Function run_epoch

tensorlayer/utils.py:612–654

Run a given non time-series network by the given cost function, test data, batch_size etc. for one epoch. Parameters ---------- network : TensorLayer Model the network to be trained. X : numpy.array The input of training data y : numpy.array The targe

(network, X, y, cost=None, acc=None, batch_size=100, shuffle=False)

def run_epoch(network, X, y, cost=None, acc=None, batch_size=100, shuffle=False):
    """Run a given non time-series network by the given cost function, test data, batch_size etc.
    for one epoch.

    Parameters
    ----------
    network : TensorLayer Model
        the network to be trained.
    X : numpy.array
        The input of training data
    y : numpy.array
        The target of training data
    cost : TensorLayer or TensorFlow loss function
        Metric for loss function, e.g tl.cost.cross_entropy.
    acc : TensorFlow/numpy expression or None
        Metric for accuracy or others. If None, would not print the information.
    batch_size : int
        The batch size for training and evaluating.
    shuffle : boolean
        Indicating whether to shuffle the dataset in training.

    Returns
    -------
    loss_ep : Tensor. Average loss of this epoch. None if 'cost' is not given.
    acc_ep : Tensor. Average accuracy(metric) of this epoch. None if 'acc' is not given.
    n_step : int. Number of iterations taken in this epoch.
    """
    network.eval()
    loss_ep = 0
    acc_ep = 0
    n_step = 0
    for X_batch, y_batch in tl.iterate.minibatches(X, y, batch_size, shuffle=shuffle):
        _loss, _acc = _run_step(network, X_batch, y_batch, cost=cost, acc=acc)
        if cost is not None:
            loss_ep += _loss
        if acc is not None:
            acc_ep += _acc
        n_step += 1

    loss_ep = loss_ep / n_step if cost is not None else None
    acc_ep = acc_ep / n_step if acc is not None else None

    return loss_ep, acc_ep, n_step


@tf.function