def _dist_train(model, data_loaders, batch_processor, cfg):
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)
    # register hooks
    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)
    # register hooks
    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(CocoDistEvalRecallHook(val_dataset_cfg))
        else:
            dataset_type = getattr(datasets, val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(CocoDistEvalmAPHook(val_dataset_cfg))
            else:
                runner.register_hook(DistEvalmAPHook(val_dataset_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)
    # register hooks
    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(CocoDistEvalRecallHook(val_dataset_cfg))
        else:
            dataset_type = getattr(datasets, val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(CocoDistEvalmAPHook(val_dataset_cfg))
            else:
                runner.register_hook(DistEvalmAPHook(val_dataset_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)
    # register hooks
    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(CocoDistEvalRecallHook(val_dataset_cfg))
        else:
            dataset_type = getattr(datasets, val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(CocoDistEvalmAPHook(val_dataset_cfg))
            else:
                runner.register_hook(DistEvalmAPHook(val_dataset_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # build runner
    runner = Runner(model, batch_processor, cfg.optimizer, cfg.work_dir,
                    cfg.log_level)
    # register hooks
    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(CocoDistEvalRecallHook(cfg.data.val))
        else:
            if cfg.data.val.type == 'CocoDataset':
                runner.register_hook(CocoDistEvalmAPHook(cfg.data.val))
            else:
                runner.register_hook(DistEvalmAPHook(cfg.data.val))

    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, cfg.total_epochs) 

def _dist_train(model, datasets, cfg, validate=False, logger=None):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True) for dataset in datasets
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # build runner
    runner = NASRunner(model, batch_processor, None, cfg.work_dir, cfg.log_level, cfg=cfg, logger=logger)

    # register hooks
    weight_optim_config = DistOptimizerHook(**cfg.optimizer.weight_optim.optimizer_config)
    arch_optim_config = ArchDistOptimizerHook(**cfg.optimizer.arch_optim.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, weight_optim_config, arch_optim_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(CocoDistEvalRecallHook(cfg.data.val))
        else:
            if cfg.dataset_type == 'CocoDataset':
                # runner.register_hook(CocoDistEvalmAPHook_(datasets[1]))
                runner.register_hook(CocoDistEvalmAPHook(cfg.data.val_))
            else:
                runner.register_hook(DistEvalmAPHook(cfg.data.val))

    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, cfg.total_epochs, cfg.arch_update_epoch) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)
    # register hooks
    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(CocoDistEvalRecallHook(val_dataset_cfg))
        else:
            dataset_type = getattr(datasets, val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(CocoDistEvalmAPHook(val_dataset_cfg))
            else:
                runner.register_hook(DistEvalmAPHook(val_dataset_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.videos_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # build runner
    runner = Runner(model, batch_processor, cfg.optimizer, cfg.work_dir,
                    cfg.log_level)
    # register hooks
    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        if cfg.data.val.type in ['RawFramesDataset', 'VideoDataset']:
            runner.register_hook(
                DistEvalTopKAccuracyHook(cfg.data.val, k=(1, 5)))
        if cfg.data.val.type == 'AVADataset':
            runner.register_hook(AVADistEvalmAPHook(cfg.data.val))
    # if validate:
    #     if isinstance(model.module, RPN):
    #         # TODO: implement recall hooks for other datasets
    #         runner.register_hook(CocoDistEvalRecallHook(cfg.data.val))
    #     else:
    #         if cfg.data.val.type == 'CocoDataset':
    #             runner.register_hook(CocoDistEvalmAPHook(cfg.data.val))
    #         else:
    #             runner.register_hook(DistEvalmAPHook(cfg.data.val))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # build runner
    runner = Runner(model, batch_processor, cfg.optimizer, cfg.work_dir,
                    cfg.log_level)
    # register hooks
    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(CocoDistEvalRecallHook(cfg.data.val))
        else:
            if cfg.data.val.type == 'CocoDataset':
                runner.register_hook(CocoDistEvalmAPHook(cfg.data.val))
            else:
                runner.register_hook(DistEvalmAPHook(cfg.data.val))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # build runner
    runner = Runner(model, batch_processor, cfg.optimizer, cfg.work_dir,
                    cfg.log_level)
    # register hooks
    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(CocoDistEvalRecallHook(cfg.data.val))
        else:
            if cfg.data.val.type == 'CocoDataset':
                runner.register_hook(CocoDistEvalmAPHook(cfg.data.val))
            else:
                runner.register_hook(DistEvalmAPHook(cfg.data.val))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = getattr(datasets, val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = getattr(datasets, val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
    data_loaders = [
        build_dataloader(
            ds, cfg.data.imgs_per_gpu, cfg.data.workers_per_gpu, dist=True)
        for ds in dataset
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = DATASETS.get(val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
    data_loaders = [
        build_dataloader(
            ds, cfg.data.imgs_per_gpu, cfg.data.workers_per_gpu, dist=True)
        for ds in dataset
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = DATASETS.get(val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalF1Hook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
    data_loaders = [
        build_dataloader(
            ds, cfg.data.imgs_per_gpu, cfg.data.workers_per_gpu, dist=True)
        for ds in dataset
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = DATASETS.get(val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
    data_loaders = [
        build_dataloader(
            ds, cfg.data.imgs_per_gpu, cfg.data.workers_per_gpu, dist=True)
        for ds in dataset
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = DATASETS.get(val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = getattr(datasets, val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
    data_loaders = [
        build_dataloader(
            ds, cfg.data.imgs_per_gpu, cfg.data.workers_per_gpu, dist=True)
        for ds in dataset
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = DATASETS.get(val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]

    

    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())
    # with torch.no_grad():
    #     for j in range(2):
    #         print(j)
    #         for i, data_batch in enumerate(data_loaders[0]):
    #             _ = model(**data_batch)
    #             # break

    # build runner
    runner = Runner(model, batch_processor, cfg.optimizer, cfg.work_dir,
                    cfg.log_level)
    # register hooks
    optimizer_config = DistOptimizerHook(**cfg.optimizer_config)
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(CocoDistEvalRecallHook(cfg.data.val))
        else:
            if cfg.data.val.type == 'CocoDataset':
                runner.register_hook(CocoDistEvalmAPHook(cfg.data.val))
            else:
                runner.register_hook(DistEvalmAPHook(cfg.data.val))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
    data_loaders = [
        build_dataloader(
            ds, cfg.data.imgs_per_gpu, cfg.data.workers_per_gpu, dist=True)
        for ds in dataset
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, (RPN, CascadeRPN)):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = DATASETS.get(val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
    data_loaders = [
        build_dataloader(
            ds, cfg.data.imgs_per_gpu, cfg.data.workers_per_gpu, dist=True)
        for ds in dataset
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = DATASETS.get(val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    data_loaders = [
        build_dataloader(
            dataset,
            cfg.data.imgs_per_gpu,
            cfg.data.workers_per_gpu,
            dist=True)
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = getattr(datasets, val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs) 

def _dist_train(model, dataset, cfg, validate=False):
    # prepare data loaders
    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
    data_loaders = [
        build_dataloader(
            ds, cfg.data.imgs_per_gpu, cfg.data.workers_per_gpu, dist=True)
        for ds in dataset
    ]
    # put model on gpus
    model = MMDistributedDataParallel(model.cuda())

    # build runner
    optimizer = build_optimizer(model, cfg.optimizer)
    runner = Runner(model, batch_processor, optimizer, cfg.work_dir,
                    cfg.log_level)

    # fp16 setting
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        optimizer_config = Fp16OptimizerHook(**cfg.optimizer_config,
                                             **fp16_cfg)
    else:
        optimizer_config = DistOptimizerHook(**cfg.optimizer_config)

    # register hooks
    runner.register_training_hooks(cfg.lr_config, optimizer_config,
                                   cfg.checkpoint_config, cfg.log_config)
    runner.register_hook(DistSamplerSeedHook())
    # register eval hooks
    if validate:
        val_dataset_cfg = cfg.data.val
        eval_cfg = cfg.get('evaluation', {})
        if isinstance(model.module, RPN):
            # TODO: implement recall hooks for other datasets
            runner.register_hook(
                CocoDistEvalRecallHook(val_dataset_cfg, **eval_cfg))
        else:
            dataset_type = DATASETS.get(val_dataset_cfg.type)
            if issubclass(dataset_type, datasets.CocoDataset):
                runner.register_hook(
                    CocoDistEvalmAPHook(val_dataset_cfg, **eval_cfg))
            else:
                runner.register_hook(
                    DistEvalmAPHook(val_dataset_cfg, **eval_cfg))

    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, cfg.total_epochs)