data.py 文件源码

def __init__(self, dataset, hdf=None, dtype=None, shape=None):
    super(Hdf5Data, self).__init__()
    raise Exception("Hdf5Data is under-maintanance!")
    # default chunks size is 32 (reduce complexity of the works)
    self._chunk_size = 32
    if isinstance(hdf, str):
      hdf = open_hdf5(hdf)
    if hdf is None and not isinstance(dataset, h5py.Dataset):
      raise ValueError('Cannot initialize dataset without hdf file')

    if isinstance(dataset, h5py.Dataset):
      self._data = dataset
      self._hdf = dataset.file
    else:
      if dataset not in hdf: # not created dataset
        if dtype is None or shape is None:
          raise ValueError('dtype and shape must be specified if '
                           'dataset has not created in hdf5 file.')
        shape = tuple([0 if i is None else i for i in shape])
        hdf.create_dataset(dataset, dtype=dtype,
            chunks=_get_chunk_size(shape, self._chunk_size),
            shape=shape, maxshape=(None, ) + shape[1:])

      self._data = hdf[dataset]
      if shape is not None and self._data[0].shape[1:] != shape[1:]:
        raise ValueError('Shape mismatch between predefined dataset '
                         'and given shape, {} != {}'
                         ''.format(shape, self._data[0].shape))
      self._hdf = hdf

  # ==================== properties ==================== #