File size: 6,574 Bytes
8b3f571 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | # Copyright (c) OpenMMLab. All rights reserved.
import sys, os
sys.path.append(os.path.join(os.path.abspath(os.path.dirname(__file__)), '..'))
import src
import copy
import argparse
import os.path as osp
from mmengine.config import Config, DictAction
from mmengine.registry import RUNNERS
from mmengine.runner._flexible_runner import FlexibleRunner
# import torch
# torch.autograd.set_detect_anomaly(True)
# import faulthandler
# faulthandler.enable()
# import numpy as np
# np.seterr(divide='raise', invalid='raise', over='raise')
def parse_args():
parser = argparse.ArgumentParser(description='Train a detector')
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(
'--amp',
action='store_true',
default=False,
help='enable automatic-mixed-precision training')
parser.add_argument(
'--auto-scale-lr',
action='store_true',
help='enable automatically scaling LR.')
parser.add_argument(
'--resume',
nargs='?',
type=str,
const='auto',
help='If specify checkpoint path, resume from it, while if not '
'specify, try to auto resume from the latest checkpoint '
'in the work directory.')
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 is True:
cfg.optim_wrapper.type = 'AmpOptimWrapper'
cfg.optim_wrapper.loss_scale = 'dynamic'
# enable automatically scaling LR
if args.auto_scale_lr:
if 'auto_scale_lr' in cfg and \
'enable' in cfg.auto_scale_lr 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.enable" or '
'"auto_scale_lr.base_batch_size" in your'
' configuration file.')
# resume is determined in this priority: resume from > auto_resume
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
# 指定 DeepSpeedStrategy 并配置参数
strategy = dict(
type='DeepSpeedStrategy',
bf16=dict(
enabled=True,
),
inputs_to_half=['motion', 'traj_data', 'audio_data', 'mean', 'std'],
zero_optimization=dict(
stage=3,
ignore_unused_parameters=True,
allgather_partitions=True,
reduce_scatter=True,
allgather_bucket_size=10000000,
reduce_bucket_size=10000000,
# overlap_comm=True,
overlap_comm=False,
contiguous_gradients=True,
cpu_offload=False),
# zero_optimization = dict(
# stage=2,
# ignore_unused_parameters=True, # 你这个场景需要保留
# reduce_scatter=True,
# allgather_partitions=True,
# overlap_comm=True,
# contiguous_gradients=True,
# reduce_bucket_size=5e7,
# allgather_bucket_size=5e7,
# )
)
optim_wrapper = dict(type='DeepSpeedOptimWrapper')
optim_wrapper['optimizer'] = cfg.optim_wrapper.optimizer
cfg.optim_wrapper = optim_wrapper
cfg = copy.deepcopy(cfg)
runner = FlexibleRunner(
model=cfg['model'],
work_dir=cfg.get('work_dir', 'work_dirs'),
experiment_name=cfg.get('experiment_name'),
train_dataloader=cfg.get('train_dataloader'),
optim_wrapper=cfg.get('optim_wrapper'),
param_scheduler=cfg.get('param_scheduler'),
train_cfg=cfg.get('train_cfg'),
val_dataloader=cfg.get('val_dataloader'),
val_evaluator=cfg.get('val_evaluator'),
val_cfg=cfg.get('val_cfg'),
test_dataloader=cfg.get('test_dataloader'),
test_evaluator=cfg.get('test_evaluator'),
test_cfg=cfg.get('test_cfg'),
strategy=strategy,
auto_scale_lr=cfg.get('auto_scale_lr'),
default_hooks=cfg.get('default_hooks'),
custom_hooks=cfg.get('custom_hooks'),
data_preprocessor=cfg.get('data_preprocessor'),
load_from=cfg.get('load_from'),
resume=cfg.get('resume', False),
launcher=cfg.get('launcher'),
env_cfg=cfg.get('env_cfg'), # type: ignore
log_processor=cfg.get('log_processor'),
log_level=cfg.get('log_level', 'INFO'),
visualizer=cfg.get('visualizer'),
default_scope=cfg.get('default_scope', 'mmengine'),
randomness=cfg.get('randomness', dict(seed=None)),
cfg=cfg,
)
runner.train()
if __name__ == '__main__':
main()
|