(fitness_list)
if best > 15.0:
break
return generations
def getbest(i):
g = NEAT.Genome(0, substrate.GetMinCPPNInputs(), 0,
substrate.GetMinCPPNOutputs(), False,
NEAT.ActivationFunction.TANH, NEAT.ActivationFunction.TANH,
0, params, 0)
pop = NEAT.Population(g, params, True, 1.0, i)
pop.RNG.Seed(i)
for generation in range(max_generations):
genome_list = NEAT.GetGenomeList(pop)
# if sys.platform == 'linux':
# fitnesses = EvaluateGenomeList_Parallel(genome_list, evaluate, display=False)
# else:
fitnesses = EvaluateGenomeList_Serial(genome_list,
evaluate,
display=False)
[
genome.SetFitness(fitness)
for genome, fitness in zip(genome_list, fitnesses)
]
net = NEAT.NeuralNetwork()
pop.GetBestGenome().BuildPhenotype(net)
complexity = "complexity ({}, {})".format(net.NumHiddenNeurons(),
net.NumConnections())
print('Gen: %d/%d Best: %3.5f. %s' %
(generation, max_generations - 1, max(fitnesses), complexity))
best = max(fitnesses)
pop.Epoch()
generations = generation
if best > 15.0:
break
return generations
def run_experiment(params, trial_id, n_generations, out_dir=None, view_results=False, save_results=True):
g = NEAT.Genome(0, 3, 0, 1, False, NEAT.ActivationFunction.UNSIGNED_SIGMOID,
NEAT.ActivationFunction.UNSIGNED_SIGMOID, 0, params, 0)
pop = NEAT.Population(g, params, True, 1.0, trial_id)
# set random seed
seed = int(time.time())
pop.RNG.Seed(seed)
generations = 0
solved = False
max_fitness = 0
complexity = 0
for generation in range(n_generations):
genome_list = NEAT.GetGenomeList(pop)
fitness_list = EvaluateGenomeList_Serial(genome_list, evaluate, display=view_results)
NEAT.ZipFitness(genome_list, fitness_list)
generations = generation
best = max(genome_list, key=get_fitness)
best_fitness = best.GetFitness()
complexity = best.NumNeurons() + best.NumLinks()
solved = best_fitness > 15.5 # Changed to correspond limit used with other tested libraries
if solved:
max_fitness = best_fitness
print("Trial: %2d\tgeneration: %d\tfitness: %f\tcomplexity: %d\tseed: %d" % (trial_id, generations, max_fitness, complexity, seed))
break
# check if best fitness in this generation is better than current maximum
max_fitness = max(best_fitness, max_fitness)
# move to the next epoch
pop.Epoch()
if not solved:
print("Trial: %2d\tFAILED\t\tfitness: %f\tcomplexity: %d\tseed: %d" % (trial_id, max_fitness, complexity, seed))
return solved, generations, complexity, max_fitness
def getbest(run):
g = NEAT.Genome(0,
substrate.GetMinCPPNInputs(),
3,
substrate.GetMinCPPNOutputs(),
False,
NEAT.ActivationFunction.TANH,
NEAT.ActivationFunction.TANH,
0,
params)
pop = NEAT.Population(g, params, True, 1.0, run)
maxf_ever = 0
hof = []
for generation in range(300):
# Evaluate genomes
genome_list = NEAT.GetGenomeList(pop)
fitnesses = EvaluateGenomeList_Serial(genome_list, evaluate_xor, display=True)
[genome.SetFitness(fitness) for genome, fitness in zip(genome_list, fitnesses)]
print('Gen: %d Best: %3.5f' % (generation, max(fitnesses)))
# Print best fitness
# print("---------------------------")
# print("Generation: ", generation)
# print("max ", max([x.GetLeader().GetFitness() for x in pop.Species]))
# maxf = max([x.GetFitness() for x in NEAT.GetGenomeList(pop)])
# print('Generation: {}, max fitness: {}'.format(generation, maxf))
# if maxf > maxf_ever:
# with open("lastGenWinner",'w') as f:
# f.write(pickle.dumps(net)
# maxf_ever = maxf
# Visualize best network's Genome
net = NEAT.NeuralNetwork()
pop.Species[0].GetLeader().BuildPhenotype(net)
# img = np.zeros((400, 400, 3), dtype=np.uint8)
# img += 10
# NEAT.DrawPhenotype(img, (0, 0, 400, 400), net)
# cv2.imshow("CPPN", img)
# # Visualize best network's Pheotype
# net = NEAT.NeuralNetwork()
pop.Species[0].GetLeader().BuildESHyperNEATPhenotype(net, substrate, params)
# img = np.zeros((400, 400, 3), dtype=np.uint8)
# img += 10
# NEAT.DrawPhenotype(img, (0, 0, 400, 400), net, substrate=True)
# cv2.imshow("NN", img)
# cv2.waitKey(33)
# time.sleep(2)
with open('winnerGenome', 'wb') as f:
pickle.dump(str(pop.GetBestGenome()),f)
with open('winnerNet', 'wb') as f:
pickle.dump(str(net), f)
with open('winnerSub', 'wb') as f:
pickle.dump(str(substrate), f)
with open('winnerParams', 'wb') as f:
pickle.dump(str(params), f)
if max(fitnesses) > 20000.0:
break
# Epoch
generations = generation
pop.Epoch()
return generations
def run_population_evolution():
genoma = NEAT.Genome(0, 2, num_neuron_hidden, 1, False, NEAT.ActivationFunction.UNSIGNED_SIGMOID, NEAT.ActivationFunction.UNSIGNED_SIGMOID, seed_gen, params, num_hidden_layers)
pop = NEAT.Population(genoma, params, True, 1.0, 0)
best_index_ever = 0
best_generation_ever = 0
for generation in xrange(0, full_generations):
genome_list = NEAT.GetGenomeList(pop)
fitness_list = EvaluateGenomeList_Serial(genome_list, train_genome, display=False)
NEAT.ZipFitness(genome_list, fitness_list)
best = max(fitness_list)
best_index = fitness_list.index(max(fitness_list))
datah.evhist.append(best)
if best > datah.best_fit_ever:
sys.stdout.flush()
datah.best_gs.append(pop.GetBestGenome())
datah.best_fit_ever = best
best_index_ever = best_index
best_generation_ever = generation
else:
pass
# Store the species contained in the population
storeSpecies = []
numSpecies = [0 for n in xrange(0, len(pop.Species))]
for n in xrange(0, len(numSpecies)):
numSpecies[n] = specie()
numSpecies[n].ID = pop.Species[n].ID()
numSpecies[n].tamano = pop.Species[n].NumIndividuals()
storeSpecies.append(numSpecies[n])
datah.species.append(storeSpecies)
# Store the statistical data for representation of the evolution
datah.bestIndividualsInGeneration[datah.generation] = pop.GetBestGenome()
datah.valueFitnessMax[datah.generation] = best
datah.valueFitnessMediana[datah.generation] = np.median(fitness_list)
datah.perc75[datah.generation] = np.percentile(fitness_list, 75)
datah.perc25[datah.generation] = np.percentile(fitness_list, 25)
datah.valueFitnessMedia[datah.generation] = np.average(fitness_list)
datah.fitnessValidation[datah.generation] = validation_genome(pop.GetBestGenome())
datah.generation = cp.deepcopy(datah.generation + 1)
if datah.generation > datah.max_generations - 1:
sf.saveStatistics(datah, directory)
else:
pass
if datah.generation > datah.max_generations - 1:
sf.representationTrain_Validation(datah, directory, topLimit)
else:
pass
pop.Epoch()
print 'Best_fit_ever:', datah.best_fit_ever
print('Generacion:', generation, 'Mejor:', round(best, 3), 'Mediana:', round(np.median(fitness_list), 3), 'Media:',round(np.average(fitness_list), 3), 'Std:', round(np.std(fitness_list), 3))
print(' ')
return (best_generation_ever, best_index_ever, datah.best_gs[len(datah.best_gs) -1], datah.best_fit_ever)
