train.py

# Copyright (c) OpenMMLab. All rights reserved.
import sys
import warnings

import mmcv
import numpy as np
import torch
import torch.distributed as dist
import tqdm
from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
from mmcv.runner import (DistSamplerSeedHook, EpochBasedRunner, OptimizerHook,
                         get_dist_info)
from mmcv.utils import digit_version

from mmpose.core import DistEvalHook, EvalHook, build_optimizers
from mmpose.core.distributed_wrapper import DistributedDataParallelWrapper
from mmpose.datasets import build_dataloader, build_dataset
from mmpose.utils import get_root_logger

try:
    from mmcv.runner import Fp16OptimizerHook
except ImportError:
    warnings.warn(
        'Fp16OptimizerHook from mmpose will be deprecated from '
        'v0.15.0. Please install mmcv>=1.1.4', DeprecationWarning)
    from mmpose.core import Fp16OptimizerHook


def init_random_seed(seed=None, device='cuda'):
    """Initialize random seed.

    If the seed is not set, the seed will be automatically randomized,
    and then broadcast to all processes to prevent some potential bugs.

    Args:
        seed (int, Optional): The seed. Default to None.
        device (str): The device where the seed will be put on.
            Default to 'cuda'.

    Returns:
        int: Seed to be used.
    """
    if seed is not None:
        return seed

    # Make sure all ranks share the same random seed to prevent
    # some potential bugs. Please refer to
    # https://github.com/open-mmlab/mmdetection/issues/6339
    rank, world_size = get_dist_info()
    seed = np.random.randint(2**31)
    if world_size == 1:
        return seed

    if rank == 0:
        random_num = torch.tensor(seed, dtype=torch.int32, device=device)
    else:
        random_num = torch.tensor(0, dtype=torch.int32, device=device)
    dist.broadcast(random_num, src=0)
    return random_num.item()


def train_model(model,
                dataset,
                cfg,
                distributed=False,
                validate=False,
                timestamp=None,
                meta=None):
    """Train model entry function.

    Args:
        model (nn.Module): The model to be trained.
        dataset (Dataset): Train dataset.
        cfg (dict): The config dict for training.
        distributed (bool): Whether to use distributed training.
            Default: False.
        validate (bool): Whether to do evaluation. Default: False.
        timestamp (str | None): Local time for runner. Default: None.
        meta (dict | None): Meta dict to record some important information.
            Default: None
    """
    logger = get_root_logger(cfg.log_level)

    # prepare data loaders
    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
    # step 1: give default values and override (if exist) from cfg.data
    loader_cfg = {
        **dict(
            seed=cfg.get('seed'),
            drop_last=False,
            dist=distributed,
            num_gpus=len(cfg.gpu_ids)),
        **({} if torch.__version__ != 'parrots' else dict(
               prefetch_num=2,
               pin_memory=False,
           )),
        **dict((k, cfg.data[k]) for k in [
                   'samples_per_gpu',
                   'workers_per_gpu',
                   'shuffle',
                   'seed',
                   'drop_last',
                   'prefetch_num',
                   'pin_memory',
                   'persistent_workers',
               ] if k in cfg.data)
    }

    # step 2: cfg.data.train_dataloader has highest priority
    train_loader_cfg = dict(loader_cfg, **cfg.data.get('train_dataloader', {}))

    data_loaders = [build_dataloader(ds, **train_loader_cfg) for ds in dataset]

    load_data_only = cfg.data.get('load_data_only', False)
    assert load_data_only
    # only enumerate dataset
    for data_loader in data_loaders:
        for _ in tqdm.tqdm(data_loader):
            pass
    print("dataset enumerated, exit!")
    sys.exit()