Python tensorflow.unstack() Examples

def stackedRNN(self, x, dropout, scope, embedding_size, sequence_length, hidden_units):
        n_hidden=hidden_units
        n_layers=3
        # Prepare data shape to match `static_rnn` function requirements
        x = tf.unstack(tf.transpose(x, perm=[1, 0, 2]))
        # print(x)
        # Define lstm cells with tensorflow
        # Forward direction cell

        with tf.name_scope("fw"+scope),tf.variable_scope("fw"+scope):
            stacked_rnn_fw = []
            for _ in range(n_layers):
                fw_cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden, forget_bias=1.0, state_is_tuple=True)
                lstm_fw_cell = tf.contrib.rnn.DropoutWrapper(fw_cell,output_keep_prob=dropout)
                stacked_rnn_fw.append(lstm_fw_cell)
            lstm_fw_cell_m = tf.nn.rnn_cell.MultiRNNCell(cells=stacked_rnn_fw, state_is_tuple=True)

            outputs, _ = tf.nn.static_rnn(lstm_fw_cell_m, x, dtype=tf.float32)
        return outputs[-1] 

def _CrossConv(self, encoded_images):
    """Apply the motion kernel on the encoded_images."""
    cross_conved_images = []
    kernels = tf.split(axis=3, num_or_size_splits=4, value=self.kernel)
    for (i, encoded_image) in enumerate(encoded_images):
      with tf.variable_scope('cross_conv_%d' % i):
        kernel = kernels[i]

        encoded_image = tf.unstack(encoded_image, axis=0)
        kernel = tf.unstack(kernel, axis=0)
        assert len(encoded_image) == len(kernel)
        assert len(encoded_image) == self.params['batch_size']
        conved_image = []
        for j in xrange(len(encoded_image)):
          conved_image.append(self._CrossConvHelper(
              encoded_image[j], kernel[j]))
        cross_conved_images.append(tf.concat(axis=0, values=conved_image))
        sys.stderr.write('cross_conved shape: %s\n' %
                         cross_conved_images[-1].get_shape())
    return cross_conved_images 

def clip_to_window(keypoints, window, scope=None):
  """Clips keypoints to a window.

  This op clips any input keypoints to a window.

  Args:
    keypoints: a tensor of shape [num_instances, num_keypoints, 2]
    window: a tensor of shape [4] representing the [y_min, x_min, y_max, x_max]
      window to which the op should clip the keypoints.
    scope: name scope.

  Returns:
    new_keypoints: a tensor of shape [num_instances, num_keypoints, 2]
  """
  with tf.name_scope(scope, 'ClipToWindow'):
    y, x = tf.split(value=keypoints, num_or_size_splits=2, axis=2)
    win_y_min, win_x_min, win_y_max, win_x_max = tf.unstack(window)
    y = tf.maximum(tf.minimum(y, win_y_max), win_y_min)
    x = tf.maximum(tf.minimum(x, win_x_max), win_x_min)
    new_keypoints = tf.concat([y, x], 2)
    return new_keypoints 

def unroll(self, actions, env_outputs, core_state):
    """Manual implementation of the network unroll."""
    _, _, done, _ = env_outputs

    torso_outputs = snt.BatchApply(self._torso)((actions, env_outputs))

    # Note, in this implementation we can't use CuDNN RNN to speed things up due
    # to the state reset. This can be XLA-compiled (LSTMBlockCell needs to be
    # changed to implement snt.LSTMCell).
    initial_core_state = self._core.zero_state(tf.shape(actions)[1], tf.float32)
    core_output_list = []
    for input_, d in zip(tf.unstack(torso_outputs), tf.unstack(done)):
      # If the episode ended, the core state should be reset before the next.
      core_state = nest.map_structure(
          functools.partial(tf.where, d), initial_core_state, core_state)
      core_output, core_state = self._core(input_, core_state)
      core_output_list.append(core_output)

    return snt.BatchApply(self._head)(tf.stack(core_output_list)), core_state 

def __init__(self, num_experts, gates):
    """Create a SparseDispatcher.

    Args:
      num_experts: an integer.
      gates: a `Tensor` of shape `[batch_size, num_experts]`.

    Returns:
      a SparseDispatcher
    """
    self._gates = gates
    self._num_experts = num_experts

    where = tf.to_int32(tf.where(tf.transpose(gates) > 0))
    self._expert_index, self._batch_index = tf.unstack(where, num=2, axis=1)
    self._part_sizes_tensor = tf.reduce_sum(tf.to_int32(gates > 0), [0])
    self._nonzero_gates = tf.gather(
        tf.reshape(self._gates, [-1]),
        self._batch_index * num_experts + self._expert_index) 

def lstm_online(cell_fn, num_steps, inputs, state, varscope):
  # inputs is B x num_steps x C, C channels.
  # state is 2 tuple with B x 1 x C1, B x 1 x C2 
  # Output state is always B x 1 x C
  inputs = tf.unstack(inputs, axis=1, num=num_steps)
  state = tf.unstack(state, axis=1, num=1)[0]
  outputs = [] 
  
  if num_steps > 1: 
    varscope.reuse_variables()
  
  for s in range(num_steps):
    output, state = cell_fn(inputs[s], state)
    outputs.append(output)
  outputs = tf.stack(outputs, axis=1)
  state = tf.stack([state], axis=1)
  return outputs, state 

def combine(self, expert_out, multiply_by_gates=True):
    """Sum together the expert output, multiplied by the corresponding gates.

    Args:
      expert_out: a list of `num_experts` `Tensor`s, each with shape
        `[expert_batch_size_i, <extra_output_dims>]`.
      multiply_by_gates: a boolean.

    Returns:
      a list of num_datashards `Tensor`s with shapes
        `[batch_size[d], <extra_output_dims>]`.
    """
    expert_part_sizes = tf.unstack(
        tf.stack([d.part_sizes for d in self._dispatchers]),
        num=self._ep.n,
        axis=1)
    # list of lists of shape [num_experts][num_datashards]
    expert_output_parts = self._ep(tf.split, expert_out, expert_part_sizes)
    expert_output_parts_t = transpose_list_of_lists(expert_output_parts)
    def my_combine(dispatcher, parts):
      return dispatcher.combine(
          common_layers.convert_gradient_to_tensor(tf.concat(parts, 0)),
          multiply_by_gates=multiply_by_gates)
    return self._dp(my_combine, self._dispatchers, expert_output_parts_t) 

def clip_to_window(keypoints, window, scope=None):
  """Clips keypoints to a window.

  This op clips any input keypoints to a window.

  Args:
    keypoints: a tensor of shape [num_instances, num_keypoints, 2]
    window: a tensor of shape [4] representing the [y_min, x_min, y_max, x_max]
      window to which the op should clip the keypoints.
    scope: name scope.

  Returns:
    new_keypoints: a tensor of shape [num_instances, num_keypoints, 2]
  """
  with tf.name_scope(scope, 'ClipToWindow'):
    y, x = tf.split(value=keypoints, num_or_size_splits=2, axis=2)
    win_y_min, win_x_min, win_y_max, win_x_max = tf.unstack(window)
    y = tf.maximum(tf.minimum(y, win_y_max), win_y_min)
    x = tf.maximum(tf.minimum(x, win_x_max), win_x_min)
    new_keypoints = tf.concat([y, x], 2)
    return new_keypoints 

def _create_lstm_inputs(self, net):
    """Splits an input tensor into a list of tensors (features).

    Args:
      net: A feature map of shape [batch_size, num_features, feature_size].

    Raises:
      AssertionError: if num_features is less than seq_length.

    Returns:
      A list with seq_length tensors of shape [batch_size, feature_size]
    """
    num_features = net.get_shape().dims[1].value
    if num_features < self._params.seq_length:
      raise AssertionError('Incorrect dimension #1 of input tensor'
                           ' %d should be bigger than %d (shape=%s)' %
                           (num_features, self._params.seq_length,
                            net.get_shape()))
    elif num_features > self._params.seq_length:
      logging.warning('Ignoring some features: use %d of %d (shape=%s)',
                      self._params.seq_length, num_features, net.get_shape())
      net = tf.slice(net, [0, 0, 0], [-1, self._params.seq_length, -1])

    return tf.unstack(net, axis=1) 

def get_center_coordinates_and_sizes(self, scope=None):
    """Computes the center coordinates, height and width of the boxes.

    Args:
      scope: name scope of the function.

    Returns:
      a list of 4 1-D tensors [ycenter, xcenter, height, width].
    """
    with tf.name_scope(scope, 'get_center_coordinates_and_sizes'):
      box_corners = self.get()
      ymin, xmin, ymax, xmax = tf.unstack(tf.transpose(box_corners))
      width = xmax - xmin
      height = ymax - ymin
      ycenter = ymin + height / 2.
      xcenter = xmin + width / 2.
      return [ycenter, xcenter, height, width] 

def get_center_coordinates_and_sizes(self, scope=None):
    """Computes the center coordinates, height and width of the boxes.

    Args:
      scope: name scope of the function.

    Returns:
      a list of 4 1-D tensors [ycenter, xcenter, height, width].
    """
    with tf.name_scope(scope, 'get_center_coordinates_and_sizes'):
      box_corners = self.get()
      ymin, xmin, ymax, xmax = tf.unstack(tf.transpose(box_corners))
      width = xmax - xmin
      height = ymax - ymin
      ycenter = ymin + height / 2.
      xcenter = xmin + width / 2.
      return [ycenter, xcenter, height, width] 

def prune_completely_outside_window(boxlist, window, scope=None):
  """Prunes bounding boxes that fall completely outside of the given window.

  The function clip_to_window prunes bounding boxes that fall
  completely outside the window, but also clips any bounding boxes that
  partially overflow. This function does not clip partially overflowing boxes.

  Args:
    boxlist: a BoxList holding M_in boxes.
    window: a float tensor of shape [4] representing [ymin, xmin, ymax, xmax]
      of the window
    scope: name scope.

  Returns:
    pruned_boxlist: a new BoxList with all bounding boxes partially or fully in
      the window.
    valid_indices: a tensor with shape [M_out] indexing the valid bounding boxes
     in the input tensor.
  """
  with tf.name_scope(scope, 'PruneCompleteleyOutsideWindow'):
    y_min, x_min, y_max, x_max = tf.split(
        value=boxlist.get(), num_or_size_splits=4, axis=1)
    win_y_min, win_x_min, win_y_max, win_x_max = tf.unstack(window)
    coordinate_violations = tf.concat([
        tf.greater_equal(y_min, win_y_max), tf.greater_equal(x_min, win_x_max),
        tf.less_equal(y_max, win_y_min), tf.less_equal(x_max, win_x_min)
    ], 1)
    valid_indices = tf.reshape(
        tf.where(tf.logical_not(tf.reduce_any(coordinate_violations, 1))), [-1])
    return gather(boxlist, valid_indices), valid_indices 

def prune_outside_window(keypoints, window, scope=None):
  """Prunes keypoints that fall outside a given window.

  This function replaces keypoints that fall outside the given window with nan.
  See also clip_to_window which clips any keypoints that fall outside the given
  window.

  Args:
    keypoints: a tensor of shape [num_instances, num_keypoints, 2]
    window: a tensor of shape [4] representing the [y_min, x_min, y_max, x_max]
      window outside of which the op should prune the keypoints.
    scope: name scope.

  Returns:
    new_keypoints: a tensor of shape [num_instances, num_keypoints, 2]
  """
  with tf.name_scope(scope, 'PruneOutsideWindow'):
    y, x = tf.split(value=keypoints, num_or_size_splits=2, axis=2)
    win_y_min, win_x_min, win_y_max, win_x_max = tf.unstack(window)

    valid_indices = tf.logical_and(
        tf.logical_and(y >= win_y_min, y <= win_y_max),
        tf.logical_and(x >= win_x_min, x <= win_x_max))

    new_y = tf.where(valid_indices, y, np.nan * tf.ones_like(y))
    new_x = tf.where(valid_indices, x, np.nan * tf.ones_like(x))
    new_keypoints = tf.concat([new_y, new_x], 2)

    return new_keypoints 

def _decode(self, rel_codes, anchors):
    """Decodes relative codes to boxes.

    Args:
      rel_codes: a tensor representing N anchor-encoded boxes.
      anchors: BoxList of anchors.

    Returns:
      boxes: BoxList holding N bounding boxes.
    """
    ycenter_a, xcenter_a, ha, wa = anchors.get_center_coordinates_and_sizes()
    la = tf.sqrt(ha * wa)

    ty, tx, tl = tf.unstack(tf.transpose(rel_codes))
    if self._scale_factors:
      ty /= self._scale_factors[0]
      tx /= self._scale_factors[1]
      tl /= self._scale_factors[2]
    l = tf.exp(tl) * la
    ycenter = ty * la + ycenter_a
    xcenter = tx * la + xcenter_a
    ymin = ycenter - l / 2.
    xmin = xcenter - l / 2.
    ymax = ycenter + l / 2.
    xmax = xcenter + l / 2.
    return box_list.BoxList(tf.transpose(tf.stack([ymin, xmin, ymax, xmax]))) 

def visualize_boxes_in_image(image, boxlist, normalized=False, scope=None):
  """Overlay bounding box list on image.

  Currently this visualization plots a 1 pixel thick red bounding box on top
  of the image.  Note that tf.image.draw_bounding_boxes essentially is
  1 indexed.

  Args:
    image: an image tensor with shape [height, width, 3]
    boxlist: a BoxList
    normalized: (boolean) specify whether corners are to be interpreted
      as absolute coordinates in image space or normalized with respect to the
      image size.
    scope: name scope.

  Returns:
    image_and_boxes: an image tensor with shape [height, width, 3]
  """
  with tf.name_scope(scope, 'VisualizeBoxesInImage'):
    if not normalized:
      height, width, _ = tf.unstack(tf.shape(image))
      boxlist = scale(boxlist,
                      1.0 / tf.cast(height, tf.float32),
                      1.0 / tf.cast(width, tf.float32))
    corners = tf.expand_dims(boxlist.get(), 0)
    image = tf.expand_dims(image, 0)
    return tf.squeeze(tf.image.draw_bounding_boxes(image, corners), [0]) 

def _decode(self, rel_codes, anchors):
    """Decode relative codes to boxes.

    Args:
      rel_codes: a tensor representing N anchor-encoded boxes.
      anchors: BoxList of anchors.

    Returns:
      boxes: BoxList holding N bounding boxes.
    """
    ycenter_a, xcenter_a, ha, wa = anchors.get_center_coordinates_and_sizes()

    ty, tx, th, tw = tf.unstack(tf.transpose(rel_codes))
    if self._scale_factors:
      ty /= self._scale_factors[0]
      tx /= self._scale_factors[1]
      th /= self._scale_factors[2]
      tw /= self._scale_factors[3]
    w = tf.exp(tw) * wa
    h = tf.exp(th) * ha
    ycenter = ty * ha + ycenter_a
    xcenter = tx * wa + xcenter_a
    ymin = ycenter - h / 2.
    xmin = xcenter - w / 2.
    ymax = ycenter + h / 2.
    xmax = xcenter + w / 2.
    return box_list.BoxList(tf.transpose(tf.stack([ymin, xmin, ymax, xmax]))) 

def batch_decode(encoded_boxes, box_coder, anchors):
  """Decode a batch of encoded boxes.

  This op takes a batch of encoded bounding boxes and transforms
  them to a batch of bounding boxes specified by their corners in
  the order of [y_min, x_min, y_max, x_max].

  Args:
    encoded_boxes: a float32 tensor of shape [batch_size, num_anchors,
      code_size] representing the location of the objects.
    box_coder: a BoxCoder object.
    anchors: a BoxList of anchors used to encode `encoded_boxes`.

  Returns:
    decoded_boxes: a float32 tensor of shape [batch_size, num_anchors,
      coder_size] representing the corners of the objects in the order
      of [y_min, x_min, y_max, x_max].

  Raises:
    ValueError: if batch sizes of the inputs are inconsistent, or if
    the number of anchors inferred from encoded_boxes and anchors are
    inconsistent.
  """
  encoded_boxes.get_shape().assert_has_rank(3)
  if encoded_boxes.get_shape()[1].value != anchors.num_boxes_static():
    raise ValueError('The number of anchors inferred from encoded_boxes'
                     ' and anchors are inconsistent: shape[1] of encoded_boxes'
                     ' %s should be equal to the number of anchors: %s.' %
                     (encoded_boxes.get_shape()[1].value,
                      anchors.num_boxes_static()))

  decoded_boxes = tf.stack([
      box_coder.decode(boxes, anchors).get()
      for boxes in tf.unstack(encoded_boxes)
  ])
  return decoded_boxes 

def _compute_clip_window(self, preprocessed_images, true_image_shapes):
    """Computes clip window to use during post_processing.

    Computes a new clip window to use during post-processing based on
    `resized_image_shapes` and `true_image_shapes` only if `preprocess` method
    has been called. Otherwise returns a default clip window of [0, 0, 1, 1].

    Args:
      preprocessed_images: the [batch, height, width, channels] image
          tensor.
      true_image_shapes: int32 tensor of shape [batch, 3] where each row is
        of the form [height, width, channels] indicating the shapes
        of true images in the resized images, as resized images can be padded
        with zeros. Or None if the clip window should cover the full image.

    Returns:
      a 2-D float32 tensor of the form [batch_size, 4] containing the clip
      window for each image in the batch in normalized coordinates (relative to
      the resized dimensions) where each clip window is of the form [ymin, xmin,
      ymax, xmax] or a default clip window of [0, 0, 1, 1].

    """
    if true_image_shapes is None:
      return tf.constant([0, 0, 1, 1], dtype=tf.float32)

    resized_inputs_shape = shape_utils.combined_static_and_dynamic_shape(
        preprocessed_images)
    true_heights, true_widths, _ = tf.unstack(
        tf.to_float(true_image_shapes), axis=1)
    padded_height = tf.to_float(resized_inputs_shape[1])
    padded_width = tf.to_float(resized_inputs_shape[2])
    return tf.stack(
        [
            tf.zeros_like(true_heights),
            tf.zeros_like(true_widths), true_heights / padded_height,
            true_widths / padded_width
        ],
        axis=1) 

def _decode(self, rel_codes, anchors):
    """Decodes relative codes to boxes.

    Args:
      rel_codes: a tensor representing N anchor-encoded boxes.
      anchors: BoxList of anchors.

    Returns:
      boxes: BoxList holding N bounding boxes.
    """
    ycenter_a, xcenter_a, ha, wa = anchors.get_center_coordinates_and_sizes()
    la = tf.sqrt(ha * wa)

    ty, tx, tl = tf.unstack(tf.transpose(rel_codes))
    if self._scale_factors:
      ty /= self._scale_factors[0]
      tx /= self._scale_factors[1]
      tl /= self._scale_factors[2]
    l = tf.exp(tl) * la
    ycenter = ty * la + ycenter_a
    xcenter = tx * la + xcenter_a
    ymin = ycenter - l / 2.
    xmin = xcenter - l / 2.
    ymax = ycenter + l / 2.
    xmax = xcenter + l / 2.
    return box_list.BoxList(tf.transpose(tf.stack([ymin, xmin, ymax, xmax]))) 

def clip_to_window(boxlist, window, filter_nonoverlapping=True, scope=None):
  """Clip bounding boxes to a window.

  This op clips any input bounding boxes (represented by bounding box
  corners) to a window, optionally filtering out boxes that do not
  overlap at all with the window.

  Args:
    boxlist: BoxList holding M_in boxes
    window: a tensor of shape [4] representing the [y_min, x_min, y_max, x_max]
      window to which the op should clip boxes.
    filter_nonoverlapping: whether to filter out boxes that do not overlap at
      all with the window.
    scope: name scope.

  Returns:
    a BoxList holding M_out boxes where M_out <= M_in
  """
  with tf.name_scope(scope, 'ClipToWindow'):
    y_min, x_min, y_max, x_max = tf.split(
        value=boxlist.get(), num_or_size_splits=4, axis=1)
    win_y_min, win_x_min, win_y_max, win_x_max = tf.unstack(window)
    y_min_clipped = tf.maximum(tf.minimum(y_min, win_y_max), win_y_min)
    y_max_clipped = tf.maximum(tf.minimum(y_max, win_y_max), win_y_min)
    x_min_clipped = tf.maximum(tf.minimum(x_min, win_x_max), win_x_min)
    x_max_clipped = tf.maximum(tf.minimum(x_max, win_x_max), win_x_min)
    clipped = box_list.BoxList(
        tf.concat([y_min_clipped, x_min_clipped, y_max_clipped, x_max_clipped],
                  1))
    clipped = _copy_extra_fields(clipped, boxlist)
    if filter_nonoverlapping:
      areas = area(clipped)
      nonzero_area_indices = tf.cast(
          tf.reshape(tf.where(tf.greater(areas, 0.0)), [-1]), tf.int32)
      clipped = gather(clipped, nonzero_area_indices)
    return clipped 

def unroll(self, actions, env_outputs, core_state):
    """Manual implementation of the network unroll."""
    _, _, done, _ = env_outputs

    torso_outputs = snt.BatchApply(self._torso)((actions, env_outputs))
    tf.logging.info(torso_outputs)
    conv_outputs, actions_and_rewards, goals = torso_outputs

    # Note, in this implementation we can't use CuDNN RNN to speed things up due
    # to the state reset. This can be XLA-compiled (LSTMBlockCell needs to be
    # changed to implement snt.LSTMCell).
    initial_core_state = self.initial_state(tf.shape(actions)[1])
    policy_input_list = []
    heading_output_list = []
    xy_output_list = []
    target_xy_output_list = []
    for torso_output_, action_and_reward_, goal_, done_ in zip(
        tf.unstack(conv_outputs),
        tf.unstack(actions_and_rewards),
        tf.unstack(goals),
        tf.unstack(done)):
      # If the episode ended, the core state should be reset before the next.
      core_state = nest.map_structure(
          functools.partial(tf.where, done_), initial_core_state, core_state)
      core_output, core_state = self._core(
          (torso_output_, action_and_reward_, goal_), core_state)
      policy_input_list.append(core_output[0])
      heading_output_list.append(core_output[1])
      xy_output_list.append(core_output[2])
      target_xy_output_list.append(core_output[3])
    head_output = snt.BatchApply(self._head)(tf.stack(policy_input_list),
                                             tf.stack(heading_output_list),
                                             tf.stack(xy_output_list),
                                             tf.stack(target_xy_output_list))

    return head_output, core_state 

def discount_rewards(self, r):
    """ take a list of size max_dec_step * (batch_size, k) and return a list of the same size """
    discounted_r = []
    running_add = tf.constant(0, tf.float32)
    for t in reversed(range(0, len(r))):
      running_add = running_add * self._hps.gamma + r[t] # rd_t = r_t + gamma * r_{t+1}
      discounted_r.append(running_add)
    discounted_r = tf.stack(discounted_r[::-1]) # (max_dec_step, batch_size, k)
    normalized_discounted_r = tf.nn.l2_normalize(discounted_r, axis=0)
    return tf.unstack(normalized_discounted_r) # list of max_dec_step * (batch_size, k) 

def non_max_suppression(inputs, n_classes, max_output_size, iou_threshold, confidence_threshold):
  """Performs non-max suppression separately for each class"""
  batch = tf.unstack(inputs)
  boxes_dicts = []

  for boxes in batch:
    boxes = tf.boolean_mask(boxes, boxes[:, 4] > confidence_threshold)
    classes = tf.argmax(boxes[:, 5:], axis=-1)
    classes = tf.expand_dims(tf.cast(classes, tf.float32), axis=-1)
    boxes = tf.concat([boxes[:, :5], classes], axis=-1)

    boxes_dict = dict()
    for cls in range(n_classes):
      mask = tf.equal(boxes[:, 5], cls)
      mask_shape = mask.get_shape()
      if mask_shape.ndims != 0:
        class_boxes = tf.boolean_mask(boxes, mask)
        boxes_coords, boxes_conf_scores, _ = tf.split(class_boxes, [4, 1, -1], axis=-1)
        boxes_conf_scores = tf.reshape(boxes_conf_scores, [-1])
        indices = tf.image.non_max_suppression(boxes_coords,
                                               boxes_conf_scores,
                                               max_output_size,
                                               iou_threshold)
        class_boxes = tf.gather(class_boxes, indices)
        boxes_dict[cls] = class_boxes[:, :5]

    boxes_dicts.append(boxes_dict)
  return boxes_dicts 

def dequeue(self):
    """Dequeues a batch of tensor_dict from the BatchQueue.

    TODO: use allow_smaller_final_batch to allow running over the whole eval set

    Returns:
      A list of tensor_dicts of the requested batch_size.
    """
    batched_tensors = self._queue.dequeue()
    # Separate input tensors from tensors containing their runtime shapes.
    tensors = {}
    shapes = {}
    for key, batched_tensor in batched_tensors.iteritems():
      unbatched_tensor_list = tf.unstack(batched_tensor)
      for i, unbatched_tensor in enumerate(unbatched_tensor_list):
        if isinstance(key, tuple) and key[1] == 'runtime_shapes':
          shapes[(key[0], i)] = unbatched_tensor
        else:
          tensors[(key, i)] = unbatched_tensor

    # Undo that padding using shapes and create a list of size `batch_size` that
    # contains tensor dictionaries.
    tensor_dict_list = []
    batch_size = self._batch_size
    for batch_id in range(batch_size):
      tensor_dict = {}
      for key in self._static_shapes:
        tensor_dict[key] = tf.slice(tensors[(key, batch_id)],
                                    tf.zeros_like(shapes[(key, batch_id)]),
                                    shapes[(key, batch_id)])
        tensor_dict[key].set_shape(self._static_shapes[key])
      tensor_dict_list.append(tensor_dict)

    return tensor_dict_list 

def visualize_boxes_in_image(image, boxlist, normalized=False, scope=None):
  """Overlay bounding box list on image.

  Currently this visualization plots a 1 pixel thick red bounding box on top
  of the image.  Note that tf.image.draw_bounding_boxes essentially is
  1 indexed.

  Args:
    image: an image tensor with shape [height, width, 3]
    boxlist: a BoxList
    normalized: (boolean) specify whether corners are to be interpreted
      as absolute coordinates in image space or normalized with respect to the
      image size.
    scope: name scope.

  Returns:
    image_and_boxes: an image tensor with shape [height, width, 3]
  """
  with tf.name_scope(scope, 'VisualizeBoxesInImage'):
    if not normalized:
      height, width, _ = tf.unstack(tf.shape(image))
      boxlist = scale(boxlist,
                      1.0 / tf.cast(height, tf.float32),
                      1.0 / tf.cast(width, tf.float32))
    corners = tf.expand_dims(boxlist.get(), 0)
    image = tf.expand_dims(image, 0)
    return tf.squeeze(tf.image.draw_bounding_boxes(image, corners), [0]) 

def prune_outside_window(boxlist, window, scope=None):
  """Prunes bounding boxes that fall outside a given window.

  This function prunes bounding boxes that even partially fall outside the given
  window. See also clip_to_window which only prunes bounding boxes that fall
  completely outside the window, and clips any bounding boxes that partially
  overflow.

  Args:
    boxlist: a BoxList holding M_in boxes.
    window: a float tensor of shape [4] representing [ymin, xmin, ymax, xmax]
      of the window
    scope: name scope.

  Returns:
    pruned_corners: a tensor with shape [M_out, 4] where M_out <= M_in
    valid_indices: a tensor with shape [M_out] indexing the valid bounding boxes
     in the input tensor.
  """
  with tf.name_scope(scope, 'PruneOutsideWindow'):
    y_min, x_min, y_max, x_max = tf.split(
        value=boxlist.get(), num_or_size_splits=4, axis=1)
    win_y_min, win_x_min, win_y_max, win_x_max = tf.unstack(window)
    coordinate_violations = tf.concat([
        tf.less(y_min, win_y_min), tf.less(x_min, win_x_min),
        tf.greater(y_max, win_y_max), tf.greater(x_max, win_x_max)
    ], 1)
    valid_indices = tf.reshape(
        tf.where(tf.logical_not(tf.reduce_any(coordinate_violations, 1))), [-1])
    return gather(boxlist, valid_indices), valid_indices 

def clip_to_window(boxlist, window, filter_nonoverlapping=True, scope=None):
  """Clip bounding boxes to a window.

  This op clips any input bounding boxes (represented by bounding box
  corners) to a window, optionally filtering out boxes that do not
  overlap at all with the window.

  Args:
    boxlist: BoxList holding M_in boxes
    window: a tensor of shape [4] representing the [y_min, x_min, y_max, x_max]
      window to which the op should clip boxes.
    filter_nonoverlapping: whether to filter out boxes that do not overlap at
      all with the window.
    scope: name scope.

  Returns:
    a BoxList holding M_out boxes where M_out <= M_in
  """
  with tf.name_scope(scope, 'ClipToWindow'):
    y_min, x_min, y_max, x_max = tf.split(
        value=boxlist.get(), num_or_size_splits=4, axis=1)
    win_y_min, win_x_min, win_y_max, win_x_max = tf.unstack(window)
    y_min_clipped = tf.maximum(tf.minimum(y_min, win_y_max), win_y_min)
    y_max_clipped = tf.maximum(tf.minimum(y_max, win_y_max), win_y_min)
    x_min_clipped = tf.maximum(tf.minimum(x_min, win_x_max), win_x_min)
    x_max_clipped = tf.maximum(tf.minimum(x_max, win_x_max), win_x_min)
    clipped = box_list.BoxList(
        tf.concat([y_min_clipped, x_min_clipped, y_max_clipped, x_max_clipped],
                  1))
    clipped = _copy_extra_fields(clipped, boxlist)
    if filter_nonoverlapping:
      areas = area(clipped)
      nonzero_area_indices = tf.cast(
          tf.reshape(tf.where(tf.greater(areas, 0.0)), [-1]), tf.int32)
      clipped = gather(clipped, nonzero_area_indices)
    return clipped 

def batch_decode(encoded_boxes, box_coder, anchors):
  """Decode a batch of encoded boxes.

  This op takes a batch of encoded bounding boxes and transforms
  them to a batch of bounding boxes specified by their corners in
  the order of [y_min, x_min, y_max, x_max].

  Args:
    encoded_boxes: a float32 tensor of shape [batch_size, num_anchors,
      code_size] representing the location of the objects.
    box_coder: a BoxCoder object.
    anchors: a BoxList of anchors used to encode `encoded_boxes`.

  Returns:
    decoded_boxes: a float32 tensor of shape [batch_size, num_anchors,
      coder_size] representing the corners of the objects in the order
      of [y_min, x_min, y_max, x_max].

  Raises:
    ValueError: if batch sizes of the inputs are inconsistent, or if
    the number of anchors inferred from encoded_boxes and anchors are
    inconsistent.
  """
  encoded_boxes.get_shape().assert_has_rank(3)
  if encoded_boxes.get_shape()[1].value != anchors.num_boxes_static():
    raise ValueError('The number of anchors inferred from encoded_boxes'
                     ' and anchors are inconsistent: shape[1] of encoded_boxes'
                     ' %s should be equal to the number of anchors: %s.' %
                     (encoded_boxes.get_shape()[1].value,
                      anchors.num_boxes_static()))

  decoded_boxes = tf.stack([
      box_coder.decode(boxes, anchors).get()
      for boxes in tf.unstack(encoded_boxes)
  ])
  return decoded_boxes 

def prune_outside_window(keypoints, window, scope=None):
  """Prunes keypoints that fall outside a given window.

  This function replaces keypoints that fall outside the given window with nan.
  See also clip_to_window which clips any keypoints that fall outside the given
  window.

  Args:
    keypoints: a tensor of shape [num_instances, num_keypoints, 2]
    window: a tensor of shape [4] representing the [y_min, x_min, y_max, x_max]
      window outside of which the op should prune the keypoints.
    scope: name scope.

  Returns:
    new_keypoints: a tensor of shape [num_instances, num_keypoints, 2]
  """
  with tf.name_scope(scope, 'PruneOutsideWindow'):
    y, x = tf.split(value=keypoints, num_or_size_splits=2, axis=2)
    win_y_min, win_x_min, win_y_max, win_x_max = tf.unstack(window)

    valid_indices = tf.logical_and(
        tf.logical_and(y >= win_y_min, y <= win_y_max),
        tf.logical_and(x >= win_x_min, x <= win_x_max))

    new_y = tf.where(valid_indices, y, np.nan * tf.ones_like(y))
    new_x = tf.where(valid_indices, x, np.nan * tf.ones_like(x))
    new_keypoints = tf.concat([new_y, new_x], 2)

    return new_keypoints 

def BiRNN(self, x, dropout, scope, embedding_size, sequence_length, hidden_units):
        n_hidden=hidden_units
        n_layers=3
        # Prepare data shape to match `static_rnn` function requirements
        x = tf.unstack(tf.transpose(x, perm=[1, 0, 2]))
        print(x)
        # Define lstm cells with tensorflow
        # Forward direction cell
        with tf.name_scope("fw"+scope),tf.variable_scope("fw"+scope):
            stacked_rnn_fw = []
            for _ in range(n_layers):
                fw_cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden, forget_bias=1.0, state_is_tuple=True)
                lstm_fw_cell = tf.contrib.rnn.DropoutWrapper(fw_cell,output_keep_prob=dropout)
                stacked_rnn_fw.append(lstm_fw_cell)
            lstm_fw_cell_m = tf.nn.rnn_cell.MultiRNNCell(cells=stacked_rnn_fw, state_is_tuple=True)

        with tf.name_scope("bw"+scope),tf.variable_scope("bw"+scope):
            stacked_rnn_bw = []
            for _ in range(n_layers):
                bw_cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden, forget_bias=1.0, state_is_tuple=True)
                lstm_bw_cell = tf.contrib.rnn.DropoutWrapper(bw_cell,output_keep_prob=dropout)
                stacked_rnn_bw.append(lstm_bw_cell)
            lstm_bw_cell_m = tf.nn.rnn_cell.MultiRNNCell(cells=stacked_rnn_bw, state_is_tuple=True)
        # Get lstm cell output

        with tf.name_scope("bw"+scope),tf.variable_scope("bw"+scope):
            outputs, _, _ = tf.nn.static_bidirectional_rnn(lstm_fw_cell_m, lstm_bw_cell_m, x, dtype=tf.float32)
        return outputs[-1]