File size: 6,614 Bytes
241adf2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
184
185
186
187
188
189
190
191
import argparse
import copy
import os
import os.path as osp
import time

import mmcv
import torch
from mmcv import Config, DictAction
from mmcv.runner import get_dist_info, init_dist, set_random_seed
from mmcv.utils import get_git_hash

from models import *  # noqa
from models.apis import train_model
from models.datasets import build_dataset

from mmpose import __version__
from mmpose.models import build_posenet
from mmpose.utils import collect_env, get_root_logger


def parse_args():
    parser = argparse.ArgumentParser(description='Train a pose model')
    parser.add_argument('--config', default=None, help='train config file path')
    parser.add_argument('--work-dir', default=None, help='the dir to save logs and models')
    parser.add_argument(
        '--resume-from', help='the checkpoint file to resume from')
    parser.add_argument(
        '--auto-resume', type=bool, default=True, help='automatically detect the latest checkpoint in word dir and resume from it.')
    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='number of gpus to use '
        '(only applicable to non-distributed training)')
    group_gpus.add_argument(
        '--gpu-ids',
        type=int,
        nargs='+',
        help='ids of gpus to use '
        '(only applicable to non-distributed training)')
    parser.add_argument('--seed', type=int, default=None, help='random seed')
    parser.add_argument(
        '--deterministic',
        action='store_true',
        help='whether to set deterministic options for CUDNN backend.') 
    parser.add_argument(
        '--cfg-options',
        nargs='+',
        action=DictAction,
        default={},
        help='override some settings in the used config, the key-value pair '
        'in xxx=yyy format will be merged into config file. For example, '
        "'--cfg-options model.backbone.depth=18 model.backbone.with_cp=True'")
    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(
        '--autoscale-lr',
        action='store_true',
        help='automatically scale lr with the number of gpus')
    parser.add_argument(
        '--show',
        action='store_true',
        help='whether to display the prediction results in a window.')
    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 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])
    # auto resume
    if args.auto_resume:
        checkpoint = os.path.join(args.work_dir, 'latest.pth')
        if os.path.exists(checkpoint):
            cfg.resume_from = checkpoint
    
    if args.resume_from is not None:
        cfg.resume_from = args.resume_from
    if args.gpu_ids is not None:
        cfg.gpu_ids = args.gpu_ids
    else:
        cfg.gpu_ids = range(1) if args.gpus is None else range(args.gpus)

    if args.autoscale_lr:
        # apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
        cfg.optimizer['lr'] = cfg.optimizer['lr'] * len(cfg.gpu_ids) / 8

    # 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)
        # 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'{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

    # log some basic info
    logger.info(f'Distributed training: {distributed}')
    logger.info(f'Config:\n{cfg.pretty_text}')

    # set random seeds
    args.seed = 1
    args.deterministic = True
    if args.seed is not None:
        logger.info(f'Set random seed to {args.seed}, '
                    f'deterministic: {args.deterministic}')
        set_random_seed(args.seed, deterministic=args.deterministic)
    cfg.seed = args.seed
    meta['seed'] = args.seed

    model = build_posenet(cfg.model)
    train_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))

    val_dataset = copy.deepcopy(cfg.data.val)
    val_dataset = build_dataset(val_dataset, dict(test_mode=True))

    if cfg.checkpoint_config is not None:
        # save mmpose version, config file content
        # checkpoints as meta data
        cfg.checkpoint_config.meta = dict(
            mmpose_version=__version__ + get_git_hash(digits=7),
            config=cfg.pretty_text,
        )
    train_model(
        model,
        train_datasets,
        val_dataset,
        cfg,
        distributed=distributed,
        validate=(not args.no_validate),
        timestamp=timestamp,
        meta=meta)


if __name__ == '__main__':
    main()