Function minibatch

numpy_ml/neural_nets/utils/utils.py:8–43

Compute the minibatch indices for a training dataset. Parameters ---------- X : :py:class:`ndarray ` of shape `(N, \*)` The dataset to divide into minibatches. Assumes the first dimension represents the number of training examples. batchsize : int

(X, batchsize=256, shuffle=True)

def minibatch(X, batchsize=256, shuffle=True):
    """
    Compute the minibatch indices for a training dataset.

    Parameters
    ----------
    X : :py:class:`ndarray <numpy.ndarray>` of shape `(N, \*)`
        The dataset to divide into minibatches. Assumes the first dimension
        represents the number of training examples.
    batchsize : int
        The desired size of each minibatch. Note, however, that if ``X.shape[0] %
        batchsize > 0`` then the final batch will contain fewer than batchsize
        entries. Default is 256.
    shuffle : bool
        Whether to shuffle the entries in the dataset before dividing into
        minibatches. Default is True.

    Returns
    -------
    mb_generator : generator
        A generator which yields the indices into X for each batch
    n_batches: int
        The number of batches
    """
    N = X.shape[0]
    ix = np.arange(N)
    n_batches = int(np.ceil(N / batchsize))

    if shuffle:
        np.random.shuffle(ix)

    def mb_generator():
        for i in range(n_batches):
            yield ix[i * batchsize : (i + 1) * batchsize]

    return mb_generator(), n_batches


#######################################################################