gram.py 文件源码

def padMatrix(seqs, labels, options):
    lengths = np.array([len(seq) for seq in seqs]) - 1
    n_samples = len(seqs)
    maxlen = np.max(lengths)

    x = np.zeros((maxlen, n_samples, options['inputDimSize'])).astype(config.floatX)
    y = np.zeros((maxlen, n_samples, options['numClass'])).astype(config.floatX)
    mask = np.zeros((maxlen, n_samples)).astype(config.floatX)

    for idx, (seq, lseq) in enumerate(zip(seqs,labels)):
        for xvec, subseq in zip(x[:,idx,:], seq[:-1]): xvec[subseq] = 1.
        for yvec, subseq in zip(y[:,idx,:], lseq[1:]): yvec[subseq] = 1.
        mask[:lengths[idx], idx] = 1.

    lengths = np.array(lengths, dtype=config.floatX)

    return x, y, mask, lengths