distributed_training/train_pytorch_single_maskrcnn.py [127:211]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    checkpointer = DetectronCheckpointer(
        cfg, model, optimizer, scheduler, output_dir, save_to_disk
    )
    extra_checkpoint_data = checkpointer.load(cfg.MODEL.WEIGHT)
    arguments.update(extra_checkpoint_data)

    data_loader, iters_per_epoch = make_data_loader(
        cfg,
        is_train=True,
        is_distributed=args.distributed,
        start_iter=arguments["iteration"],
        data_dir = args.data_dir
    )
    checkpoint_period = cfg.SOLVER.CHECKPOINT_PERIOD

    # set the callback function to evaluate and potentially
    # early exit each epoch
    if cfg.PER_EPOCH_EVAL:
        per_iter_callback_fn = functools.partial(
            mlperf_test_early_exit,
            iters_per_epoch=iters_per_epoch,
            tester=functools.partial(test, cfg=cfg),
            model=model,
            distributed=args.distributed,
            min_bbox_map=cfg.MIN_BBOX_MAP,
            min_segm_map=cfg.MIN_MASK_MAP)
    else:
        per_iter_callback_fn = None
    do_train(
        model,
        data_loader,
        optimizer,
        scheduler,
        checkpointer,
        device,
        checkpoint_period,
        arguments,
        use_amp,
        cfg,
        per_iter_end_callback_fn=per_iter_callback_fn,
    )

    return model


def test_model(cfg, model, args):
    if args.distributed:
        model = model.module
    torch.cuda.empty_cache()  # TODO check if it helps
    iou_types = ("bbox",)
    if cfg.MODEL.MASK_ON:
        iou_types = iou_types + ("segm",)
    output_folders = [None] * len(cfg.DATASETS.TEST)
    dataset_names = cfg.DATASETS.TEST
    if cfg.OUTPUT_DIR:
        for idx, dataset_name in enumerate(dataset_names):
            output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
            mkdir(output_folder)
            output_folders[idx] = output_folder
    data_loaders_val = make_data_loader(cfg, is_train=False, is_distributed=args.distributed,
                                        data_dir = args.data_dir)
    for output_folder, dataset_name, data_loader_val in zip(output_folders, dataset_names, data_loaders_val):
        inference(
            model,
            data_loader_val,
            dataset_name=dataset_name,
            iou_types=iou_types,
            box_only=cfg.MODEL.RPN_ONLY,
            device=cfg.MODEL.DEVICE,
            expected_results=cfg.TEST.EXPECTED_RESULTS,
            expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
            output_folder=output_folder,
        )
        #synchronize()


def main():
    parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
    parser.add_argument(
        "--config-file",
        default="",
        metavar="FILE",
        help="path to config file",
        type=str,
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



distributed_training/train_pytorch_smdataparallel_maskrcnn.py [144:228]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    checkpointer = DetectronCheckpointer(
        cfg, model, optimizer, scheduler, output_dir, save_to_disk
    )
    extra_checkpoint_data = checkpointer.load(cfg.MODEL.WEIGHT)
    arguments.update(extra_checkpoint_data)

    data_loader, iters_per_epoch = make_data_loader(
        cfg,
        is_train=True,
        is_distributed=args.distributed,
        start_iter=arguments["iteration"],
        data_dir = args.data_dir
    )
    checkpoint_period = cfg.SOLVER.CHECKPOINT_PERIOD

    # set the callback function to evaluate and potentially
    # early exit each epoch
    if cfg.PER_EPOCH_EVAL:
        per_iter_callback_fn = functools.partial(
            mlperf_test_early_exit,
            iters_per_epoch=iters_per_epoch,
            tester=functools.partial(test, cfg=cfg),
            model=model,
            distributed=args.distributed,
            min_bbox_map=cfg.MIN_BBOX_MAP,
            min_segm_map=cfg.MIN_MASK_MAP)
    else:
        per_iter_callback_fn = None
    do_train(
        model,
        data_loader,
        optimizer,
        scheduler,
        checkpointer,
        device,
        checkpoint_period,
        arguments,
        use_amp,
        cfg,
        per_iter_end_callback_fn=per_iter_callback_fn,
    )

    return model


def test_model(cfg, model, args):
    if args.distributed:
        model = model.module
    torch.cuda.empty_cache()  # TODO check if it helps
    iou_types = ("bbox",)
    if cfg.MODEL.MASK_ON:
        iou_types = iou_types + ("segm",)
    output_folders = [None] * len(cfg.DATASETS.TEST)
    dataset_names = cfg.DATASETS.TEST
    if cfg.OUTPUT_DIR:
        for idx, dataset_name in enumerate(dataset_names):
            output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
            mkdir(output_folder)
            output_folders[idx] = output_folder
    data_loaders_val = make_data_loader(cfg, is_train=False, is_distributed=args.distributed,
                                        data_dir = args.data_dir)
    for output_folder, dataset_name, data_loader_val in zip(output_folders, dataset_names, data_loaders_val):
        inference(
            model,
            data_loader_val,
            dataset_name=dataset_name,
            iou_types=iou_types,
            box_only=cfg.MODEL.RPN_ONLY,
            device=cfg.MODEL.DEVICE,
            expected_results=cfg.TEST.EXPECTED_RESULTS,
            expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
            output_folder=output_folder,
        )
        #synchronize()


def main():
    parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
    parser.add_argument(
        "--config-file",
        default="",
        metavar="FILE",
        help="path to config file",
        type=str,
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -