def main(args):
file_name = 'log_%s_%d' % ('gpus', args.gpu)
logger = setup_logger(file_name,
args.save_dir,
args.gpu,
log_level='DEBUG',
filename='%s.txt' % file_name)
logger.info(args)
if args.search_space == 'nasbench_101':
with open(nas_bench_101_all_data, 'rb') as fpkl:
all_data = pickle.load(fpkl)
else:
raise NotImplementedError(
f'The search space {args.search_space} does not support now!')
for k in range(args.trails):
seed = random_id_int(4)
set_random_seed(seed)
s_results_dict = defaultdict(list)
k_results_dict = defaultdict(list)
logger.info(
f'====================== Trails {k} Begin Setting Seed to {seed} ==========================='
)
for budget in args.search_budget:
train_data, test_data = data.dataset_split_idx(all_data, budget)
print(
f'budget: {budget}, train data size: {len(train_data)}, test data size: {len(test_data)}'
)
for epochs in args.train_iterations:
if args.compare_supervised == 'T':
logger.info(
f'==== predictor type: SUPERVISED, load pretrain model False, '
f'search budget is {budget}. Training epoch is {epochs} ===='
)
spearman_corr, kendalltau_corr, duration = predictor_retrain_compare(
args,
'SS_RL',
train_data,
test_data,
flag=False,
train_epochs=epochs,
logger=logger)
if math.isnan(spearman_corr):
spearman_corr = 0
if math.isnan(kendalltau_corr):
kendalltau_corr = 0
s_results_dict[f'supervised#{budget}#{epochs}'].append(
spearman_corr)
k_results_dict[f'supervised#{budget}#{epochs}'].append(
kendalltau_corr)
for predictor_type, dir in zip(args.predictor_list,
args.load_dir):
logger.info(
f'==== predictor type: {predictor_type}, load pretrain model True. '
f'Search budget is {budget}. Training epoch is {epochs}. '
f'The model save dir is {dir.split("/")[-1][:-3]} ===='
)
spearman_corr, kendalltau_corr, duration = predictor_retrain_compare(
args,
predictor_type,
train_data,
test_data,
flag=True,
load_dir=dir,
train_epochs=epochs,
logger=logger)
if math.isnan(spearman_corr):
spearman_corr = 0
if math.isnan(kendalltau_corr):
kendalltau_corr = 0
s_results_dict[predictor_type + '#' + str(budget) + '#' +
str(epochs)].append(spearman_corr)
k_results_dict[predictor_type + '#' + str(budget) + '#' +
str(epochs)].append(kendalltau_corr)
file_id = random_id(6)
save_path = os.path.join(
args.save_dir,
f'{file_id}_{args.predictor_list[0]}_{args.search_space.split("_")[-1]}_{args.gpu}_{k}.pkl'
)
with open(save_path, 'wb') as fp:
pickle.dump(s_results_dict, fp)
pickle.dump(k_results_dict, fp)
default='nasbench_case2',
choices=['nasbench_case1', 'nasbench_case2', 'nasbench_201'],
help='nasbench')
parser.add_argument('--algo_params',
type=str,
default='nasbench101_case2',
choices=[
'nasbench101_case1', 'nasbench101_case2',
'nasbench_201', 'scalar_prior',
'evaluation_compare', 'box_compare_case1',
'box_compare_case2', 'experiment'
],
help='which algorithms to compare')
parser.add_argument('--output_filename',
type=str,
default=random_id(64),
help='name of output files')
parser.add_argument('--gpus',
type=int,
default=1,
help='The num of gpus used for search.')
parser.add_argument('--loss_type',
type=str,
default="mae",
help='Loss used to train architecture.')
parser.add_argument('--with_details',
type=str,
default="F",
help='Record detailed training procedure.')
parser.add_argument(
'--save_dir',
from nas_lib.utils.comm import random_id, setup_logger
from nas_lib.utils.utils_darts import compute_best_test_losses, compute_darts_test_losses
from nas_lib.algos_darts.build_open_algos import build_open_algos
from nas_lib.data_darts.build_ss import build_open_search_space_dataset
from nas_lib.configs import algo_params_open_domain
import pickle
if __name__ == "__main__":
loss_type = 'mae'
parser = argparse.ArgumentParser(description='Args for darts search space.')
parser.add_argument('--search_space', type=str, default='darts', help='darts')
parser.add_argument('--gpus', type=int, default=1, help='Number of gpus')
parser.add_argument('--algorithm', type=str, default='gin_predictor',
choices=['gin_uncertainty_predictor', 'gin_predictor'], help='which parameters to use')
parser.add_argument('--output_filename', type=str, default=random_id(64), help='name of output files')
parser.add_argument('--node_nums', type=int, default=4, help='cell num')
parser.add_argument('--log_level', type=str, default='DEBUG', help='information logging level')
parser.add_argument('--seed', type=int, default=22, help='seed')
parser.add_argument('--budget', type=int, default=100, help='searching budget.')
parser.add_argument('--save_dir', type=str,
default='/home/albert_wei/Disk_A/train_output_npenas/npenas_open_domain_darts_2/',
help='name of save directory')
args = parser.parse_args()
# make save directory
save_dir = args.save_dir
if not os.path.exists(save_dir):
os.mkdir(save_dir)
if not os.path.exists(os.path.join(save_dir, 'model_pkl')):
os.mkdir(os.path.join(save_dir, 'model_pkl'))