208 lines
7.7 KiB
Python
208 lines
7.7 KiB
Python
import argparse
|
|
import copy
|
|
import os
|
|
import os.path as osp
|
|
import time
|
|
import warnings
|
|
|
|
import mmcv
|
|
import torch
|
|
from mmcv import Config, DictAction
|
|
from mmcv.runner import get_dist_info, init_dist, set_random_seed
|
|
from mmcv.utils import get_git_hash
|
|
from mmdet.utils import collect_env, get_root_logger
|
|
|
|
import mmfewshot # noqa: F401, F403
|
|
from mmfewshot import __version__
|
|
from mmfewshot.detection.apis import train_detector
|
|
from mmfewshot.detection.datasets import build_dataset
|
|
from mmfewshot.detection.models import build_detector
|
|
|
|
|
|
def parse_args():
|
|
parser = argparse.ArgumentParser(description='Train a FewShot model')
|
|
parser.add_argument('config', help='train config file path')
|
|
parser.add_argument(
|
|
'--work-dir', help='the directory to save logs and models')
|
|
parser.add_argument(
|
|
'--resume-from', help='the checkpoint file to resume from')
|
|
parser.add_argument(
|
|
'--no-validate',
|
|
action='store_true',
|
|
help='whether not to evaluate the checkpoint during training')
|
|
group_gpus = parser.add_mutually_exclusive_group()
|
|
group_gpus.add_argument(
|
|
'--gpus',
|
|
type=int,
|
|
help='number of gpus to use '
|
|
'(only applicable to non-distributed training)')
|
|
group_gpus.add_argument(
|
|
'--gpu-ids',
|
|
type=int,
|
|
nargs='+',
|
|
help='ids of gpus to use '
|
|
'(only applicable to non-distributed training)')
|
|
parser.add_argument('--seed', type=int, default=None, help='random seed')
|
|
parser.add_argument(
|
|
'--deterministic',
|
|
action='store_true',
|
|
help='whether to set deterministic options for CUDNN backend.')
|
|
parser.add_argument(
|
|
'--options',
|
|
nargs='+',
|
|
action=DictAction,
|
|
help='override some settings in the used config, the key-value pair '
|
|
'in xxx=yyy format will be merged into config file (deprecate), '
|
|
'change to --cfg-options instead.')
|
|
parser.add_argument(
|
|
'--cfg-options',
|
|
nargs='+',
|
|
action=DictAction,
|
|
help='override some settings in the used config, the key-value pair '
|
|
'in xxx=yyy format will be merged into config file. If the value '
|
|
'to be overwritten is a list, it should be like key="[a,b]" or '
|
|
'key=a,b It also allows nested list/tuple values, e.g. '
|
|
'key="[(a,b),(c,d)]" Note that the quotation marks are necessary '
|
|
'and that no white space is allowed.')
|
|
parser.add_argument(
|
|
'--launcher',
|
|
choices=['none', 'pytorch', 'slurm', 'mpi'],
|
|
default='none',
|
|
help='job launcher')
|
|
parser.add_argument('--local_rank', type=int, default=0)
|
|
args = parser.parse_args()
|
|
if 'LOCAL_RANK' not in os.environ:
|
|
os.environ['LOCAL_RANK'] = str(args.local_rank)
|
|
|
|
if args.options and args.cfg_options:
|
|
raise ValueError(
|
|
'--options and --cfg-options cannot be both '
|
|
'specified, --options is deprecated in favor of --cfg-options')
|
|
if args.options:
|
|
warnings.warn('--options is deprecated in favor of --cfg-options')
|
|
args.cfg_options = args.options
|
|
|
|
return args
|
|
|
|
|
|
def main():
|
|
args = parse_args()
|
|
|
|
cfg = Config.fromfile(args.config)
|
|
|
|
if args.cfg_options is not None:
|
|
cfg.merge_from_dict(args.cfg_options)
|
|
|
|
# import modules from string list.
|
|
if cfg.get('custom_imports', None):
|
|
from mmcv.utils import import_modules_from_strings
|
|
import_modules_from_strings(**cfg['custom_imports'])
|
|
# set cudnn_benchmark
|
|
if cfg.get('cudnn_benchmark', False):
|
|
torch.backends.cudnn.benchmark = True
|
|
|
|
# work_dir is determined in this priority: CLI > segment in file > filename
|
|
if args.work_dir is not None:
|
|
# update configs according to CLI args if args.work_dir is not None
|
|
cfg.work_dir = args.work_dir
|
|
elif cfg.get('work_dir', None) is None:
|
|
# use config filename as default work_dir if cfg.work_dir is None
|
|
cfg.work_dir = osp.join('./work_dirs',
|
|
osp.splitext(osp.basename(args.config))[0])
|
|
if args.resume_from is not None:
|
|
cfg.resume_from = args.resume_from
|
|
if args.gpu_ids is not None:
|
|
cfg.gpu_ids = args.gpu_ids
|
|
else:
|
|
cfg.gpu_ids = range(1) if args.gpus is None else range(args.gpus)
|
|
|
|
# init distributed env first, since logger depends on the dist info.
|
|
if args.launcher == 'none':
|
|
distributed = False
|
|
rank, world_size = get_dist_info()
|
|
else:
|
|
distributed = True
|
|
init_dist(args.launcher, **cfg.dist_params)
|
|
rank, world_size = get_dist_info()
|
|
# re-set gpu_ids with distributed training mode
|
|
cfg.gpu_ids = range(world_size)
|
|
# create work_dir
|
|
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
|
|
# dump config
|
|
cfg.dump(osp.join(cfg.work_dir, osp.basename(args.config)))
|
|
# init the logger before other steps
|
|
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
|
|
log_file = osp.join(cfg.work_dir, f'{timestamp}.log')
|
|
logger = get_root_logger(log_file=log_file, log_level=cfg.log_level)
|
|
|
|
# init the meta dict to record some important information such as
|
|
# environment info and seed, which will be logged
|
|
meta = dict()
|
|
# log env info
|
|
env_info_dict = collect_env()
|
|
env_info = '\n'.join([(f'{k}: {v}') for k, v in env_info_dict.items()])
|
|
dash_line = '-' * 60 + '\n'
|
|
logger.info('Environment info:\n' + dash_line + env_info + '\n' +
|
|
dash_line)
|
|
meta['env_info'] = env_info
|
|
meta['config'] = cfg.pretty_text
|
|
# log some basic info
|
|
logger.info(f'Distributed training: {distributed}')
|
|
logger.info(f'Config:\n{cfg.pretty_text}')
|
|
|
|
# set random seeds
|
|
if args.seed is not None:
|
|
seed = args.seed
|
|
elif cfg.seed is not None:
|
|
seed = cfg.seed
|
|
elif distributed:
|
|
seed = 0
|
|
Warning(f'When using DistributedDataParallel, each rank will '
|
|
f'initialize different random seed. It will cause different'
|
|
f'random action for each rank. In few shot setting, novel '
|
|
f'shots may be generated by random sampling. If all rank do '
|
|
f'not use same seed, each rank will sample different data.'
|
|
f'It will cause UNFAIR data usage. Therefore, seed is set '
|
|
f'to {seed} for default.')
|
|
else:
|
|
seed = None
|
|
|
|
if seed is not None:
|
|
logger.info(f'Set random seed to {seed}, '
|
|
f'deterministic: {args.deterministic}')
|
|
set_random_seed(seed, deterministic=args.deterministic)
|
|
meta['seed'] = seed
|
|
meta['exp_name'] = osp.basename(args.config)
|
|
|
|
# build_detector will do three things, including building model,
|
|
# initializing weights and freezing parameters (optional).
|
|
model = build_detector(cfg.model, logger=logger)
|
|
# build_dataset will do two things, including building dataset
|
|
# and saving dataset into json file (optional).
|
|
datasets = [build_dataset(cfg.data.train, rank=rank, timestamp=timestamp)]
|
|
|
|
if len(cfg.workflow) == 2:
|
|
val_dataset = copy.deepcopy(cfg.data.val)
|
|
val_dataset.pipeline = cfg.data.train.pipeline
|
|
datasets.append(build_dataset(val_dataset))
|
|
if cfg.checkpoint_config is not None:
|
|
# save mmfewshot version, config file content and class names in
|
|
# checkpoints as meta data
|
|
cfg.checkpoint_config.meta = dict(
|
|
mmfewshot_version=__version__ + get_git_hash()[:7],
|
|
CLASSES=datasets[0].CLASSES)
|
|
# add an attribute for visualization convenience
|
|
model.CLASSES = datasets[0].CLASSES
|
|
train_detector(
|
|
model,
|
|
datasets,
|
|
cfg,
|
|
distributed=distributed,
|
|
validate=(not args.no_validate),
|
|
timestamp=timestamp,
|
|
meta=meta)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|