iicd/xautodl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add int search space

Browse Source
This commit is contained in:
D-X-Y
2021-03-18 16:02:55 +08:00
parent ece6ac5f41
commit 63c8bb9bc8
67 changed files with 5150 additions and 1474 deletions
Download Patch File Download Diff File Expand all files Collapse all files

308
exps/NATS-Bench/main-tss.py
View File

@@ -57,23 +57,35 @@ def evaluate_all_datasets(
train_data, valid_data, xshape, class_num = get_datasets(dataset, xpath, -1)
# load the configuration
if dataset == "cifar10" or dataset == "cifar100":
split_info = load_config("configs/nas-benchmark/cifar-split.txt", None, None)
split_info = load_config(
"configs/nas-benchmark/cifar-split.txt", None, None
)
elif dataset.startswith("ImageNet16"):
split_info = load_config("configs/nas-benchmark/{:}-split.txt".format(dataset), None, None)
split_info = load_config(
"configs/nas-benchmark/{:}-split.txt".format(dataset), None, None
)
else:
raise ValueError("invalid dataset : {:}".format(dataset))
config = load_config(config_path, dict(class_num=class_num, xshape=xshape), logger)
config = load_config(
config_path, dict(class_num=class_num, xshape=xshape), logger
)
# check whether use splited validation set
if bool(split):
assert dataset == "cifar10"
ValLoaders = {
"ori-test": torch.utils.data.DataLoader(
valid_data, batch_size=config.batch_size, shuffle=False, num_workers=workers, pin_memory=True
valid_data,
batch_size=config.batch_size,
shuffle=False,
num_workers=workers,
pin_memory=True,
)
}
assert len(train_data) == len(split_info.train) + len(
split_info.valid
), "invalid length : {:} vs {:} + {:}".format(len(train_data), len(split_info.train), len(split_info.valid))
), "invalid length : {:} vs {:} + {:}".format(
len(train_data), len(split_info.train), len(split_info.valid)
)
train_data_v2 = deepcopy(train_data)
train_data_v2.transform = valid_data.transform
valid_data = train_data_v2
@@ -96,47 +108,67 @@ def evaluate_all_datasets(
else:
# data loader
train_loader = torch.utils.data.DataLoader(
train_data, batch_size=config.batch_size, shuffle=True, num_workers=workers, pin_memory=True
train_data,
batch_size=config.batch_size,
shuffle=True,
num_workers=workers,
pin_memory=True,
)
valid_loader = torch.utils.data.DataLoader(
valid_data, batch_size=config.batch_size, shuffle=False, num_workers=workers, pin_memory=True
valid_data,
batch_size=config.batch_size,
shuffle=False,
num_workers=workers,
pin_memory=True,
)
if dataset == "cifar10":
ValLoaders = {"ori-test": valid_loader}
elif dataset == "cifar100":
cifar100_splits = load_config("configs/nas-benchmark/cifar100-test-split.txt", None, None)
cifar100_splits = load_config(
"configs/nas-benchmark/cifar100-test-split.txt", None, None
)
ValLoaders = {
"ori-test": valid_loader,
"x-valid": torch.utils.data.DataLoader(
valid_data,
batch_size=config.batch_size,
sampler=torch.utils.data.sampler.SubsetRandomSampler(cifar100_splits.xvalid),
sampler=torch.utils.data.sampler.SubsetRandomSampler(
cifar100_splits.xvalid
),
num_workers=workers,
pin_memory=True,
),
"x-test": torch.utils.data.DataLoader(
valid_data,
batch_size=config.batch_size,
sampler=torch.utils.data.sampler.SubsetRandomSampler(cifar100_splits.xtest),
sampler=torch.utils.data.sampler.SubsetRandomSampler(
cifar100_splits.xtest
),
num_workers=workers,
pin_memory=True,
),
}
elif dataset == "ImageNet16-120":
imagenet16_splits = load_config("configs/nas-benchmark/imagenet-16-120-test-split.txt", None, None)
imagenet16_splits = load_config(
"configs/nas-benchmark/imagenet-16-120-test-split.txt", None, None
)
ValLoaders = {
"ori-test": valid_loader,
"x-valid": torch.utils.data.DataLoader(
valid_data,
batch_size=config.batch_size,
sampler=torch.utils.data.sampler.SubsetRandomSampler(imagenet16_splits.xvalid),
sampler=torch.utils.data.sampler.SubsetRandomSampler(
imagenet16_splits.xvalid
),
num_workers=workers,
pin_memory=True,
),
"x-test": torch.utils.data.DataLoader(
valid_data,
batch_size=config.batch_size,
sampler=torch.utils.data.sampler.SubsetRandomSampler(imagenet16_splits.xtest),
sampler=torch.utils.data.sampler.SubsetRandomSampler(
imagenet16_splits.xtest
),
num_workers=workers,
pin_memory=True,
),
@@ -149,12 +181,21 @@ def evaluate_all_datasets(
dataset_key = dataset_key + "-valid"
logger.log(
"Evaluate ||||||| {:10s} ||||||| Train-Num={:}, Valid-Num={:}, Train-Loader-Num={:}, Valid-Loader-Num={:}, batch size={:}".format(
dataset_key, len(train_data), len(valid_data), len(train_loader), len(valid_loader), config.batch_size
dataset_key,
len(train_data),
len(valid_data),
len(train_loader),
len(valid_loader),
config.batch_size,
)
)
logger.log("Evaluate ||||||| {:10s} ||||||| Config={:}".format(dataset_key, config))
logger.log(
"Evaluate ||||||| {:10s} ||||||| Config={:}".format(dataset_key, config)
)
for key, value in ValLoaders.items():
logger.log("Evaluate ---->>>> {:10s} with {:} batchs".format(key, len(value)))
logger.log(
"Evaluate ---->>>> {:10s} with {:} batchs".format(key, len(value))
)
arch_config = dict2config(
dict(
name="infer.tiny",
@@ -165,7 +206,9 @@ def evaluate_all_datasets(
),
None,
)
results = bench_evaluate_for_seed(arch_config, config, train_loader, ValLoaders, seed, logger)
results = bench_evaluate_for_seed(
arch_config, config, train_loader, ValLoaders, seed, logger
)
all_infos[dataset_key] = results
all_dataset_keys.append(dataset_key)
all_infos["all_dataset_keys"] = all_dataset_keys
@@ -194,8 +237,12 @@ def main(
logger.log("xargs : cover_mode = {:}".format(cover_mode))
logger.log("-" * 100)
logger.log(
"Start evaluating range =: {:06d} - {:06d}".format(min(to_evaluate_indexes), max(to_evaluate_indexes))
+ "({:} in total) / {:06d} with cover-mode={:}".format(len(to_evaluate_indexes), len(nets), cover_mode)
"Start evaluating range =: {:06d} - {:06d}".format(
min(to_evaluate_indexes), max(to_evaluate_indexes)
)
+ "({:} in total) / {:06d} with cover-mode={:}".format(
len(to_evaluate_indexes), len(nets), cover_mode
)
)
for i, (dataset, xpath, split) in enumerate(zip(datasets, xpaths, splits)):
logger.log(
@@ -210,7 +257,13 @@ def main(
arch = nets[index]
logger.log(
"\n{:} evaluate {:06d}/{:06d} ({:06d}/{:06d})-th arch [seeds={:}] {:}".format(
time_string(), i, len(to_evaluate_indexes), index, len(nets), seeds, "-" * 15
time_string(),
i,
len(to_evaluate_indexes),
index,
len(nets),
seeds,
"-" * 15,
)
)
logger.log("{:} {:} {:}".format("-" * 15, arch, "-" * 15))
@@ -221,10 +274,18 @@ def main(
to_save_name = save_dir / "arch-{:06d}-seed-{:04d}.pth".format(index, seed)
if to_save_name.exists():
if cover_mode:
logger.log("Find existing file : {:}, remove it before evaluation".format(to_save_name))
logger.log(
"Find existing file : {:}, remove it before evaluation".format(
to_save_name
)
)
os.remove(str(to_save_name))
else:
logger.log("Find existing file : {:}, skip this evaluation".format(to_save_name))
logger.log(
"Find existing file : {:}, skip this evaluation".format(
to_save_name
)
)
has_continue = True
continue
results = evaluate_all_datasets(
@@ -241,7 +302,13 @@ def main(
torch.save(results, to_save_name)
logger.log(
"\n{:} evaluate {:06d}/{:06d} ({:06d}/{:06d})-th arch [seeds={:}] ===>>> {:}".format(
time_string(), i, len(to_evaluate_indexes), index, len(nets), seeds, to_save_name
time_string(),
i,
len(to_evaluate_indexes),
index,
len(nets),
seeds,
to_save_name,
)
)
# measure elapsed time
@@ -251,7 +318,9 @@ def main(
need_time = "Time Left: {:}".format(
convert_secs2time(epoch_time.avg * (len(to_evaluate_indexes) - i - 1), True)
)
logger.log("This arch costs : {:}".format(convert_secs2time(epoch_time.val, True)))
logger.log(
"This arch costs : {:}".format(convert_secs2time(epoch_time.val, True))
)
logger.log("{:}".format("*" * 100))
logger.log(
"{:} {:74s} {:}".format(
@@ -267,7 +336,9 @@ def main(
logger.close()
def train_single_model(save_dir, workers, datasets, xpaths, splits, use_less, seeds, model_str, arch_config):
def train_single_model(
save_dir, workers, datasets, xpaths, splits, use_less, seeds, model_str, arch_config
):
assert torch.cuda.is_available(), "CUDA is not available."
torch.backends.cudnn.enabled = True
torch.backends.cudnn.deterministic = True
@@ -278,19 +349,32 @@ def train_single_model(save_dir, workers, datasets, xpaths, splits, use_less, se
Path(save_dir)
/ "specifics"
/ "{:}-{:}-{:}-{:}".format(
"LESS" if use_less else "FULL", model_str, arch_config["channel"], arch_config["num_cells"]
"LESS" if use_less else "FULL",
model_str,
arch_config["channel"],
arch_config["num_cells"],
)
)
logger = Logger(str(save_dir), 0, False)
if model_str in CellArchitectures:
arch = CellArchitectures[model_str]
logger.log("The model string is found in pre-defined architecture dict : {:}".format(model_str))
logger.log(
"The model string is found in pre-defined architecture dict : {:}".format(
model_str
)
)
else:
try:
arch = CellStructure.str2structure(model_str)
except:
raise ValueError("Invalid model string : {:}. It can not be found or parsed.".format(model_str))
assert arch.check_valid_op(get_search_spaces("cell", "full")), "{:} has the invalid op.".format(arch)
raise ValueError(
"Invalid model string : {:}. It can not be found or parsed.".format(
model_str
)
)
assert arch.check_valid_op(
get_search_spaces("cell", "full")
), "{:} has the invalid op.".format(arch)
logger.log("Start train-evaluate {:}".format(arch.tostr()))
logger.log("arch_config : {:}".format(arch_config))
@@ -303,27 +387,55 @@ def train_single_model(save_dir, workers, datasets, xpaths, splits, use_less, se
)
to_save_name = save_dir / "seed-{:04d}.pth".format(seed)
if to_save_name.exists():
logger.log("Find the existing file {:}, directly load!".format(to_save_name))
logger.log(
"Find the existing file {:}, directly load!".format(to_save_name)
)
checkpoint = torch.load(to_save_name)
else:
logger.log("Does not find the existing file {:}, train and evaluate!".format(to_save_name))
logger.log(
"Does not find the existing file {:}, train and evaluate!".format(
to_save_name
)
)
checkpoint = evaluate_all_datasets(
arch, datasets, xpaths, splits, use_less, seed, arch_config, workers, logger
arch,
datasets,
xpaths,
splits,
use_less,
seed,
arch_config,
workers,
logger,
)
torch.save(checkpoint, to_save_name)
# log information
logger.log("{:}".format(checkpoint["info"]))
all_dataset_keys = checkpoint["all_dataset_keys"]
for dataset_key in all_dataset_keys:
logger.log("\n{:} dataset : {:} {:}".format("-" * 15, dataset_key, "-" * 15))
logger.log(
"\n{:} dataset : {:} {:}".format("-" * 15, dataset_key, "-" * 15)
)
dataset_info = checkpoint[dataset_key]
# logger.log('Network ==>\n{:}'.format( dataset_info['net_string'] ))
logger.log("Flops = {:} MB, Params = {:} MB".format(dataset_info["flop"], dataset_info["param"]))
logger.log(
"Flops = {:} MB, Params = {:} MB".format(
dataset_info["flop"], dataset_info["param"]
)
)
logger.log("config : {:}".format(dataset_info["config"]))
logger.log("Training State (finish) = {:}".format(dataset_info["finish-train"]))
logger.log(
"Training State (finish) = {:}".format(dataset_info["finish-train"])
)
last_epoch = dataset_info["total_epoch"] - 1
train_acc1es, train_acc5es = dataset_info["train_acc1es"], dataset_info["train_acc5es"]
valid_acc1es, valid_acc5es = dataset_info["valid_acc1es"], dataset_info["valid_acc5es"]
train_acc1es, train_acc5es = (
dataset_info["train_acc1es"],
dataset_info["train_acc5es"],
)
valid_acc1es, valid_acc5es = (
dataset_info["valid_acc1es"],
dataset_info["valid_acc5es"],
)
logger.log(
"Last Info : Train = Acc@1 {:.2f}% Acc@5 {:.2f}% Error@1 {:.2f}%, Test = Acc@1 {:.2f}% Acc@5 {:.2f}% Error@1 {:.2f}%".format(
train_acc1es[last_epoch],
@@ -337,7 +449,9 @@ def train_single_model(save_dir, workers, datasets, xpaths, splits, use_less, se
# measure elapsed time
seed_time.update(time.time() - start_time)
start_time = time.time()
need_time = "Time Left: {:}".format(convert_secs2time(seed_time.avg * (len(seeds) - _is - 1), True))
need_time = "Time Left: {:}".format(
convert_secs2time(seed_time.avg * (len(seeds) - _is - 1), True)
)
logger.log(
"\n<<<***>>> The {:02d}/{:02d}-th seed is {:} <finish> other procedures need {:}".format(
_is, len(seeds), seed, need_time
@@ -349,7 +463,11 @@ def train_single_model(save_dir, workers, datasets, xpaths, splits, use_less, se
def generate_meta_info(save_dir, max_node, divide=40):
aa_nas_bench_ss = get_search_spaces("cell", "nas-bench-201")
archs = CellStructure.gen_all(aa_nas_bench_ss, max_node, False)
print("There are {:} archs vs {:}.".format(len(archs), len(aa_nas_bench_ss) ** ((max_node - 1) * max_node / 2)))
print(
"There are {:} archs vs {:}.".format(
len(archs), len(aa_nas_bench_ss) ** ((max_node - 1) * max_node / 2)
)
)
random.seed(88) # please do not change this line for reproducibility
random.shuffle(archs)
@@ -361,10 +479,12 @@ def generate_meta_info(save_dir, max_node, divide=40):
== "|avg_pool_3x3~0|+|nor_conv_1x1~0|skip_connect~1|+|nor_conv_1x1~0|skip_connect~1|skip_connect~2|"
), "please check the 0-th architecture : {:}".format(archs[0])
assert (
archs[9].tostr() == "|avg_pool_3x3~0|+|none~0|none~1|+|skip_connect~0|none~1|nor_conv_3x3~2|"
archs[9].tostr()
== "|avg_pool_3x3~0|+|none~0|none~1|+|skip_connect~0|none~1|nor_conv_3x3~2|"
), "please check the 9-th architecture : {:}".format(archs[9])
assert (
archs[123].tostr() == "|avg_pool_3x3~0|+|avg_pool_3x3~0|nor_conv_1x1~1|+|none~0|avg_pool_3x3~1|nor_conv_3x3~2|"
archs[123].tostr()
== "|avg_pool_3x3~0|+|avg_pool_3x3~0|nor_conv_1x1~1|+|none~0|avg_pool_3x3~1|nor_conv_3x3~2|"
), "please check the 123-th architecture : {:}".format(archs[123])
total_arch = len(archs)
@@ -383,11 +503,21 @@ def generate_meta_info(save_dir, max_node, divide=40):
and valid_split[10] == 18
and valid_split[111] == 242
), "{:} {:} {:} - {:} {:} {:}".format(
train_split[0], train_split[10], train_split[111], valid_split[0], valid_split[10], valid_split[111]
train_split[0],
train_split[10],
train_split[111],
valid_split[0],
valid_split[10],
valid_split[111],
)
splits = {num: {"train": train_split, "valid": valid_split}}
info = {"archs": [x.tostr() for x in archs], "total": total_arch, "max_node": max_node, "splits": splits}
info = {
"archs": [x.tostr() for x in archs],
"total": total_arch,
"max_node": max_node,
"splits": splits,
}
save_dir = Path(save_dir)
save_dir.mkdir(parents=True, exist_ok=True)
@@ -400,7 +530,11 @@ def generate_meta_info(save_dir, max_node, divide=40):
def traverse_net(max_node):
aa_nas_bench_ss = get_search_spaces("cell", "nats-bench")
archs = CellStructure.gen_all(aa_nas_bench_ss, max_node, False)
print("There are {:} archs vs {:}.".format(len(archs), len(aa_nas_bench_ss) ** ((max_node - 1) * max_node / 2)))
print(
"There are {:} archs vs {:}.".format(
len(archs), len(aa_nas_bench_ss) ** ((max_node - 1) * max_node / 2)
)
)
random.seed(88) # please do not change this line for reproducibility
random.shuffle(archs)
@@ -409,10 +543,12 @@ def traverse_net(max_node):
== "|avg_pool_3x3~0|+|nor_conv_1x1~0|skip_connect~1|+|nor_conv_1x1~0|skip_connect~1|skip_connect~2|"
), "please check the 0-th architecture : {:}".format(archs[0])
assert (
archs[9].tostr() == "|avg_pool_3x3~0|+|none~0|none~1|+|skip_connect~0|none~1|nor_conv_3x3~2|"
archs[9].tostr()
== "|avg_pool_3x3~0|+|none~0|none~1|+|skip_connect~0|none~1|nor_conv_3x3~2|"
), "please check the 9-th architecture : {:}".format(archs[9])
assert (
archs[123].tostr() == "|avg_pool_3x3~0|+|avg_pool_3x3~0|nor_conv_1x1~1|+|none~0|avg_pool_3x3~1|nor_conv_3x3~2|"
archs[123].tostr()
== "|avg_pool_3x3~0|+|avg_pool_3x3~0|nor_conv_1x1~1|+|none~0|avg_pool_3x3~1|nor_conv_3x3~2|"
), "please check the 123-th architecture : {:}".format(archs[123])
return [x.tostr() for x in archs]
@@ -439,32 +575,62 @@ def filter_indexes(xlist, mode, save_dir, seeds):
if __name__ == "__main__":
# mode_choices = ['meta', 'new', 'cover'] + ['specific-{:}'.format(_) for _ in CellArchitectures.keys()]
parser = argparse.ArgumentParser(
description="NATS-Bench (topology search space)", formatter_class=argparse.ArgumentDefaultsHelpFormatter
description="NATS-Bench (topology search space)",
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
parser.add_argument("--mode", type=str, required=True, help="The script mode.")
parser.add_argument(
"--save_dir", type=str, default="output/NATS-Bench-topology", help="Folder to save checkpoints and log."
"--save_dir",
type=str,
default="output/NATS-Bench-topology",
help="Folder to save checkpoints and log.",
)
parser.add_argument("--max_node", type=int, default=4, help="The maximum node in a cell (please do not change it).")
# use for train the model
parser.add_argument("--workers", type=int, default=8, help="number of data loading workers (default: 2)")
parser.add_argument("--srange", type=str, required=True, help="The range of models to be evaluated")
parser.add_argument("--datasets", type=str, nargs="+", help="The applied datasets.")
parser.add_argument("--xpaths", type=str, nargs="+", help="The root path for this dataset.")
parser.add_argument("--splits", type=int, nargs="+", help="The root path for this dataset.")
parser.add_argument(
"--hyper", type=str, default="12", choices=["01", "12", "200"], help="The tag for hyper-parameters."
"--max_node",
type=int,
default=4,
help="The maximum node in a cell (please do not change it).",
)
# use for train the model
parser.add_argument(
"--workers",
type=int,
default=8,
help="number of data loading workers (default: 2)",
)
parser.add_argument(
"--srange", type=str, required=True, help="The range of models to be evaluated"
)
parser.add_argument("--datasets", type=str, nargs="+", help="The applied datasets.")
parser.add_argument(
"--xpaths", type=str, nargs="+", help="The root path for this dataset."
)
parser.add_argument(
"--splits", type=int, nargs="+", help="The root path for this dataset."
)
parser.add_argument(
"--hyper",
type=str,
default="12",
choices=["01", "12", "200"],
help="The tag for hyper-parameters.",
)
parser.add_argument("--seeds", type=int, nargs="+", help="The range of models to be evaluated")
parser.add_argument("--channel", type=int, default=16, help="The number of channels.")
parser.add_argument("--num_cells", type=int, default=5, help="The number of cells in one stage.")
parser.add_argument(
"--seeds", type=int, nargs="+", help="The range of models to be evaluated"
)
parser.add_argument(
"--channel", type=int, default=16, help="The number of channels."
)
parser.add_argument(
"--num_cells", type=int, default=5, help="The number of cells in one stage."
)
parser.add_argument("--check_N", type=int, default=15625, help="For safety.")
args = parser.parse_args()
assert args.mode in ["meta", "new", "cover"] or args.mode.startswith("specific-"), "invalid mode : {:}".format(
args.mode
)
assert args.mode in ["meta", "new", "cover"] or args.mode.startswith(
"specific-"
), "invalid mode : {:}".format(args.mode)
if args.mode == "meta":
generate_meta_info(args.save_dir, args.max_node)
@@ -485,7 +651,9 @@ if __name__ == "__main__":
else:
nets = traverse_net(args.max_node)
if len(nets) != args.check_N:
raise ValueError("Pre-num-check failed : {:} vs {:}".format(len(nets), args.check_N))
raise ValueError(
"Pre-num-check failed : {:} vs {:}".format(len(nets), args.check_N)
)
opt_config = "./configs/nas-benchmark/hyper-opts/{:}E.config".format(args.hyper)
if not os.path.isfile(opt_config):
raise ValueError("{:} is not a file.".format(opt_config))
@@ -496,12 +664,16 @@ if __name__ == "__main__":
raise ValueError("invalid length of seeds args: {:}".format(args.seeds))
if not (len(args.datasets) == len(args.xpaths) == len(args.splits)):
raise ValueError(
"invalid infos : {:} vs {:} vs {:}".format(len(args.datasets), len(args.xpaths), len(args.splits))
"invalid infos : {:} vs {:} vs {:}".format(
len(args.datasets), len(args.xpaths), len(args.splits)
)
)
if args.workers <= 0:
raise ValueError("invalid number of workers : {:}".format(args.workers))
target_indexes = filter_indexes(to_evaluate_indexes, args.mode, save_dir, args.seeds)
target_indexes = filter_indexes(
to_evaluate_indexes, args.mode, save_dir, args.seeds
)
assert torch.cuda.is_available(), "CUDA is not available."
torch.backends.cudnn.enabled = True
@@ -519,5 +691,9 @@ if __name__ == "__main__":
opt_config,
target_indexes,
args.mode == "cover",
{"name": "infer.tiny", "channel": args.channel, "num_cells": args.num_cells},
{
"name": "infer.tiny",
"channel": args.channel,
"num_cells": args.num_cells,
},
)