mmsegmentation之tools/train.py文件解析(部分,持续更新)

# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import copy
import os
import os.path as osp
import time
import warnings

import mmcv
import torch
import torch.distributed as dist
from mmcv.cnn.utils import revert_sync_batchnorm
from mmcv.runner import get_dist_info, init_dist
from mmcv.utils import Config, DictAction, get_git_hash

from mmseg import __version__
from mmseg.apis import init_random_seed, set_random_seed, train_segmentor
from mmseg.datasets import build_dataset
from mmseg.models import build_segmentor
from mmseg.utils import collect_env, get_root_logger, setup_multi_processes


def parse_args():
    parser = argparse.ArgumentParser(description='Train a segmentor')
    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(
        '--load-from', help='the checkpoint file to load weights from')
    parser.add_argument(
        '--resume-from', help='the checkpoint file to resume from')
    parser.add_argument(
        '--no-validate',
        action='store_true',
        help='whether not to evaluate the checkpoint during training')
    group_gpus = parser.add_mutually_exclusive_group()
    group_gpus.add_argument(
        '--gpus',
        type=int,
        help='(Deprecated, please use --gpu-id) number of gpus to use '
        '(only applicable to non-distributed training)')
    group_gpus.add_argument(
        '--gpu-ids',
        type=int,
        nargs='+',
        help='(Deprecated, please use --gpu-id) ids of gpus to use '
        '(only applicable to non-distributed training)')
    group_gpus.add_argument(
        '--gpu-id',
        type=int,
        default=0,
        help='id of gpu to use '
        '(only applicable to non-distributed training)')
    parser.add_argument('--seed', type=int, default=None, help='random seed')
    parser.add_argument(
        '--diff_seed',
        action='store_true',
        help='Whether or not set different seeds for different ranks')
    parser.add_argument(
        '--deterministic',
        action='store_true',
        help='whether to set deterministic options for CUDNN backend.')
    parser.add_argument(
        '--options',
        nargs='+',
        action=DictAction,
        help="--options is deprecated in favor of --cfg_options' and it will "
        'not be supported in version v0.22.0. 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(
        '--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')
    parser.add_argument('--local_rank', type=int, default=0)
    parser.add_argument(
        '--auto-resume',
        action='store_true',
        help='resume from the latest checkpoint automatically.')
    args = parser.parse_args()
    if 'LOCAL_RANK' not in os.environ:
        os.environ['LOCAL_RANK'] = str(args.local_rank)

    if args.options and args.cfg_options:
        raise ValueError(
            '--options and --cfg-options cannot be both '
            'specified, --options is deprecated in favor of --cfg-options. '
            '--options will not be supported in version v0.22.0.')
    if args.options:
        warnings.warn('--options is deprecated in favor of --cfg-options. '
                      '--options will not be supported in version v0.22.0.')
        args.cfg_options = args.options

    return args


def main():
    args = parse_args() # 解析命令行参数

    cfg = Config.fromfile(args.config) # 读入cfg参数
    if args.cfg_options is not None:
        cfg.merge_from_dict(args.cfg_options)

    # 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.load_from is not None:
        cfg.load_from = args.load_from
    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]

    cfg.auto_resume = args.auto_resume

    # 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)
        # gpu_ids is used to calculate iter when resuming checkpoint
        _, world_size = get_dist_info()
        cfg.gpu_ids = range(world_size)

    # create work_dir
    mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir)) # 检测work_dir,若不存在创建work_dir
    # dump config
    cfg.dump(osp.join(cfg.work_dir, osp.basename(args.config))) # dump cfg参数
    # init the logger before other steps
    timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime()) # time记录
    log_file = osp.join(cfg.work_dir, f'{timestamp}.log') # 创建log文件
    logger = get_root_logger(log_file=log_file, log_level=cfg.log_level) #

    # set multi-process settings
    setup_multi_processes(cfg)

    # 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() # 收集环境信息
    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)
    seed = seed + dist.get_rank() if args.diff_seed else seed
    logger.info(f'Set random seed to {seed}, '
                f'deterministic: {args.deterministic}')
    set_random_seed(seed, deterministic=args.deterministic) # 设置随机种子
    cfg.seed = seed
    meta['seed'] = seed
    meta['exp_name'] = osp.basename(args.config)

    model = build_segmentor(
        cfg.model,
        train_cfg=cfg.get('train_cfg'),
        test_cfg=cfg.get('test_cfg'))
    model.init_weights()

    # SyncBN is not support for DP
    if not distributed:
        warnings.warn(
            'SyncBN is only supported with DDP. To be compatible with DP, '
            'we convert SyncBN to BN. Please use dist_train.sh which can '
            'avoid this error.')
        model = revert_sync_batchnorm(model)

    logger.info(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 mmseg version, config file content and class names in
        # checkpoints as meta data
        cfg.checkpoint_config.meta = dict(
            mmseg_version=f'{__version__}+{get_git_hash()[:7]}',
            config=cfg.pretty_text,
            CLASSES=datasets[0].CLASSES,
            PALETTE=datasets[0].PALETTE)
    # add an attribute for visualization convenience
    model.CLASSES = datasets[0].CLASSES
    # passing checkpoint meta for saving best checkpoint
    meta.update(cfg.checkpoint_config.meta)
    train_segmentor(
        model,
        datasets,
        cfg,
        distributed=distributed,
        validate=(not args.no_validate),
        timestamp=timestamp,
        meta=meta)


if __name__ == '__main__':
    main()

  • 2
    点赞
  • 4
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 2
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

kira_Y

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值