Python tensorflow.sparse_tensor_to_dense() Examples

def to_dense(tensor):
    """Converts a sparse tensor into a dense tensor and returns it.

    # Arguments
        tensor: A tensor instance (potentially sparse).

    # Returns
        A dense tensor.

    # Examples
    ```python
        >>> from keras import backend as K
        >>> b = K.placeholder((2, 2), sparse=True)
        >>> print(K.is_sparse(b))
        True
        >>> c = K.to_dense(b)
        >>> print(K.is_sparse(c))
        False
    ```
    """
    if is_sparse(tensor):
        return tf.sparse_tensor_to_dense(tensor)
    else:
        return tensor 

def multiple_content_lookup(content, vocab_table, ids, name=None):
    """

    :param content:
    :param vocab_table:
    :param ids:
    :param name:
    :return: 2-D [batch_size, max_length_in_batch] content id matrix,
             1-D [batch_size] content len vector
    """
    with tf.name_scope(name, 'multiple_content_lookup', [content, vocab_table, ids]):
        content_list = tf.nn.embedding_lookup(content, ids)

        extracted_sparse_content = tf.string_split(content_list, delimiter=' ')

        sparse_content = tf.SparseTensor(indices=extracted_sparse_content.indices,
                                         values=vocab_table.lookup(extracted_sparse_content.values),
                                         dense_shape=extracted_sparse_content.dense_shape)

        extracted_content_ids = tf.sparse_tensor_to_dense(sparse_content,
                                                          default_value=0, name='dense_content')
        extracted_content_len = tf.reduce_sum(tf.cast(tf.not_equal(extracted_content_ids, 0), tf.int32), axis=-1)

        return extracted_content_ids, extracted_content_len 

def recon_wav_file(self, wav_files, txt_labels):
        self.audio_features, self.audio_features_len, text_vector, text_vector_len = utils.get_audio_mfcc_features(
            None,
            wav_files,
            self.hyparam.n_input,
            self.hyparam.n_context,
            self.word_num_map,
            txt_labels,
            specgram_type=self.hyparam.specgram_type)
        self.sparse_labels = utils.sparse_tuple_from(text_vector)
        prob, d, train_ler = self.sess.run([self.prob, self.decoded[0], self.label_err], feed_dict=self.get_feed_dict(dropout=1.0))
        if self.hyparam.use_lm_decoder:
            result_transcripts = self.lm_decode(prob)
        else:
            dense_decoded = tf.sparse_tensor_to_dense(d, default_value=-1).eval(session=self.sess)
            result_transcripts = utils.trans_array_to_text_ch(dense_decoded[0], self.words).encode('utf-8')
#        print "Transcript: ", result_transcripts
        return result_transcripts
         
#        self.sess.close() 

def process_input(self, session, inputs, input_seq_lengths, run_options=None, run_metadata=None):
        """
        Returns:
          Next char
        """
        input_feed = {self.inputs_ph: np.array(inputs), self.input_seq_lengths_ph: np.array(input_seq_lengths)}

        if (self.input_keep_prob_ph is not None) and (self.output_keep_prob_ph is not None):
            input_feed[self.input_keep_prob_ph] = 1.0
            input_feed[self.output_keep_prob_ph] = 1.0

        output_feed = [self.prediction]
        outputs = session.run(output_feed, input_feed, options=run_options, run_metadata=run_metadata)
        predictions = session.run(tf.sparse_tensor_to_dense(outputs[0], default_value=self.num_labels,
                                                            validate_indices=True),
                                  options=run_options, run_metadata=run_metadata)
        return predictions 

def process_input(self, session, inputs, input_seq_lengths, run_options=None, run_metadata=None):
        """
        Returns:
          Output vector
        """
        input_feed = {self.inputs_ph: np.array(inputs), self.input_seq_lengths_ph: np.array(input_seq_lengths)}

        if (self.input_keep_prob_ph is not None) and (self.output_keep_prob_ph is not None):
            input_feed[self.input_keep_prob_ph] = 1.0
            input_feed[self.output_keep_prob_ph] = 1.0

        output_feed = [self.prediction]
        outputs = session.run(output_feed, input_feed, options=run_options, run_metadata=run_metadata)
        predictions = session.run(tf.sparse_tensor_to_dense(outputs[0], default_value=self.num_labels,
                                                            validate_indices=True),
                                  options=run_options, run_metadata=run_metadata)
        return predictions 

def _reshape_keypoints(self, keys_to_tensors):
    """Reshape keypoints.

    The instance segmentation masks are reshaped to [num_instances,
    num_keypoints, 2].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, num_keypoints, 2] with values
        in {0, 1}.
    """
    y = keys_to_tensors['image/object/keypoint/y']
    if isinstance(y, tf.SparseTensor):
      y = tf.sparse_tensor_to_dense(y)
    y = tf.expand_dims(y, 1)
    x = keys_to_tensors['image/object/keypoint/x']
    if isinstance(x, tf.SparseTensor):
      x = tf.sparse_tensor_to_dense(x)
    x = tf.expand_dims(x, 1)
    keypoints = tf.concat([y, x], 1)
    keypoints = tf.reshape(keypoints, [-1, self._num_keypoints, 2])
    return keypoints 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, height, width] with values
        in {0, 1}.
    """
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)
    masks = keys_to_tensors['image/object/mask']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    masks = tf.reshape(tf.to_float(tf.greater(masks, 0.0)), to_shape)
    return tf.cast(masks, tf.float32) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, height, width] with values
        in {0, 1}.
    """
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)
    masks = keys_to_tensors['image/object/mask']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    masks = tf.reshape(tf.to_float(tf.greater(masks, 0.0)), to_shape)
    return tf.cast(masks, tf.float32) 

def _reshape_keypoints(self, keys_to_tensors):
    """Reshape keypoints.

    The instance segmentation masks are reshaped to [num_instances,
    num_keypoints, 2].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, num_keypoints, 2] with values
        in {0, 1}.
    """
    y = keys_to_tensors['image/object/keypoint/y']
    if isinstance(y, tf.SparseTensor):
      y = tf.sparse_tensor_to_dense(y)
    y = tf.expand_dims(y, 1)
    x = keys_to_tensors['image/object/keypoint/x']
    if isinstance(x, tf.SparseTensor):
      x = tf.sparse_tensor_to_dense(x)
    x = tf.expand_dims(x, 1)
    keypoints = tf.concat([y, x], 1)
    keypoints = tf.reshape(keypoints, [-1, self._num_keypoints, 2])
    return keypoints 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width] and cast to boolean type to save memory.

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D boolean tensor of shape [num_instances, height, width].
    """
    masks = keys_to_tensors['image/segmentation/object']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)

    return tf.cast(tf.reshape(masks, to_shape), tf.bool) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width] and cast to boolean type to save memory.

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D boolean tensor of shape [num_instances, height, width].
    """
    masks = keys_to_tensors['image/segmentation/object']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)

    return tf.cast(tf.reshape(masks, to_shape), tf.bool) 

def entity_content_embedding_lookup(entities, content, content_len, vocab_table, word_embedding, str_pad, name=None):
    """ Lookup entity word embeddings given a flatten 1-D entity id list and content lookup table

    :param entities: Must be a 1-D entity vector
    :param content:
    :param content_len:
    :param vocab_table:
    :param word_embedding:
    :param str_pad:
    :param name:
    :return:
    """
    with tf.device('/cpu:0'):
        with tf.name_scope(name, 'entity_content_lookup',
                           [entities, content, content_len, vocab_table, word_embedding]):
            ent_content = tf.string_split(tf.nn.embedding_lookup(content, entities, name='ent_content'), delimiter=' ')
            content_len = tf.nn.embedding_lookup(content_len, entities, name='ent_content_len')
            ent_content_dense = tf.sparse_tensor_to_dense(ent_content,
                                                          default_value=str_pad,
                                                          name='ent_content_dense')
            ent_embedding = tf.nn.embedding_lookup(word_embedding,
                                                   vocab_table.lookup(ent_content_dense,
                                                                      name='ent_content_ids'))

            return ent_embedding, content_len 

def get_label(self, text, null_character=u'\u2591'):
    """ Returns the ids of the corresponding text,

        Args:
          text: a tensor with shape [batch_size, lexicon_size]
                         and type string
          null_character: a unicode character used to replace '<null>'
          character. the default value is a light shade block '░'.
    """
    batch_size = text.shape[0].value
    lexicon_size = text.shape[1].value
    text = tf.reshape(text, [-1])
    sp_text = tf.string_split(text, delimiter='')
    sp_text = tf.sparse_reset_shape(sp_text, [batch_size*lexicon_size,
                                              self.max_sequence_length])
    sp_text = tf.sparse_tensor_to_dense(sp_text, default_value=null_character)
    ids = self.invert_table.lookup(sp_text)
    ids = tf.reshape(ids, [batch_size, lexicon_size, self.max_sequence_length])
    return tf.to_int32(ids) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, height, width] with values
        in {0, 1}.
    """
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)
    masks = keys_to_tensors['image/object/mask']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    masks = tf.reshape(tf.to_float(tf.greater(masks, 0.0)), to_shape)
    return tf.cast(masks, tf.float32) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, height, width] with values
        in {0, 1}.
    """
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)
    masks = keys_to_tensors['image/object/mask']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    masks = tf.reshape(tf.to_float(tf.greater(masks, 0.0)), to_shape)
    return tf.cast(masks, tf.float32) 

def _reshape_keypoints(self, keys_to_tensors):
    """Reshape keypoints.

    The instance segmentation masks are reshaped to [num_instances,
    num_keypoints, 2].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, num_keypoints, 2] with values
        in {0, 1}.
    """
    y = keys_to_tensors['image/object/keypoint/y']
    if isinstance(y, tf.SparseTensor):
      y = tf.sparse_tensor_to_dense(y)
    y = tf.expand_dims(y, 1)
    x = keys_to_tensors['image/object/keypoint/x']
    if isinstance(x, tf.SparseTensor):
      x = tf.sparse_tensor_to_dense(x)
    x = tf.expand_dims(x, 1)
    keypoints = tf.concat([y, x], 1)
    keypoints = tf.reshape(keypoints, [-1, self._num_keypoints, 2])
    return keypoints 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, height, width] with values
        in {0, 1}.
    """
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)
    masks = keys_to_tensors['image/object/mask']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    masks = tf.reshape(tf.to_float(tf.greater(masks, 0.0)), to_shape)
    return tf.cast(masks, tf.float32) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width] and cast to boolean type to save memory.

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, height, width] with values
        in {0, 1}.
    """
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)
    masks = keys_to_tensors['image/object/mask']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    masks = tf.reshape(tf.to_float(tf.greater(masks, 0.0)), to_shape)
    return tf.cast(masks, tf.float32) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width] and cast to boolean type to save memory.

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D boolean tensor of shape [num_instances, height, width].
    """
    masks = keys_to_tensors['image/segmentation/object']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)

    return tf.cast(tf.reshape(masks, to_shape), tf.bool) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width] and cast to boolean type to save memory.

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D boolean tensor of shape [num_instances, height, width].
    """
    masks = keys_to_tensors['image/segmentation/object']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)

    return tf.cast(tf.reshape(masks, to_shape), tf.bool) 

def testRandom(self):
    np.random.seed(1618)
    shapes = [(13,), (6, 8), (1, 7, 1)]
    for shape in shapes:
      for dtype in [np.int32, np.int64, np.float16, np.float32, np.float64]:
        a_np = np.random.randn(*shape).astype(dtype)
        b_np = np.random.randn(*shape).astype(dtype)
        sp_a, unused_a_nnz = _sparsify(a_np, thresh=-.5)
        sp_b, unused_b_nnz = _sparsify(b_np, thresh=-.5)

        with self.test_session(use_gpu=False):
          maximum_tf = tf.sparse_maximum(sp_a, sp_b)
          maximum_tf_densified = tf.sparse_tensor_to_dense(maximum_tf).eval()
          minimum_tf = tf.sparse_minimum(sp_a, sp_b)
          minimum_tf_densified = tf.sparse_tensor_to_dense(minimum_tf).eval()

          a_densified = tf.sparse_tensor_to_dense(sp_a).eval()
          b_densified = tf.sparse_tensor_to_dense(sp_b).eval()

        self.assertAllEqual(
            np.maximum(a_densified, b_densified), maximum_tf_densified)
        self.assertAllEqual(
            np.minimum(a_densified, b_densified), minimum_tf_densified) 

def testCwiseDivAndMul(self):
    np.random.seed(1618)
    sp_shapes = [(10, 10, 10), (5, 5), (1618,), (3, 3, 7)]
    dense_shapes = [(10, 10, 1), (5, 5), (1,), (1, 7)]

    with self.test_session(use_gpu=False):
      for dtype in [np.float32, np.float64, np.int32, np.int64]:
        for sp_shape, dense_shape in zip(sp_shapes, dense_shapes):
          sp_vals_np = np.random.rand(*sp_shape).astype(dtype) + 1
          dense_vals_np = np.random.rand(*dense_shape).astype(dtype) + 1
          sp_t, unused_nnz = _sparsify(sp_vals_np, thresh=1.5)
          sp_t_densified = sparse_ops.sparse_tensor_to_dense(sp_t).eval()
          dense_t = tf.constant(dense_vals_np)

          self._check(sp_t / dense_t, sp_t_densified / dense_vals_np, sp_t)
          # Check commutative.
          self._check(sp_t * dense_t, sp_t_densified * dense_vals_np, sp_t)
          self._check(dense_t * sp_t, sp_t_densified * dense_vals_np, sp_t)

          if dtype in [np.int32, np.int64]:
            res = sp_t / dense_t  # should invoke "__truediv__"
            self.assertEqual(res.values.eval().dtype, np.float64) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width] and cast to boolean type to save memory.

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, height, width] with values
        in {0, 1}.
    """
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)
    masks = keys_to_tensors['image/object/mask']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    masks = tf.reshape(tf.to_float(tf.greater(masks, 0.0)), to_shape)
    return tf.cast(masks, tf.float32) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, height, width] with values
        in {0, 1}.
    """
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)
    masks = keys_to_tensors['image/object/mask']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    masks = tf.reshape(tf.to_float(tf.greater(masks, 0.0)), to_shape)
    return tf.cast(masks, tf.float32) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, height, width] with values
        in {0, 1}.
    """
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)
    masks = keys_to_tensors['image/object/mask']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    masks = tf.reshape(tf.to_float(tf.greater(masks, 0.0)), to_shape)
    return tf.cast(masks, tf.float32) 

def _reshape_keypoints(self, keys_to_tensors):
    """Reshape keypoints.

    The instance segmentation masks are reshaped to [num_instances,
    num_keypoints, 2].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, num_keypoints, 2] with values
        in {0, 1}.
    """
    y = keys_to_tensors['image/object/keypoint/y']
    if isinstance(y, tf.SparseTensor):
      y = tf.sparse_tensor_to_dense(y)
    y = tf.expand_dims(y, 1)
    x = keys_to_tensors['image/object/keypoint/x']
    if isinstance(x, tf.SparseTensor):
      x = tf.sparse_tensor_to_dense(x)
    x = tf.expand_dims(x, 1)
    keypoints = tf.concat([y, x], 1)
    keypoints = tf.reshape(keypoints, [-1, self._num_keypoints, 2])
    return keypoints 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width] and cast to boolean type to save memory.

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D boolean tensor of shape [num_instances, height, width].
    """
    masks = keys_to_tensors['image/segmentation/object']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)

    return tf.cast(tf.reshape(masks, to_shape), tf.bool) 

def _reshape_instance_masks(self, keys_to_tensors):
    """Reshape instance segmentation masks.

    The instance segmentation masks are reshaped to [num_instances, height,
    width] and cast to boolean type to save memory.

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D boolean tensor of shape [num_instances, height, width].
    """
    masks = keys_to_tensors['image/segmentation/object']
    if isinstance(masks, tf.SparseTensor):
      masks = tf.sparse_tensor_to_dense(masks)
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    to_shape = tf.cast(tf.stack([-1, height, width]), tf.int32)

    return tf.cast(tf.reshape(masks, to_shape), tf.bool) 

def _reshape_keypoints(self, keys_to_tensors):
    """Reshape keypoints.

    The instance segmentation masks are reshaped to [num_instances,
    num_keypoints, 2].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, num_keypoints, 2] with values
        in {0, 1}.
    """
    y = keys_to_tensors['image/object/keypoint/y']
    if isinstance(y, tf.SparseTensor):
      y = tf.sparse_tensor_to_dense(y)
    y = tf.expand_dims(y, 1)
    x = keys_to_tensors['image/object/keypoint/x']
    if isinstance(x, tf.SparseTensor):
      x = tf.sparse_tensor_to_dense(x)
    x = tf.expand_dims(x, 1)
    keypoints = tf.concat([y, x], 1)
    keypoints = tf.reshape(keypoints, [-1, self._num_keypoints, 2])
    return keypoints 

def _decode_png_instance_masks(self, keys_to_tensors):
    """Decode PNG instance segmentation masks and stack into dense tensor.

    The instance segmentation masks are reshaped to [num_instances, height,
    width].

    Args:
      keys_to_tensors: a dictionary from keys to tensors.

    Returns:
      A 3-D float tensor of shape [num_instances, height, width] with values
        in {0, 1}.
    """

    def decode_png_mask(image_buffer):
      image = tf.squeeze(
          tf.image.decode_image(image_buffer, channels=1), axis=2)
      image.set_shape([None, None])
      image = tf.to_float(tf.greater(image, 0))
      return image

    png_masks = keys_to_tensors['image/object/mask']
    height = keys_to_tensors['image/height']
    width = keys_to_tensors['image/width']
    if isinstance(png_masks, tf.SparseTensor):
      png_masks = tf.sparse_tensor_to_dense(png_masks, default_value='')
    return tf.cond(
        tf.greater(tf.size(png_masks), 0),
        lambda: tf.map_fn(decode_png_mask, png_masks, dtype=tf.float32),
        lambda: tf.zeros(tf.to_int32(tf.stack([0, height, width]))))