Python v1.greater_equal方法代码示例

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def _flat_reconstruction_loss(self, flat_x_target, flat_rnn_output):
    b_enc, b_dec = tf.split(
        flat_rnn_output,
        [self._nade.num_hidden, self._output_depth], axis=1)
    ll, cond_probs = self._nade.log_prob(
        flat_x_target, b_enc=b_enc, b_dec=b_dec)
    r_loss = -ll
    flat_truth = tf.cast(flat_x_target, tf.bool)
    flat_predictions = tf.greater_equal(cond_probs, 0.5)

    metric_map = {
        'metrics/accuracy':
            tf.metrics.mean(
                tf.reduce_all(tf.equal(flat_truth, flat_predictions), axis=-1)),
        'metrics/recall':
            tf.metrics.recall(flat_truth, flat_predictions),
        'metrics/precision':
            tf.metrics.precision(flat_truth, flat_predictions),
    }

    return r_loss, metric_map 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def truncate_labels(context_labels, max_contexts):
  """Truncate labels based on max_contexts.

  Limit non-null labels to only be one of the first 'max_context' contexts.
  Otherwise mask it to -1 (the NULL label).

  Args:
    context_labels: <int32> [batch_size] with gold labels.
    max_contexts: <int32> for max_contexts.

  Returns:
    truncated context_labels: <int32>[batch_size]
  """
  # Null contexts are assigned label -1.
  null_labels = tf.ones_like(context_labels, dtype=tf.int32) * -1
  prune_gold_context = tf.greater_equal(context_labels, max_contexts)
  context_labels = tf.where(prune_gold_context, null_labels, context_labels)
  return context_labels 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def assert_box_normalized(boxes, maximum_normalized_coordinate=1.1):
  """Asserts the input box tensor is normalized.

  Args:
    boxes: a tensor of shape [N, 4] where N is the number of boxes.
    maximum_normalized_coordinate: Maximum coordinate value to be considered
      as normalized, default to 1.1.

  Returns:
    a tf.Assert op which fails when the input box tensor is not normalized.

  Raises:
    ValueError: When the input box tensor is not normalized.
  """
  box_minimum = tf.reduce_min(boxes)
  box_maximum = tf.reduce_max(boxes)
  return tf.Assert(
      tf.logical_and(
          tf.less_equal(box_maximum, maximum_normalized_coordinate),
          tf.greater_equal(box_minimum, 0)),
      [boxes]) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def prune_small_boxes(boxlist, min_side, scope=None):
  """Prunes small boxes in the boxlist which have a side smaller than min_side.

  Args:
    boxlist: BoxList holding N boxes.
    min_side: Minimum width AND height of box to survive pruning.
    scope: name scope.

  Returns:
    A pruned boxlist.
  """
  with tf.name_scope(scope, 'PruneSmallBoxes'):
    height, width = height_width(boxlist)
    is_valid = tf.logical_and(tf.greater_equal(width, min_side),
                              tf.greater_equal(height, min_side))
    return gather(boxlist, tf.reshape(tf.where(is_valid), [-1])) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def test_loop_conditions():
    graph = tf.Graph()
    with graph.as_default():
        i = tf.constant(1)
        j = tf.constant(1)
        k = tf.constant(5)

        def c(i, j, k): return \
            tf.equal(tf.not_equal(tf.less(i + j, 10),
                                  tf.less(j * k, 100)),
                     tf.greater_equal(k, i + j))

        def b(i, j, k): return [i+j, j+k, k+1]
        r = tf.while_loop(c, b, loop_vars=[i, j, k])
        with tf.Session() as sess:
            tf_out = sess.run(r)

    check_equal(graph, tf_out) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def _create_topk_unique(inputs, k):
  """Creates the top k values in sorted order with indices.

  Args:
    inputs: A tensor with rank of 2. [batch_size, original_size].
    k: An integer, number of top elements to select.

  Returns:
    topk_r2: A tensor, the k largest elements. [batch_size, k].
    topk_indices_r2: A tensor, indices of the top k values. [batch_size, k].
  """
  height = inputs.shape[0]
  width = inputs.shape[1]
  neg_inf_r0 = tf.constant(-np.inf, dtype=tf.float32)
  ones = tf.ones([height, width], dtype=tf.float32)
  neg_inf_r2 = ones * neg_inf_r0
  inputs = tf.where(tf.is_nan(inputs), neg_inf_r2, inputs)

  # Select the current largest value k times and keep them in topk_r2. The
  # selected largest values are marked as the smallest value to avoid being
  # selected again.
  tmp = inputs
  topk_r2 = tf.zeros([height, k], dtype=tf.float32)
  for i in range(k):
    kth_order_statistic = tf.reduce_max(tmp, axis=1, keepdims=True)
    k_mask = tf.tile(tf.expand_dims(tf.equal(tf.range(k), tf.fill([k], i)), 0),
                     [height, 1])
    topk_r2 = tf.where(k_mask, tf.tile(kth_order_statistic, [1, k]), topk_r2)
    ge_r2 = tf.greater_equal(inputs, tf.tile(kth_order_statistic, [1, width]))
    tmp = tf.where(ge_r2, neg_inf_r2, inputs)

  log2_ceiling = int(math.ceil(math.log(float(int(width)), 2)))
  next_power_of_two = 1 << log2_ceiling
  count_mask = next_power_of_two - 1
  mask_r0 = tf.constant(count_mask)
  mask_r2 = tf.fill([height, k], mask_r0)
  topk_r2_s32 = tf.bitcast(topk_r2, tf.int32)
  topk_indices_r2 = tf.bitwise.bitwise_and(topk_r2_s32, mask_r2)
  return topk_r2, topk_indices_r2 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def _crop(image, offset_height, offset_width, crop_height, crop_width):
  """Crops the given image using the provided offsets and sizes.

  Note that the method doesn't assume we know the input image size but it does
  assume we know the input image rank.

  Args:
    image: `Tensor` image of shape [height, width, channels].
    offset_height: `Tensor` indicating the height offset.
    offset_width: `Tensor` indicating the width offset.
    crop_height: the height of the cropped image.
    crop_width: the width of the cropped image.

  Returns:
    the cropped (and resized) image.

  Raises:
    InvalidArgumentError: if the rank is not 3 or if the image dimensions are
      less than the crop size.
  """
  original_shape = tf.shape(image)

  rank_assertion = tf.Assert(
      tf.equal(tf.rank(image), 3), ["Rank of image must be equal to 3."])
  with tf.control_dependencies([rank_assertion]):
    cropped_shape = tf.stack([crop_height, crop_width, original_shape[2]])

  size_assertion = tf.Assert(
      tf.logical_and(
          tf.greater_equal(original_shape[0], crop_height),
          tf.greater_equal(original_shape[1], crop_width)),
      ["Crop size greater than the image size."])

  offsets = tf.to_int32(tf.stack([offset_height, offset_width, 0]))

  # Use tf.slice instead of crop_to_bounding box as it accepts tensors to
  # define the crop size.
  with tf.control_dependencies([size_assertion]):
    image = tf.slice(image, offsets, cropped_shape)
  return tf.reshape(image, cropped_shape) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def _at_least_x_are_true(a, b, x):
  """At least `x` of `a` and `b` `Tensors` are true."""
  match = tf.equal(a, b)
  match = tf.cast(match, tf.int32)
  return tf.greater_equal(tf.reduce_sum(match), x) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def matched_column_indicator(self):
    """Returns column indices that are matched.

    Returns:
      column_indices: int32 tensor of shape [K] with column indices.
    """
    return tf.greater_equal(self._match_results, 0) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def _at_least_x_are_equal(a, b, x):
  """At least `x` of `a` and `b` `Tensors` are equal."""
  match = tf.equal(a, b)
  match = tf.cast(match, tf.int32)
  return tf.greater_equal(tf.reduce_sum(match), x) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def _get_action_type(extended_indices, output_vocab_size, model_config):
  """Returns action_type tensor."""
  action_type = tf.constant(0, dtype=tf.int64)
  for action_type_range in _get_action_types_to_range(output_vocab_size,
                                                      model_config):
    index_in_range = tf.logical_and(
        tf.greater_equal(extended_indices, action_type_range.start_index),
        tf.less(extended_indices, action_type_range.end_index))
    action_type += (
        tf.to_int64(index_in_range) * tf.constant(
            action_type_range.action_type, dtype=tf.int64))
  return action_type 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def load_nli_file(data_path, num_par=2):
  """Build a tf.data.Data from a file of NLI examples."""
  tokenizer = tokenization.NltkTokenizer()
  dataset = tf.data.TextLineDataset(data_path)
  dataset = dataset.map(
      functools.partial(_nli_line_to_tensors, tokenizer=tokenizer),
      num_parallel_calls=num_par)
  dataset = dataset.filter(lambda x: tf.greater_equal(x["label"], 0))
  return dataset 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def _crop(image, offset_height, offset_width, crop_height, crop_width):
  """Crops the given image using the provided offsets and sizes.

  Note that the method doesn't assume we know the input image size but it does
  assume we know the input image rank.

  Args:
    image: an image of shape [height, width, channels].
    offset_height: a scalar tensor indicating the height offset.
    offset_width: a scalar tensor indicating the width offset.
    crop_height: the height of the cropped image.
    crop_width: the width of the cropped image.

  Returns:
    the cropped (and resized) image.

  Raises:
    InvalidArgumentError: if the rank is not 3 or if the image dimensions are
      less than the crop size.
  """
  original_shape = tf.shape(image)

  rank_assertion = tf.Assert(
      tf.equal(tf.rank(image), 3),
      ['Rank of image must be equal to 3.'])
  with tf.control_dependencies([rank_assertion]):
    cropped_shape = tf.stack([crop_height, crop_width, original_shape[2]])

  size_assertion = tf.Assert(
      tf.logical_and(
          tf.greater_equal(original_shape[0], crop_height),
          tf.greater_equal(original_shape[1], crop_width)),
      ['Crop size greater than the image size.'])

  offsets = tf.to_int32(tf.stack([offset_height, offset_width, 0]))

  # Use tf.slice instead of crop_to_bounding box as it accepts tensors to
  # define the crop size.
  with tf.control_dependencies([size_assertion]):
    image = tf.slice(image, offsets, cropped_shape)
  return tf.reshape(image, cropped_shape) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def check_min_image_dim(min_dim, image_tensor):
  """Checks that the image width/height are greater than some number.

  This function is used to check that the width and height of an image are above
  a certain value. If the image shape is static, this function will perform the
  check at graph construction time. Otherwise, if the image shape varies, an
  Assertion control dependency will be added to the graph.

  Args:
    min_dim: The minimum number of pixels along the width and height of the
             image.
    image_tensor: The image tensor to check size for.

  Returns:
    If `image_tensor` has dynamic size, return `image_tensor` with a Assert
    control dependency. Otherwise returns image_tensor.

  Raises:
    ValueError: if `image_tensor`'s' width or height is smaller than `min_dim`.
  """
  image_shape = image_tensor.get_shape()
  image_height = static_shape.get_height(image_shape)
  image_width = static_shape.get_width(image_shape)
  if image_height is None or image_width is None:
    shape_assert = tf.Assert(
        tf.logical_and(tf.greater_equal(tf.shape(image_tensor)[1], min_dim),
                       tf.greater_equal(tf.shape(image_tensor)[2], min_dim)),
        ['image size must be >= {} in both height and width.'.format(min_dim)])
    with tf.control_dependencies([shape_assert]):
      return tf.identity(image_tensor)

  if image_height < min_dim or image_width < min_dim:
    raise ValueError(
        'image size must be >= %d in both height and width; image dim = %d,%d' %
        (min_dim, image_height, image_width))

  return image_tensor 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import greater_equal [as 别名]
def _extract_proposal_features(self, preprocessed_inputs, scope):
    """Extracts first stage RPN features.

    Args:
      preprocessed_inputs: A [batch, height, width, channels] float32 tensor
        representing a batch of images.
      scope: A scope name.

    Returns:
      rpn_feature_map: A tensor with shape [batch, height, width, depth]
      activations: A dictionary mapping feature extractor tensor names to
        tensors

    Raises:
      InvalidArgumentError: If the spatial size of `preprocessed_inputs`
        (height or width) is less than 33.
      ValueError: If the created network is missing the required activation.
    """

    preprocessed_inputs.get_shape().assert_has_rank(4)
    shape_assert = tf.Assert(
        tf.logical_and(tf.greater_equal(tf.shape(preprocessed_inputs)[1], 33),
                       tf.greater_equal(tf.shape(preprocessed_inputs)[2], 33)),
        ['image size must at least be 33 in both height and width.'])

    with tf.control_dependencies([shape_assert]):
      with tf.variable_scope('InceptionV2',
                             reuse=self._reuse_weights) as scope:
        with _batch_norm_arg_scope([slim.conv2d, slim.separable_conv2d],
                                   batch_norm_scale=True,
                                   train_batch_norm=self._train_batch_norm):
          _, activations = inception_v2.inception_v2_base(
              preprocessed_inputs,
              final_endpoint='Mixed_4e',
              min_depth=self._min_depth,
              depth_multiplier=self._depth_multiplier,
              scope=scope)

    return activations['Mixed_4e'], activations