def test_entropy_search(self):
res = entropy_search(objective_function=objective,
lower=self.lower, upper=self.upper,
n_init=2,
num_iterations=3)
assert len(res["x_opt"]) == 1
assert np.array(res["x_opt"]) >= 0
assert np.array(res["x_opt"]) <= 1
def test_entropy_search(self):
res = entropy_search(objective_function=objective,
lower=self.lower,
upper=self.upper,
n_init=2,
num_iterations=3)
assert len(res["x_opt"]) == 1
assert np.array(res["x_opt"]) >= 0
assert np.array(res["x_opt"]) <= 1
def get_res(self):
lower = self.space.bound[0]
upper = self.space.bound[1]
res = entropy_search(
self.fn,
lower,
upper,
maximizer=self.params.get('maximizer', 'scipy'),
num_iterations=self.params['niter'],
output_path=str(self.output_path),
rng=self.rng,
)
return res
def ent_search():
"""
Entropy search
"""
print('\n============= START Entropy Search OPTIMIZATION =============\n')
print("""Optimization parameters:
- lower = {}
- upper = {}
- num_iter = {}
- maximizer = {}
- model_type = {}
- n_init = {} """.format(lower, upper, args.num_iterations,
args.maximizer, args.model_type,
args.n_init))
results = entropy_search(objective_function,
lower,
upper,
num_iterations=args.num_iterations,
maximizer=args.maximizer,
model=args.model_type)
print(results["x_opt"])
print(results["f_opt"])
print('\n============= END OPTIMIZATION =============\n')
output_path = "./experiments/fabolas/results/cnn_%s/entropy_search_%d" % (
dataset, run_id)
elif dataset == "res_net":
f = ResidualNeuralNetworkOnCIFAR10(rng=rng)
num_iterations = 10
output_path = "./experiments/fabolas/results/res_%s/entropy_search_%d" % (
dataset, run_id)
os.makedirs(output_path, exist_ok=True)
info = f.get_meta_information()
bounds = np.array(info['bounds'])
results = entropy_search(f,
bounds[:, 0],
bounds[:, 1],
num_iterations=num_iterations,
n_init=2,
rng=rng,
output_path=output_path)
results["run_id"] = run_id
results['X'] = results['X'].tolist()
results['y'] = results['y'].tolist()
test_error = []
current_inc = None
current_inc_val = None
key = "incumbents"
for inc in results["incumbents"]:
f = SurrogateSVM(path="/ihome/kleinaa/devel/git/HPOlib/surrogates/")
elif benchmark == "cnn_cifar10":
f = SurrogateCNN(path="/ihome/kleinaa/devel/git/HPOlib/surrogates/")
elif benchmark == "fcnet_mnist":
f = SurrogateFCNet(path="/ihome/kleinaa/devel/git/HPOlib/surrogates/")
elif benchmark == "paramnet":
dataset = sys.argv[4]
f = SurrogateParamNet(dataset, "/ihome/kleinaa/devel/git/HPOlib/surrogates/")
benchmark += "_" + dataset
info = f.get_meta_information()
bounds = np.array(info['bounds'])
if method == "entropy_search":
results = entropy_search(f, bounds[:, 0], bounds[:, 1],
num_iterations=n_iters, n_init=n_init)
elif method == "gp_mcmc":
results = bayesian_optimization(f, bounds[:, 0], bounds[:, 1],
num_iterations=n_iters,
n_init=n_init, model_type="gp_mcmc")
elif method == "gp":
results = bayesian_optimization(f, bounds[:, 0], bounds[:, 1],
num_iterations=n_iters,
n_init=n_init, model_type="gp")
elif method == "rf":
results = bayesian_optimization(f, bounds[:, 0], bounds[:, 1],
num_iterations=n_iters,
n_init=n_init, model_type="rf")
elif method == "random_search":
results = random_search(f, bounds[:, 0], bounds[:, 1],
num_iterations=n_iters)
elif benchmark == "fcnet_mnist":
f = SurrogateFCNet(path="/ihome/kleinaa/devel/git/HPOlib/surrogates/")
elif benchmark == "paramnet":
dataset = sys.argv[4]
f = SurrogateParamNet(dataset,
"/ihome/kleinaa/devel/git/HPOlib/surrogates/")
benchmark += "_" + dataset
info = f.get_meta_information()
bounds = np.array(info['bounds'])
if method == "entropy_search":
results = entropy_search(f,
bounds[:, 0],
bounds[:, 1],
num_iterations=n_iters,
n_init=n_init)
elif method == "gp_mcmc":
results = bayesian_optimization(f,
bounds[:, 0],
bounds[:, 1],
num_iterations=n_iters,
n_init=n_init,
model_type="gp_mcmc")
elif method == "gp":
results = bayesian_optimization(f,
bounds[:, 0],
bounds[:, 1],
num_iterations=n_iters,
n_init=n_init,
results_over_runs = dict()
#################################################
# Initial data setup
#################################################
version = 1
n_init_num = 5
budget_iter = 50
x_init_dir = home_dir + '/IBO_master/experiments_IBO/' + exp_name + '/initial_data/'
x_init_name = 'x_init_{}_v{}.pkl'.format(exp_name, version)
#################################################
# ES main function
#################################################
for it in range(n_runs):
results_over_runs[it] = entropy_search(objective_function,
lower,
upper,
n_init=n_init_num,
init_data=x_init_dir + x_init_name,
num_iterations=budget_iter)
#################################################
# Saving the results
#################################################
output_main_dir = home_dir + '/IBO_master/experiments_IBO/' + exp_name + '/output_main/'
pickle.dump(
results_over_runs,
open(
output_main_dir + "results_{}_{}_init{}_budget{}_v{}.pkl".format(
exp_name, method, n_init_num, budget_iter, version), "wb"))
print(results_over_runs[0])
output_path = "./experiments/fabolas/results/cnn_%s/entropy_search_%d" % (dataset, run_id)
elif dataset == "svhn":
f = ConvolutionalNeuralNetworkOnSVHN(rng=rng)
num_iterations = 15
output_path = "./experiments/fabolas/results/cnn_%s/entropy_search_%d" % (dataset, run_id)
elif dataset == "res_net":
f = ResidualNeuralNetworkOnCIFAR10(rng=rng)
num_iterations = 10
output_path = "./experiments/fabolas/results/%s/entropy_search_%d" % (dataset, run_id)
os.makedirs(output_path, exist_ok=True)
info = f.get_meta_information()
bounds = np.array(info['bounds'])
results = entropy_search(f, bounds[:, 0], bounds[:, 1],
num_iterations=num_iterations, n_init=2,
rng=rng, output_path=output_path)
results["run_id"] = run_id
results['X'] = results['X'].tolist()
results['y'] = results['y'].tolist()
test_error = []
current_inc = None
current_inc_val = None
key = "incumbents"
for inc in results["incumbents"]:
print(inc)
if current_inc == inc: