Spaces:
Running
Running
File size: 4,193 Bytes
174ad5e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import logging
import os
import os.path as osp
from mmengine.config import Config, DictAction
from mmengine.logging import print_log
from mmengine.registry import RUNNERS
from mmengine.runner import Runner
def parse_args():
parser = argparse.ArgumentParser(description='Train a 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', action='store_true', help='Whether to resume checkpoint.')
parser.add_argument(
'--amp',
action='store_true',
default=False,
help='Enable automatic-mixed-precision training')
parser.add_argument(
'--auto-scale-lr',
action='store_true',
help='Whether to scale the learning rate automatically. It requires '
'`auto_scale_lr` in config, and `base_batch_size` in `auto_scale_lr`')
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 main():
args = parse_args()
# load config
cfg = Config.fromfile(args.config)
cfg.launcher = args.launcher
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# 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:
optim_wrapper = cfg.optim_wrapper.type
if optim_wrapper == 'AmpOptimWrapper':
print_log(
'AMP training is already enabled in your config.',
logger='current',
level=logging.WARNING)
else:
assert optim_wrapper == 'OptimWrapper', (
'`--amp` is only supported when the optimizer wrapper type is '
f'`OptimWrapper` but got {optim_wrapper}.')
cfg.optim_wrapper.type = 'AmpOptimWrapper'
cfg.optim_wrapper.loss_scale = 'dynamic'
if args.resume:
cfg.resume = True
# enable automatically scaling LR
if args.auto_scale_lr:
if 'auto_scale_lr' in cfg and \
'base_batch_size' in cfg.auto_scale_lr:
cfg.auto_scale_lr.enable = True
else:
raise RuntimeError('Can not find "auto_scale_lr" or '
'"auto_scale_lr.base_batch_size" in your'
' configuration file.')
# build the runner from config
if 'runner_type' not in cfg:
# build the default runner
runner = Runner.from_cfg(cfg)
else:
# build customized runner from the registry
# if 'runner_type' is set in the cfg
runner = RUNNERS.build(cfg)
# start training
runner.train()
if __name__ == '__main__':
main()
|