data.py 文件源码

def cli_render(input, output, size):
    '''Render a JSONlines dataset to numpy arrays, saved in an HDF5 file.
    '''
    chars = []
    images = []
    for line in input:
        datum = json.loads(line)
        chars.append(datum['target'])
        images.append(render(
            [np.array(s) for s in datum['strokes']],
            size))

    vocab = list(sorted(set(chars)))
    char_to_index = {ch: y for y, ch in enumerate(vocab)}

    with h5py.File(output, 'a') as f:
        str_dt = h5py.special_dtype(vlen=str)
        f.require_dataset(
            'vocab', (len(vocab),), dtype=str_dt
        )[...] = vocab
        f.require_dataset(
            'x', shape=(len(images), size, size), dtype=np.float32
        )[...] = np.array(images)
        f.require_dataset(
            'y', shape=(len(chars),), dtype=np.int
        )[...] = np.array([char_to_index[ch] for ch in chars])