Function train

tools/train_net.py:387–538

Train a video model for many epochs on train set and evaluate it on val set. Args: cfg (CfgNode): configs. Details can be found in slowfast/config/defaults.py

(cfg)

def train(cfg):
    """
    Train a video model for many epochs on train set and evaluate it on val set.
    Args:
        cfg (CfgNode): configs. Details can be found in
            slowfast/config/defaults.py
    """
    # Set up environment.
    du.init_distributed_training(cfg)
    # Set random seed from configs.
    np.random.seed(cfg.RNG_SEED)
    torch.manual_seed(cfg.RNG_SEED)

    # Setup logging format.
    logging.setup_logging(cfg.OUTPUT_DIR)

    # Init multigrid.
    multigrid = None
    if cfg.MULTIGRID.LONG_CYCLE or cfg.MULTIGRID.SHORT_CYCLE:
        multigrid = MultigridSchedule()
        cfg = multigrid.init_multigrid(cfg)
        if cfg.MULTIGRID.LONG_CYCLE:
            cfg, _ = multigrid.update_long_cycle(cfg, cur_epoch=0)
    # Print config.
    logger.info("Train with config:")
    logger.info(pprint.pformat(cfg))

    # Loss scaler
    loss_scaler = NativeScaler()

    # Build the video model and print model statistics.
    model = build_model(cfg)
    if du.is_master_proc() and cfg.LOG_MODEL_INFO:
        misc.log_model_info(model, cfg, use_train_input=True)

    # Construct the optimizer.
    optimizer = optim.construct_optimizer(model, cfg)

    # Load a checkpoint to resume training if applicable.
    start_epoch = cu.load_train_checkpoint(cfg, model, optimizer, loss_scaler)

    # Create the video train and val loaders.
    train_loader = loader.construct_loader(cfg, "train")
    val_loader = loader.construct_loader(cfg, "val")
    precise_bn_loader = (
        loader.construct_loader(cfg, "train", is_precise_bn=True)
        if cfg.BN.USE_PRECISE_STATS
        else None
    )

    # Create meters.
    if cfg.DETECTION.ENABLE:
        train_meter = AVAMeter(len(train_loader), cfg, mode="train")
        val_meter = AVAMeter(len(val_loader), cfg, mode="val")
    else:
        train_meter = TrainMeter(len(train_loader), cfg)
        val_meter = ValMeter(len(val_loader), cfg)