def train_model(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
device=None,
meta=None):
"""Train a model.
This method will build dataloaders, wrap the model and build a runner
according to the provided config.
Args:
model (:obj:`torch.nn.Module`): The model to be run.
dataset (:obj:`mmcls.datasets.BaseDataset` | List[BaseDataset]):
The dataset used to train the model. It can be a single dataset,
or a list of dataset with the same length as workflow.
cfg (:obj:`mmcv.utils.Config`): The configs of the experiment.
distributed (bool): Whether to train the model in a distributed
environment. Defaults to False.
validate (bool): Whether to do validation with
:obj:`mmcv.runner.EvalHook`. Defaults to False.
timestamp (str, optional): The timestamp string to auto generate the
name of log files. Defaults to None.
device (str, optional): TODO
meta (dict, optional): A dict records some import information such as
environment info and seed, which will be logged in logger hook.
Defaults to None.
"""
logger = get_root_logger()
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
# The default loader config
loader_cfg = dict(
# cfg.gpus will be ignored if distributed
num_gpus=cfg.ipu_replicas if device == 'ipu' else len(cfg.gpu_ids),
dist=distributed,
round_up=True,
seed=cfg.get('seed'),
sampler_cfg=cfg.get('sampler', None),
)
# The overall dataloader settings
loader_cfg.update({
k: v
for k, v in cfg.data.items() if k not in [
'train', 'val', 'test', 'train_dataloader', 'val_dataloader',
'test_dataloader'
]
})
# The specific dataloader settings
train_loader_cfg = {**loader_cfg, **cfg.data.get('train_dataloader', {})}
data_loaders = [build_dataloader(ds, **train_loader_cfg) for ds in dataset]
# put model on gpus
if distributed:
find_unused_parameters = cfg.get('find_unused_parameters', False)
# Sets the `find_unused_parameters` parameter in
# torch.nn.parallel.DistributedDataParallel
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False,
find_unused_parameters=find_unused_parameters)
else:
if device == 'cpu':
warnings.warn(
'The argument `device` is deprecated. To use cpu to train, '
'please refers to https://mmclassification.readthedocs.io/en'
'/latest/getting_started.html#train-a-model')
model = model.cpu()
elif device == 'ipu':
model = model.cpu()
else:
model = MMDataParallel(model, device_ids=cfg.gpu_ids)
if not model.device_ids:
from mmcv import __version__, digit_version
assert digit_version(__version__) >= (1, 4, 4), \
'To train with CPU, please confirm your mmcv version ' \
'is not lower than v1.4.4'
# build runner
optimizer = build_optimizer(model, cfg.optimizer)
if cfg.get('runner') is None:
cfg.runner = {
'type': 'EpochBasedRunner',
'max_epochs': cfg.total_epochs
}
warnings.warn(
'config is now expected to have a `runner` section, '
'please set `runner` in your config.', UserWarning)
if device == 'ipu':
if not cfg.runner['type'].startswith('IPU'):
cfg.runner['type'] = 'IPU' + cfg.runner['type']
if 'options_cfg' not in cfg.runner:
cfg.runner['options_cfg'] = {}
cfg.runner['options_cfg']['replicationFactor'] = cfg.ipu_replicas
cfg.runner['fp16_cfg'] = cfg.get('fp16', None)
runner = build_runner(cfg.runner,
default_args=dict(model=model,
batch_processor=None,
optimizer=optimizer,
work_dir=cfg.work_dir,
logger=logger,
meta=meta))
# an ugly walkaround to make the .log and .log.json filenames the same
runner.timestamp = timestamp
# fp16 setting
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
if device == 'ipu':
from mmcv.device.ipu import IPUFp16OptimizerHook
optimizer_config = IPUFp16OptimizerHook(
**cfg.optimizer_config,
loss_scale=fp16_cfg['loss_scale'],
distributed=distributed)
else:
optimizer_config = Fp16OptimizerHook(
**cfg.optimizer_config,
loss_scale=fp16_cfg['loss_scale'],
distributed=distributed)
elif distributed and 'type' not in cfg.optimizer_config:
optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
else:
optimizer_config = cfg.optimizer_config
# register hooks
runner.register_training_hooks(cfg.lr_config,
optimizer_config,
cfg.checkpoint_config,
cfg.log_config,
cfg.get('momentum_config', None),
custom_hooks_config=cfg.get(
'custom_hooks', None))
if distributed and cfg.runner['type'] == 'EpochBasedRunner':
runner.register_hook(DistSamplerSeedHook())
# register eval hooks
if validate:
val_dataset = build_dataset(cfg.data.val, dict(test_mode=True))
# The specific dataloader settings
val_loader_cfg = {
**loader_cfg,
'shuffle': False, # Not shuffle by default
'sampler_cfg': None, # Not use sampler by default
**cfg.data.get('val_dataloader', {}),
}
val_dataloader = build_dataloader(val_dataset, **val_loader_cfg)
eval_cfg = cfg.get('evaluation', {})
eval_cfg['by_epoch'] = cfg.runner['type'] != 'IterBasedRunner'
eval_hook = DistEvalHook if distributed else EvalHook
# `EvalHook` needs to be executed after `IterTimerHook`.
# Otherwise, it will cause a bug if use `IterBasedRunner`.
# Refers to https://github.com/open-mmlab/mmcv/issues/1261
runner.register_hook(eval_hook(val_dataloader, **eval_cfg),
priority='LOW')
if cfg.resume_from:
runner.resume(cfg.resume_from)
elif cfg.load_from:
runner.load_checkpoint(cfg.load_from)
runner.run(data_loaders, cfg.workflow)
def train_model(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
device='cuda',
meta=None):
logger = get_root_logger(cfg.log_level)
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
data_loaders = [
build_dataloader(
ds,
cfg.data.samples_per_gpu,
cfg.data.workers_per_gpu,
# cfg.gpus will be ignored if distributed
num_gpus=len(cfg.gpu_ids),
dist=distributed,
round_up=True,
seed=cfg.seed) for ds in dataset
]
# put model on gpus
if distributed:
find_unused_parameters = cfg.get('find_unused_parameters', False)
# Sets the `find_unused_parameters` parameter in
# torch.nn.parallel.DistributedDataParallel
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False,
find_unused_parameters=find_unused_parameters)
else:
if device == 'cuda':
model = MMDataParallel(model.cuda(cfg.gpu_ids[0]),
device_ids=cfg.gpu_ids)
elif device == 'cpu':
model = model.cpu()
else:
raise ValueError(F'unsupported device name {device}.')
# build runner
optimizer = build_optimizer(model, cfg.optimizer)
if cfg.get('runner') is None:
cfg.runner = {
'type': 'EpochBasedRunner',
'max_epochs': cfg.total_epochs
}
warnings.warn(
'config is now expected to have a `runner` section, '
'please set `runner` in your config.', UserWarning)
runner = build_runner(cfg.runner,
default_args=dict(model=model,
batch_processor=None,
optimizer=optimizer,
work_dir=cfg.work_dir,
logger=logger,
meta=meta))
# an ugly walkaround to make the .log and .log.json filenames the same
runner.timestamp = timestamp
# fp16 setting
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
**fp16_cfg,
distributed=distributed)
elif distributed and 'type' not in cfg.optimizer_config:
optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
else:
optimizer_config = cfg.optimizer_config
# register hooks
runner.register_training_hooks(cfg.lr_config,
optimizer_config,
cfg.checkpoint_config,
cfg.log_config,
cfg.get('momentum_config', None),
custom_hooks_config=cfg.get(
'custom_hooks', None))
if distributed:
runner.register_hook(DistSamplerSeedHook())
# register eval hooks
if validate:
val_dataset = build_dataset(cfg.data.val, dict(test_mode=True))
val_dataloader = build_dataloader(
val_dataset,
samples_per_gpu=cfg.data.samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False,
round_up=True)
eval_cfg = cfg.get('evaluation', {})
eval_cfg['by_epoch'] = cfg.runner['type'] != 'IterBasedRunner'
eval_hook = DistEvalHook if distributed else EvalHook
runner.register_hook(eval_hook(val_dataloader, **eval_cfg))
if cfg.resume_from:
runner.resume(cfg.resume_from)
elif cfg.load_from:
runner.load_checkpoint(cfg.load_from)
runner.run(data_loaders, cfg.workflow)
def train_model(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
device=None,
meta=None):
logger = get_root_logger()
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
sampler_cfg = cfg.data.get('sampler', None)
data_loaders = [
build_dataloader(
ds,
cfg.data.samples_per_gpu,
cfg.data.workers_per_gpu,
# cfg.gpus will be ignored if distributed
num_gpus=len(cfg.gpu_ids),
dist=distributed,
round_up=True,
seed=cfg.seed,
sampler_cfg=sampler_cfg) for ds in dataset
]
# put model on gpus
if distributed:
find_unused_parameters = cfg.get('find_unused_parameters', False)
# Sets the `find_unused_parameters` parameter in
# torch.nn.parallel.DistributedDataParallel
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False,
find_unused_parameters=find_unused_parameters)
else:
if device == 'cpu':
warnings.warn(
'The argument `device` is deprecated. To use cpu to train, '
'please refers to https://mmclassification.readthedocs.io/en'
'/latest/getting_started.html#train-a-model')
model = model.cpu()
else:
model = MMDataParallel(model, device_ids=cfg.gpu_ids)
if not model.device_ids:
from mmcv import __version__, digit_version
assert digit_version(__version__) >= (1, 4, 4), \
'To train with CPU, please confirm your mmcv version ' \
'is not lower than v1.4.4'
# build runner
optimizer = build_optimizer(model, cfg.optimizer)
if cfg.get('runner') is None:
cfg.runner = {
'type': 'EpochBasedRunner',
'max_epochs': cfg.total_epochs
}
warnings.warn(
'config is now expected to have a `runner` section, '
'please set `runner` in your config.', UserWarning)
runner = build_runner(cfg.runner,
default_args=dict(model=model,
batch_processor=None,
optimizer=optimizer,
work_dir=cfg.work_dir,
logger=logger,
meta=meta))
# an ugly walkaround to make the .log and .log.json filenames the same
runner.timestamp = timestamp
# fp16 setting
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
**fp16_cfg,
distributed=distributed)
elif distributed and 'type' not in cfg.optimizer_config:
optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
else:
optimizer_config = cfg.optimizer_config
# register hooks
runner.register_training_hooks(cfg.lr_config,
optimizer_config,
cfg.checkpoint_config,
cfg.log_config,
cfg.get('momentum_config', None),
custom_hooks_config=cfg.get(
'custom_hooks', None))
if distributed and cfg.runner['type'] == 'EpochBasedRunner':
runner.register_hook(DistSamplerSeedHook())
# register eval hooks
if validate:
val_dataset = build_dataset(cfg.data.val, dict(test_mode=True))
val_dataloader = build_dataloader(
val_dataset,
samples_per_gpu=cfg.data.samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False,
round_up=True)
eval_cfg = cfg.get('evaluation', {})
eval_cfg['by_epoch'] = cfg.runner['type'] != 'IterBasedRunner'
eval_hook = DistEvalHook if distributed else EvalHook
# `EvalHook` needs to be executed after `IterTimerHook`.
# Otherwise, it will cause a bug if use `IterBasedRunner`.
# Refers to https://github.com/open-mmlab/mmcv/issues/1261
runner.register_hook(eval_hook(val_dataloader, **eval_cfg),
priority='LOW')
if cfg.resume_from:
runner.resume(cfg.resume_from)
elif cfg.load_from:
runner.load_checkpoint(cfg.load_from)
runner.run(data_loaders, cfg.workflow)
