def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.options is not None:
cfg.merge_from_dict(args.options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
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.aml:
data_store = os.environ['AZUREML_DATAREFERENCE_{}'.format(
args.aml_data_store)]
parse(cfg, data_store)
if cfg.resume_from is not None:
cfg.resume_from = os.path.join(data_store,
args.aml_work_dir_prefix,
cfg.resume_from)
cfg.work_dir = os.path.join(data_store, args.aml_work_dir_prefix,
cfg.work_dir)
print('work_dir: ', cfg.work_dir)
if 'data' in cfg.model.pretrained:
cfg.model.pretrained = os.path.join(data_store,
cfg.model.pretrained)
# if not args.aml:
# # 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)
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# update gpu num
if dist.is_initialized():
cfg.gpus = dist.get_world_size()
else:
cfg.gpus = args.gpus
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer[
'lr'] * cfg.gpus / 8 * cfg.data.samples_per_gpu / 32
# create work_dir
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
# 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
# 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:
logger.info(f'Set random seed to {args.seed}, '
f'deterministic: {args.deterministic}')
set_random_seed(args.seed, deterministic=args.deterministic)
cfg.seed = args.seed
meta['seed'] = args.seed
model = build_classifier(cfg.model)
datasets = [build_dataset(cfg.data.train)]
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 mmcls version, config file content and class names in
# checkpoints as meta data
cfg.checkpoint_config.meta = dict(mmcls_version=__version__,
config=cfg.pretty_text,
CLASSES=datasets[0].CLASSES)
# add an attribute for visualization convenience
train_model(model,
datasets,
cfg,
distributed=distributed,
validate=(not args.no_validate),
timestamp=timestamp,
meta=meta)
def main():
print("--------> 1")
args = parse_args()
print("--------> 2")
cfg = Config.fromfile(args.config)
print("--------> 3")
if args.options is not None:
cfg.merge_from_dict(args.options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
print("--------> 4")
# 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)
print("--------> 5")
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
_, world_size = get_dist_info()
cfg.gpu_ids = range(world_size)
print("--------> 6")
# create work_dir
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
# 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)
print("--------> 7")
# 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
# log some basic info
cfg_pretty_text = cfg.pretty_text
logger.info(f'Distributed training: {distributed}')
logger.info(f'Config:\n{cfg_pretty_text}')
# set random seeds
if args.seed is not None:
logger.info(f'Set random seed to {args.seed}, '
f'deterministic: {args.deterministic}')
set_random_seed(args.seed, deterministic=args.deterministic)
cfg.seed = args.seed
meta['seed'] = args.seed
model = build_classifier(cfg.model)
datasets = [build_dataset(cfg.data.train)]
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 mmcls version, config file content and class names in
# checkpoints as meta data
cfg.checkpoint_config.meta = dict(mmcls_version=__version__,
config=cfg_pretty_text,
CLASSES=datasets[0].CLASSES)
model.CLASSES = datasets[0].CLASSES
# add an attribute for visualization convenience
train_model(model,
datasets,
cfg,
distributed=distributed,
validate=(not args.no_validate),
timestamp=timestamp,
device='cpu' if args.device == 'cpu' else 'cuda',
meta=meta)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.options is not None:
cfg.merge_from_dict(args.options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
if args.net_params:
tag, input_channels, block1, block2, block3, block4, last_channel = args.net_params.split('-')
input_channels = [int(item) for item in input_channels.split('_')]
block1 = [int(item) for item in block1.split('_')]
block2 = [int(item) for item in block2.split('_')]
block3 = [int(item) for item in block3.split('_')]
block4 = [int(item) for item in block4.split('_')]
last_channel = int(last_channel)
inverted_residual_setting = []
for item in [block1, block2, block3, block4]:
for _ in range(item[0]):
inverted_residual_setting.append([item[1], item[2:-int(len(item)/2-1)], item[-int(len(item)/2-1):]])
cfg.model.backbone.input_channel = input_channels
cfg.model.backbone.inverted_residual_setting = inverted_residual_setting
cfg.model.backbone.last_channel = last_channel
cfg.model.head.in_channels = last_channel
# 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)
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer['lr'] * len(cfg.gpu_ids) / 8
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# create work_dir
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
# init the logger before other steps
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
if args.net_params:
log_file = osp.join(cfg.work_dir, f'{args.net_params}.log')
else:
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
# 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:
logger.info(f'Set random seed to {args.seed}, '
f'deterministic: {args.deterministic}')
set_random_seed(args.seed, deterministic=args.deterministic)
cfg.seed = args.seed
meta['seed'] = args.seed
model = build_classifier(cfg.model)
datasets = [build_dataset(cfg.data.train)]
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 mmcls version, config file content and class names in
# checkpoints as meta data
cfg.checkpoint_config.meta = dict(
mmcls_version=__version__,
config=cfg.pretty_text,
CLASSES=datasets[0].CLASSES)
# add an attribute for visualization convenience
train_model(
model,
datasets,
cfg,
distributed=distributed,
validate=(not args.no_validate),
timestamp=timestamp,
meta=meta)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# set multi-process settings
setup_multi_processes(cfg)
# 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.gpus is not None:
cfg.gpu_ids = range(1)
warnings.warn('`--gpus` is deprecated because we only support '
'single GPU mode in non-distributed training. '
'Use `gpus=1` now.')
if args.gpu_ids is not None:
cfg.gpu_ids = args.gpu_ids[0:1]
warnings.warn('`--gpu-ids` is deprecated, please use `--gpu-id`. '
'Because we only support single GPU mode in '
'non-distributed training. Use the first GPU '
'in `gpu_ids` now.')
if args.gpus is None and args.gpu_ids is None:
cfg.gpu_ids = [args.gpu_id]
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
_, world_size = get_dist_info()
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
# log some basic info
logger.info(f'Distributed training: {distributed}')
logger.info(f'Config:\n{cfg.pretty_text}')
# set random seeds
seed = init_random_seed(args.seed)
logger.info(f'Set random seed to {seed}, '
f'deterministic: {args.deterministic}')
set_random_seed(seed, deterministic=args.deterministic)
cfg.seed = seed
meta['seed'] = seed
model = build_classifier(cfg.model)
model.init_weights()
datasets = [build_dataset(cfg.data.train)]
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))
# save mmcls version, config file content and class names in
# runner as meta data
meta.update(
dict(mmcls_version=__version__,
config=cfg.pretty_text,
CLASSES=datasets[0].CLASSES))
# add an attribute for visualization convenience
train_model(model,
datasets,
cfg,
distributed=distributed,
validate=(not args.no_validate),
timestamp=timestamp,
device='cpu' if args.device == 'cpu' else 'cuda',
meta=meta)
def train_single_fold(args, cfg, fold, distributed, seed):
# create the work_dir for the fold
work_dir = osp.join(cfg.work_dir, f'fold{fold}')
cfg.work_dir = work_dir
# create work_dir
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
# wrap the dataset cfg
train_dataset = dict(
type='KFoldDataset',
fold=fold,
dataset=cfg.data.train,
num_splits=args.num_splits,
seed=seed,
)
val_dataset = dict(
type='KFoldDataset',
fold=fold,
# Use the same dataset with training.
dataset=copy.deepcopy(cfg.data.train),
num_splits=args.num_splits,
seed=seed,
test_mode=True,
)
val_dataset['dataset']['pipeline'] = cfg.data.val.pipeline
cfg.data.train = train_dataset
cfg.data.val = val_dataset
cfg.data.test = val_dataset
# dump config
stem, suffix = osp.basename(args.config).rsplit('.', 1)
cfg.dump(osp.join(cfg.work_dir, f'{stem}_fold{fold}.{suffix}'))
# 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
# log some basic info
logger.info(f'Distributed training: {distributed}')
logger.info(f'Config:\n{cfg.pretty_text}')
logger.info(
f'-------- Cross-validation: [{fold+1}/{args.num_splits}] -------- ')
# set random seeds
# Use different seed in different folds
logger.info(f'Set random seed to {seed + fold}, '
f'deterministic: {args.deterministic}')
set_random_seed(seed + fold, deterministic=args.deterministic)
cfg.seed = seed + fold
meta['seed'] = seed + fold
model = build_classifier(cfg.model)
model.init_weights()
datasets = [build_dataset(cfg.data.train)]
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))
meta.update(
dict(mmcls_version=__version__,
config=cfg.pretty_text,
CLASSES=datasets[0].CLASSES,
kfold=dict(fold=fold, num_splits=args.num_splits)))
# add an attribute for visualization convenience
train_model(model,
datasets,
cfg,
distributed=distributed,
validate=(not args.no_validate),
timestamp=timestamp,
device='cpu' if args.device == 'cpu' else 'cuda',
meta=meta)