mmselfsup/tools/train.py

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

import mmcv
import torch
import torch.distributed as dist
from mmcv import Config, DictAction
from mmcv.runner import get_dist_info, init_dist

from mmselfsup import __version__
from mmselfsup.apis import init_random_seed, set_random_seed, train_model
from mmselfsup.datasets import build_dataset
from mmselfsup.models import build_algorithm
from mmselfsup.utils import collect_env, get_root_logger, setup_multi_processes


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='(Deprecated, please use --work-dir) the dir to save logs and '
        'models')
    parser.add_argument('--work-dir', help='the dir to save logs and models')
    parser.add_argument(
        '--resume_from',
        help='(Deprecated, please use --resume-from) the checkpoint file '
        'to resume from')
    parser.add_argument(
        '--resume-from', help='the checkpoint file to resume from')
    parser.add_argument(
        '--auto-resume',
        action='store_true',
        help='resume from the latest checkpoint automatically')
    group_gpus = parser.add_mutually_exclusive_group()
    group_gpus.add_argument(
        '--gpus',
        type=int,
        default=1,
        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(
        '--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)
    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()

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

    # set multi-process settings
    setup_multi_processes(cfg)

    # 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
        work_type = args.config.split('/')[1]
        cfg.work_dir = osp.join('./work_dirs', work_type,
                                osp.splitext(osp.basename(args.config))[0])
    if args.resume_from is not None:
        cfg.resume_from = args.resume_from
    cfg.auto_resume = args.auto_resume
    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]

    # init distributed env first, since logger depends on the dist info.
    if args.launcher == 'none':
        distributed = False
        assert cfg.model.type not in [
            'DeepCluster', 'MoCo', 'SimCLR', 'ODC', 'NPID', 'SimSiam',
            'DenseCL', 'BYOL'
        ], f'{cfg.model.type} does not support non-dist training.'
    else:
        distributed = True
        init_dist(args.launcher, **cfg.dist_params)
        # re-set gpu_ids with distributed training mode
        _, world_size = get_dist_info()
        cfg.gpu_ids = range(world_size)

    # create work_dir
    mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))

    # init the logger before other steps
    timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
    log_file = osp.join(cfg.work_dir, f'train_{timestamp}.log')
    logger = get_root_logger(log_file=log_file, log_level=cfg.log_level)

    # 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()
    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
    meta['config'] = cfg.pretty_text
    # 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)
    cfg.seed = seed
    meta['seed'] = seed
    meta['exp_name'] = osp.basename(args.config)

    model = build_algorithm(cfg.model)
    model.init_weights()

    datasets = [build_dataset(cfg.data.train)]
    assert len(cfg.workflow) == 1, 'Validation is called by hook.'
    if cfg.checkpoint_config is not None:
        # save mmselfsup version, config file content and class names in
        # checkpoints as meta data
        cfg.checkpoint_config.meta = dict(
            mmselfsup_version=__version__, config=cfg.pretty_text)

    train_model(
        model,
        datasets,
        cfg,
        distributed=distributed,
        timestamp=timestamp,
        meta=meta)


if __name__ == '__main__':
    main()