def single_proc_train()

in tools/train_net.py [0:0]

• 25 lines of code
• 10 McCabe index (conditional complexity)

def single_proc_train():
    """Performs single process training."""

    # Setup logging
    lu.setup_logging()

    # Show the config
    logger.info('Config:\n{}'.format(cfg))
    # Setup tensorboard if provided
    writer_train = None
    writer_eval = None
    ## If use tensorboard
    if cfg.TENSORBOARD and du.is_master_proc() and cfg.RGRAPH.SEED_TRAIN == cfg.RGRAPH.SEED_TRAIN_START:
        comment = ''
        current_time = datetime.now().strftime('%b%d_%H-%M-%S')
        logdir_train = os.path.join(cfg.OUT_DIR,
                                    'runs', current_time + comment + '_train')
        logdir_eval = os.path.join(cfg.OUT_DIR,
                                   'runs', current_time + comment + '_eval')
        if not os.path.exists(logdir_train):
            os.makedirs(logdir_train)
        if not os.path.exists(logdir_eval):
            os.makedirs(logdir_eval)
        writer_train = SummaryWriter(logdir_train)
        writer_eval = SummaryWriter(logdir_eval)

    # Fix the RNG seeds (see RNG comment in core/config.py for discussion)
    np.random.seed(cfg.RGRAPH.SEED_TRAIN)
    torch.manual_seed(cfg.RGRAPH.SEED_TRAIN)
    # Configure the CUDNN backend
    torch.backends.cudnn.benchmark = cfg.CUDNN.BENCHMARK
    # Train the model
    train_model(writer_train, writer_eval, is_master=du.is_master_proc())

    if writer_train is not None and writer_eval is not None:
        writer_train.close()
        writer_eval.close()