123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160 |
- # Copyright (c) OpenMMLab. All rights reserved.
- import argparse
- import os
- import os.path as osp
- from mmengine.config import Config, DictAction
- from mmengine.runner import Runner
- def parse_args():
- parser = argparse.ArgumentParser(description='Train a pose model')
- parser.add_argument('config', help='train config file path')
- parser.add_argument('--work-dir', help='the dir to save logs and models')
- parser.add_argument(
- '--resume',
- nargs='?',
- type=str,
- const='auto',
- help='If specify checkpint path, resume from it, while if not '
- 'specify, try to auto resume from the latest checkpoint '
- 'in the work directory.')
- parser.add_argument(
- '--amp',
- action='store_true',
- default=False,
- help='enable automatic-mixed-precision training')
- parser.add_argument(
- '--no-validate',
- action='store_true',
- help='whether not to evaluate the checkpoint during training')
- parser.add_argument(
- '--auto-scale-lr',
- action='store_true',
- help='whether to auto scale the learning rate according to the '
- 'actual batch size and the original batch size.')
- parser.add_argument(
- '--show-dir',
- help='directory where the visualization images will be saved.')
- parser.add_argument(
- '--show',
- action='store_true',
- help='whether to display the prediction results in a window.')
- parser.add_argument(
- '--interval',
- type=int,
- default=1,
- help='visualize per interval samples.')
- parser.add_argument(
- '--wait-time',
- type=float,
- default=1,
- help='display time of every window. (second)')
- 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')
- # When using PyTorch version >= 2.0.0, the `torch.distributed.launch`
- # will pass the `--local-rank` parameter to `tools/train.py` instead
- # of `--local_rank`.
- parser.add_argument('--local_rank', '--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)
- return args
- def merge_args(cfg, args):
- """Merge CLI arguments to config."""
- if args.no_validate:
- cfg.val_cfg = None
- cfg.val_dataloader = None
- cfg.val_evaluator = None
- cfg.launcher = args.launcher
- # 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])
- # enable automatic-mixed-precision training
- if args.amp is True:
- optim_wrapper = cfg.optim_wrapper.get('type', 'OptimWrapper')
- assert optim_wrapper in ['OptimWrapper', 'AmpOptimWrapper'], \
- '`--amp` is not supported custom optimizer wrapper type ' \
- f'`{optim_wrapper}.'
- cfg.optim_wrapper.type = 'AmpOptimWrapper'
- cfg.optim_wrapper.setdefault('loss_scale', 'dynamic')
- # resume training
- if args.resume == 'auto':
- cfg.resume = True
- cfg.load_from = None
- elif args.resume is not None:
- cfg.resume = True
- cfg.load_from = args.resume
- # enable auto scale learning rate
- if args.auto_scale_lr:
- cfg.auto_scale_lr.enable = True
- # visualization-
- if args.show or (args.show_dir is not None):
- assert 'visualization' in cfg.default_hooks, \
- 'PoseVisualizationHook is not set in the ' \
- '`default_hooks` field of config. Please set ' \
- '`visualization=dict(type="PoseVisualizationHook")`'
- cfg.default_hooks.visualization.enable = True
- cfg.default_hooks.visualization.show = args.show
- if args.show:
- cfg.default_hooks.visualization.wait_time = args.wait_time
- cfg.default_hooks.visualization.out_dir = args.show_dir
- cfg.default_hooks.visualization.interval = args.interval
- if args.cfg_options is not None:
- cfg.merge_from_dict(args.cfg_options)
- return cfg
- def main():
- args = parse_args()
- # load config
- cfg = Config.fromfile(args.config)
- # merge CLI arguments to config
- cfg = merge_args(cfg, args)
- # set preprocess configs to model
- if 'preprocess_cfg' in cfg:
- cfg.model.setdefault('data_preprocessor',
- cfg.get('preprocess_cfg', {}))
- # build the runner from config
- runner = Runner.from_cfg(cfg)
- # start training
- runner.train()
- if __name__ == '__main__':
- main()
|