optimiser.setSelectionOperator(RankSelection());
# Create the genetic operators
elitism = ElitismOperator(0.1);
new_blood = NewBloodOperator(0.3);
gaussian_mutation = GaussianMutationOperator(0.1, 0.4);
blend_cross_over = BlendCrossoverOperator(0.5, gaussian_mutation);
# Add the genetic operators to the EA
optimiser.addGeneticOperator(new_blood);
optimiser.addGeneticOperator(gaussian_mutation);
optimiser.addGeneticOperator(blend_cross_over);
optimiser.addGeneticOperator(elitism);
# Print the current state in the console
optimiser.printCurrentStates(0);
# Run the optimisation loop g_iterations times,
# with the mutation variance varying linearly from g_max_mutation_sigma to
# g_min_mutation_sigma
for i in range(g_iterations):
# Compute the value of the mutation variance
sigma = g_min_mutation_sigma + (g_iterations - 1 - i) / (g_iterations - 1) * (g_max_mutation_sigma - g_min_mutation_sigma);
# Set the mutation variance
gaussian_mutation.setMutationVariance(sigma);
# Run the optimisation loop
optimiser.runIteration();
# Print the current state in the console
optimiser.addGeneticOperator(elitism)
for i in range(g_iterations):
# Compute the value of the mutation variance
sigma = g_min_mutation_sigma + (g_iterations - 1 - i) / (
g_iterations - 1) * (g_max_mutation_sigma - g_min_mutation_sigma)
# Set the mutation variance
gaussian_mutation.setMutationVariance(sigma)
start = time.time()
# Run the optimisation loop
optimiser.runIteration()
# Print the current state in the console
optimiser.printCurrentStates(i + 1)
end = time.time()
computing_time = end - start
overall_computing_time += computing_time
if args.plot_metrics:
temp_best_solution = copy.deepcopy(
optimiser.best_solution.parameter_set)
SOD = temp_best_solution[0] * temp_best_solution[1]
SDD = temp_best_solution[1]
setXRayParameters(SOD, SDD)
temp_objective = -optimiser.best_solution.objective