File size: 4,015 Bytes
18dd6ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import random
import warnings

import numpy as np
import torch
from annotator.mmpkg.mmcv.parallel import MMDataParallel, MMDistributedDataParallel
from annotator.mmpkg.mmcv.runner import build_optimizer, build_runner

from annotator.mmpkg.mmseg.core import DistEvalHook, EvalHook
from annotator.mmpkg.mmseg.datasets import build_dataloader, build_dataset
from annotator.mmpkg.mmseg.utils import get_root_logger


def set_random_seed(seed, deterministic=False):
    """Set random seed.

    Args:
        seed (int): Seed to be used.
        deterministic (bool): Whether to set the deterministic option for
            CUDNN backend, i.e., set `torch.backends.cudnn.deterministic`
            to True and `torch.backends.cudnn.benchmark` to False.
            Default: False.
    """
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)
    if deterministic:
        torch.backends.cudnn.deterministic = True
        torch.backends.cudnn.benchmark = False


def train_segmentor(model,
                    dataset,
                    cfg,
                    distributed=False,
                    validate=False,
                    timestamp=None,
                    meta=None):
    """Launch segmentor training."""
    logger = get_root_logger(cfg.log_level)

    # prepare data loaders
    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
    data_loaders = [
        build_dataloader(
            ds,
            cfg.data.samples_per_gpu,
            cfg.data.workers_per_gpu,
            # cfg.gpus will be ignored if distributed
            len(cfg.gpu_ids),
            dist=distributed,
            seed=cfg.seed,
            drop_last=True) for ds in dataset
    ]

    # put model on gpus
    if distributed:
        find_unused_parameters = cfg.get('find_unused_parameters', False)
        # Sets the `find_unused_parameters` parameter in
        # torch.nn.parallel.DistributedDataParallel
        model = MMDistributedDataParallel(
            model.cuda(),
            device_ids=[torch.cuda.current_device()],
            broadcast_buffers=False,
            find_unused_parameters=find_unused_parameters)
    else:
        model = MMDataParallel(
            model.cuda(cfg.gpu_ids[0]), device_ids=cfg.gpu_ids)

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)

    if cfg.get('runner') is None:
        cfg.runner = {'type': 'IterBasedRunner', 'max_iters': cfg.total_iters}
        warnings.warn(
            'config is now expected to have a `runner` section, '
            'please set `runner` in your config.', UserWarning)

    runner = build_runner(
        cfg.runner,
        default_args=dict(
            model=model,
            batch_processor=None,
            optimizer=optimizer,
            work_dir=cfg.work_dir,
            logger=logger,
            meta=meta))

    # register hooks
    runner.register_training_hooks(cfg.lr_config, cfg.optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config,
                                   cfg.get('momentum_config', None))

    # an ugly walkaround to make the .log and .log.json filenames the same
    runner.timestamp = timestamp

    # register eval hooks
    if validate:
        val_dataset = build_dataset(cfg.data.val, dict(test_mode=True))
        val_dataloader = build_dataloader(
            val_dataset,
            samples_per_gpu=1,
            workers_per_gpu=cfg.data.workers_per_gpu,
            dist=distributed,
            shuffle=False)
        eval_cfg = cfg.get('evaluation', {})
        eval_cfg['by_epoch'] = cfg.runner['type'] != 'IterBasedRunner'
        eval_hook = DistEvalHook if distributed else EvalHook
        runner.register_hook(eval_hook(val_dataloader, **eval_cfg), priority='LOW')

    if cfg.resume_from:
        runner.resume(cfg.resume_from)
    elif cfg.load_from:
        runner.load_checkpoint(cfg.load_from)
    runner.run(data_loaders, cfg.workflow)