iicd/autodl-projects
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Create NATS

Browse Source
This commit is contained in:
D-X-Y
2020-07-30 13:07:11 +00:00
parent df45e68366
commit 6061d74631
21 changed files with 1336 additions and 126 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
exps/algos-v2/README.md
View File

@@ -1 +1,3 @@
# Benchmarking NAS Algorithms
# NATS-Bench: Benchmarking NAS algorithms for Architecture Topology and Size
# Benchmarking 13 NAS Algorithm

9
exps/algos-v2/bohb.py
View File

@@ -18,7 +18,7 @@ from config_utils import load_config
from datasets import get_datasets, SearchDataset
from procedures import prepare_seed, prepare_logger
from log_utils import AverageMeter, time_string, convert_secs2time
from nas_201_api import NASBench201API, NASBench301API
from nats_bench import create
from models import CellStructure, get_search_spaces
# BOHB: Robust and Efficient Hyperparameter Optimization at Scale, ICML 2018
import ConfigSpace
@@ -167,12 +167,7 @@ if __name__ == '__main__':
parser.add_argument('--rand_seed', type=int, default=-1, help='manual seed')
args = parser.parse_args()
if args.search_space == 'tss':
api = NASBench201API(verbose=False)
elif args.search_space == 'sss':
api = NASBench301API(verbose=False)
else:
raise ValueError('Invalid search space : {:}'.format(args.search_space))
api = create(None, args.search_space, verbose=False)
args.save_dir = os.path.join('{:}-{:}'.format(args.save_dir, args.search_space), args.dataset, 'BOHB')
print('save-dir : {:}'.format(args.save_dir))

9
exps/algos-v2/random_wo_share.py
View File

@@ -21,7 +21,7 @@ from procedures import prepare_seed, prepare_logger, save_checkpoint, copy_che
from utils import get_model_infos, obtain_accuracy
from log_utils import AverageMeter, time_string, convert_secs2time
from models import get_search_spaces
from nas_201_api import NASBench201API, NASBench301API
from nats_bench import create
from regularized_ea import random_topology_func, random_size_func
@@ -71,12 +71,7 @@ if __name__ == '__main__':
parser.add_argument('--rand_seed', type=int, default=-1, help='manual seed')
args = parser.parse_args()
if args.search_space == 'tss':
api = NASBench201API(verbose=False)
elif args.search_space == 'sss':
api = NASBench301API(verbose=False)
else:
raise ValueError('Invalid search space : {:}'.format(args.search_space))
api = create(None, args.search_space, verbose=False)
args.save_dir = os.path.join('{:}-{:}'.format(args.save_dir, args.search_space), args.dataset, 'RANDOM')
print('save-dir : {:}'.format(args.save_dir))

50
exps/algos-v2/regularized_ea.py
View File

@@ -23,8 +23,8 @@ from datasets import get_datasets, SearchDataset
from procedures import prepare_seed, prepare_logger, save_checkpoint, copy_checkpoint, get_optim_scheduler
from utils import get_model_infos, obtain_accuracy
from log_utils import AverageMeter, time_string, convert_secs2time
from nas_201_api import NASBench201API, NASBench301API
from models import CellStructure, get_search_spaces
from nats_bench import create
class Model(object):
@@ -38,47 +38,6 @@ class Model(object):
return '{:}'.format(self.arch)
# This function is to mimic the training and evaluatinig procedure for a single architecture `arch`.
# The time_cost is calculated as the total training time for a few (e.g., 12 epochs) plus the evaluation time for one epoch.
# For use_012_epoch_training = True, the architecture is trained for 12 epochs, with LR being decaded from 0.1 to 0.
# In this case, the LR schedular is converged.
# For use_012_epoch_training = False, the architecture is planed to be trained for 200 epochs, but we early stop its procedure.
#
def train_and_eval(arch, nas_bench, extra_info, dataname='cifar10-valid', use_012_epoch_training=True):
if use_012_epoch_training and nas_bench is not None:
arch_index = nas_bench.query_index_by_arch( arch )
assert arch_index >= 0, 'can not find this arch : {:}'.format(arch)
valid_acc, time_cost = info['valid-accuracy'], info['train-all-time'] + info['valid-per-time']
#_, valid_acc = info.get_metrics('cifar10-valid', 'x-valid' , 25, True) # use the validation accuracy after 25 training epochs
elif not use_012_epoch_training and nas_bench is not None:
# Please contact me if you want to use the following logic, because it has some potential issues.
# Please use `use_012_epoch_training=False` for cifar10 only.
# It did return values for cifar100 and ImageNet16-120, but it has some potential issues. (Please email me for more details)
arch_index, nepoch = nas_bench.query_index_by_arch( arch ), 25
assert arch_index >= 0, 'can not find this arch : {:}'.format(arch)
xoinfo = nas_bench.get_more_info(arch_index, 'cifar10-valid', iepoch=None, hp='12')
xocost = nas_bench.get_cost_info(arch_index, 'cifar10-valid', hp='200')
info = nas_bench.get_more_info(arch_index, dataname, nepoch, hp='200', is_random=True) # use the validation accuracy after 25 training epochs, which is used in our ICLR submission (not the camera ready).
cost = nas_bench.get_cost_info(arch_index, dataname, hp='200')
# The following codes are used to estimate the time cost.
# When we build NAS-Bench-201, architectures are trained on different machines and we can not use that time record.
# When we create checkpoints for converged_LR, we run all experiments on 1080Ti, and thus the time for each architecture can be fairly compared.
nums = {'ImageNet16-120-train': 151700, 'ImageNet16-120-valid': 3000,
'cifar10-valid-train' : 25000, 'cifar10-valid-valid' : 25000,
'cifar100-train' : 50000, 'cifar100-valid' : 5000}
estimated_train_cost = xoinfo['train-per-time'] / nums['cifar10-valid-train'] * nums['{:}-train'.format(dataname)] / xocost['latency'] * cost['latency'] * nepoch
estimated_valid_cost = xoinfo['valid-per-time'] / nums['cifar10-valid-valid'] * nums['{:}-valid'.format(dataname)] / xocost['latency'] * cost['latency']
try:
valid_acc, time_cost = info['valid-accuracy'], estimated_train_cost + estimated_valid_cost
except:
valid_acc, time_cost = info['valtest-accuracy'], estimated_train_cost + estimated_valid_cost
else:
# train a model from scratch.
raise ValueError('NOT IMPLEMENT YET')
return valid_acc, time_cost
def random_topology_func(op_names, max_nodes=4):
# Return a random architecture
def random_architecture():
@@ -239,12 +198,7 @@ if __name__ == '__main__':
parser.add_argument('--rand_seed', type=int, default=-1, help='manual seed')
args = parser.parse_args()
if args.search_space == 'tss':
api = NASBench201API(verbose=False)
elif args.search_space == 'sss':
api = NASBench301API(verbose=False)
else:
raise ValueError('Invalid search space : {:}'.format(args.search_space))
api = create(None, args.search_space, verbose=False)
args.save_dir = os.path.join('{:}-{:}'.format(args.save_dir, args.search_space), args.dataset, 'R-EA-SS{:}'.format(args.ea_sample_size))
print('save-dir : {:}'.format(args.save_dir))

9
exps/algos-v2/reinforce.py
View File

@@ -24,8 +24,8 @@ from datasets import get_datasets, SearchDataset
from procedures import prepare_seed, prepare_logger, save_checkpoint, copy_checkpoint, get_optim_scheduler
from utils import get_model_infos, obtain_accuracy
from log_utils import AverageMeter, time_string, convert_secs2time
from nas_201_api import NASBench201API, NASBench301API
from models import CellStructure, get_search_spaces
from nats_bench import create
class PolicyTopology(nn.Module):
@@ -192,12 +192,7 @@ if __name__ == '__main__':
parser.add_argument('--rand_seed', type=int, default=-1, help='manual seed')
args = parser.parse_args()
if args.search_space == 'tss':
api = NASBench201API(verbose=False)
elif args.search_space == 'sss':
api = NASBench301API(verbose=False)
else:
raise ValueError('Invalid search space : {:}'.format(args.search_space))
api = create(None, args.search_space, verbose=False)
args.save_dir = os.path.join('{:}-{:}'.format(args.save_dir, args.search_space), args.dataset, 'REINFORCE-{:}'.format(args.learning_rate))
print('save-dir : {:}'.format(args.save_dir))

4
exps/algos-v2/search-cell.py
View File

@@ -39,7 +39,7 @@ from procedures import prepare_seed, prepare_logger, save_checkpoint, copy_che
from utils import count_parameters_in_MB, obtain_accuracy
from log_utils import AverageMeter, time_string, convert_secs2time
from models import get_cell_based_tiny_net, get_search_spaces
from nas_201_api import NASBench201API as API
from nats_bench import create
# The following three functions are used for DARTS-V2
@@ -364,7 +364,7 @@ def main(xargs):
logger.log('The parameters of the search model = {:.2f} MB'.format(params))
logger.log('search-space : {:}'.format(search_space))
if bool(xargs.use_api):
api = API(verbose=False)
api = create(None, 'topology', verbose=False)
else:
api = None
logger.log('{:} create API = {:} done'.format(time_string(), api))

6
exps/algos-v2/search-size.py
View File

@@ -27,7 +27,7 @@ from procedures import prepare_seed, prepare_logger, save_checkpoint, copy_che
from utils import count_parameters_in_MB, obtain_accuracy
from log_utils import AverageMeter, time_string, convert_secs2time
from models import get_cell_based_tiny_net, get_search_spaces
from nas_201_api import NASBench301API as API
from nats_bench import create
# Ad-hoc for TuNAS
@@ -176,7 +176,7 @@ def main(xargs):
logger.log('The parameters of the search model = {:.2f} MB'.format(params))
logger.log('search-space : {:}'.format(search_space))
if bool(xargs.use_api):
api = API(verbose=False)
api = create(None, 'size', verbose=False)
else:
api = None
logger.log('{:} create API = {:} done'.format(time_string(), api))
@@ -291,7 +291,7 @@ if __name__ == '__main__':
parser.add_argument('--rand_seed', type=int, help='manual seed')
args = parser.parse_args()
if args.rand_seed is None or args.rand_seed < 0: args.rand_seed = random.randint(1, 100000)
dirname = '{:}-affine{:}_BN{:}'.format(args.algo, args.affine, args.track_running_stats)
dirname = '{:}-affine{:}_BN{:}-AWD{:}'.format(args.algo, args.affine, args.track_running_stats, args.arch_weight_decay)
if args.overwite_epochs is not None:
dirname = dirname + '-E{:}'.format(args.overwite_epochs)
args.save_dir = os.path.join('{:}-{:}'.format(args.save_dir, args.search_space), args.dataset, dirname)