def __init__(self, filenames): """Create a `SequenceFileDataset`. `SequenceFileDataset` allows a user to read data from a hadoop sequence file. A sequence file consists of (key value) pairs sequentially. At the moment, `org.apache.hadoop.io.Text` is the only serialization type being supported, and there is no compression support. For example: ```python tf.compat.v1.enable_eager_execution() dataset = tf.contrib.hadoop.SequenceFileDataset("/foo/bar.seq") # Prints the (key, value) pairs inside a hadoop sequence file. for key, value in dataset: print(key, value) ``` Args: filenames: A `tf.string` tensor containing one or more filenames. """ self._filenames = ops.convert_to_tensor(filenames, dtype=dtypes.string, name="filenames") variant_tensor = gen_dataset_ops.sequence_file_dataset( self._filenames, structure.get_flat_tensor_types(self._element_structure)) super(SequenceFileDataset, self).__init__(variant_tensor)
def __init__(self, filenames): """Create a `SequenceFileDataset`. `SequenceFileDataset` allows a user to read data from a hadoop sequence file. A sequence file consists of (key value) pairs sequentially. At the moment, `org.apache.hadoop.io.Text` is the only serialization type being supported, and there is no compression support. For example: ```python tf.compat.v1.enable_eager_execution() dataset = tf.contrib.hadoop.SequenceFileDataset("/foo/bar.seq") # Prints the (key, value) pairs inside a hadoop sequence file. for key, value in dataset: print(key, value) ``` Args: filenames: A `tf.string` tensor containing one or more filenames. """ self._filenames = ops.convert_to_tensor( filenames, dtype=dtypes.string, name="filenames") variant_tensor = gen_dataset_ops.sequence_file_dataset( self._filenames, self._element_structure._flat_types) # pylint: disable=protected-access super(SequenceFileDataset, self).__init__(variant_tensor)
def __init__(self, filenames): """Create a `SequenceFileDataset`. `SequenceFileDataset` allows a user to read data from a hadoop sequence file. A sequence file consists of (key value) pairs sequentially. At the moment, `org.apache.hadoop.io.Text` is the only serialization type being supported, and there is no compression support. For example: ```python dataset = tf.contrib.hadoop.SequenceFileDataset("/foo/bar.seq") iterator = dataset.make_one_shot_iterator() next_element = iterator.get_next() # Prints the (key, value) pairs inside a hadoop sequence file. while True: try: print(sess.run(next_element)) except tf.errors.OutOfRangeError: break ``` Args: filenames: A `tf.string` tensor containing one or more filenames. """ self._filenames = ops.convert_to_tensor(filenames, dtype=dtypes.string, name="filenames") variant_tensor = gen_dataset_ops.sequence_file_dataset( self._filenames, self._element_structure._flat_types) # pylint: disable=protected-access super(SequenceFileDataset, self).__init__(variant_tensor)
def _as_variant_tensor(self): return gen_dataset_ops.sequence_file_dataset( self._filenames, self._element_structure._flat_types) # pylint: disable=protected-access
def _as_variant_tensor(self): return gen_dataset_ops.sequence_file_dataset( self._filenames, nest.flatten(self.output_types))
def _as_variant_tensor(self): return gen_dataset_ops.sequence_file_dataset( self._filenames, nest.flatten(self.output_types))