def train()

in sagemaker/distributed-training/train_pytorch_single_maskrcnn.py [0:0]

• 53 lines of code
• 7 McCabe index (conditional complexity)

def train(cfg, args):
    model = build_detection_model(cfg)
    device = torch.device(cfg.MODEL.DEVICE)
    model.to(device)

    optimizer = make_optimizer(cfg, model)
    scheduler = make_lr_scheduler(cfg, optimizer)

    if use_amp:
        # Initialize mixed-precision training
        use_mixed_precision = cfg.DTYPE == "float16"

        amp_opt_level = 'O1' if use_mixed_precision else 'O0'
        model, optimizer = amp.initialize(model, optimizer, opt_level=amp_opt_level)

    print("model parameter size: ", sum(p.numel() for p in model.parameters() if p.requires_grad))
    arguments = {}
    arguments["iteration"] = 0

    output_dir = cfg.OUTPUT_DIR

    # Save model
    save_to_disk = True
    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