Python v1.logical_not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 logical_not [as 别名]
def lengths_to_area_mask(feature_length, length, max_area_size):
  """Generates a non-padding mask for areas based on lengths.

  Args:
    feature_length: a tensor of [batch_size]
    length: the length of the batch
    max_area_size: the maximum area size considered
  Returns:
    mask: a tensor in shape of [batch_size, num_areas]
  """

  paddings = tf.cast(tf.expand_dims(
      tf.logical_not(
          tf.sequence_mask(feature_length, maxlen=length)), 2), tf.float32)
  _, _, area_sum, _, _ = compute_area_features(paddings,
                                               max_area_width=max_area_size)
  mask = tf.squeeze(tf.logical_not(tf.cast(area_sum, tf.bool)), [2])
  return mask 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def __init__(self, c, d=None, prune_irrelevant=True, collapse=True):
    """Builds a linear specification module."""
    super(LinearSpecification, self).__init__(name='specs', collapse=collapse)
    # c has shape [batch_size, num_specifications, num_outputs]
    # d has shape [batch_size, num_specifications]
    # Some specifications may be irrelevant (not a function of the output).
    # We automatically remove them for clarity. We expect the number of
    # irrelevant specs to be equal for all elements of a batch.
    # Shape is [batch_size, num_specifications]
    if prune_irrelevant:
      irrelevant = tf.equal(tf.reduce_sum(
          tf.cast(tf.abs(c) > 1e-6, tf.int32), axis=-1, keepdims=True), 0)
      batch_size = tf.shape(c)[0]
      num_outputs = tf.shape(c)[2]
      irrelevant = tf.tile(irrelevant, [1, 1, num_outputs])
      self._c = tf.reshape(
          tf.boolean_mask(c, tf.logical_not(irrelevant)),
          [batch_size, -1, num_outputs])
    else:
      self._c = c
    self._d = d 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def _build(self, inputs, labels):

    def cond(i, unused_attack, success):
      # If we are already successful, we break.
      return tf.logical_and(i < self._num_restarts,
                            tf.logical_not(tf.reduce_all(success)))

    def body(i, attack, success):
      new_attack = self._inner_attack(inputs, labels)
      new_success = self._inner_attack.success
      # The first iteration always sets the attack.
      use_new_values = tf.logical_or(tf.equal(i, 0), new_success)
      return (i + 1,
              tf.where(use_new_values, new_attack, attack),
              tf.logical_or(success, new_success))

    _, self._attack, self._success = tf.while_loop(
        cond, body, back_prop=False, parallel_iterations=1,
        loop_vars=[
            tf.constant(0, dtype=tf.int32),
            inputs,
            tf.zeros([tf.shape(inputs)[0]], dtype=tf.bool),
        ])
    self._logits = self._eval_fn(self._attack, mode='final')
    return self._attack 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def _sequence_correct(labels, predictions):
  """Computes a per-example sequence accuracy."""
  target_decode_steps = decode_utils.decode_steps_from_labels(
      labels, trim_start_symbol=True)
  predicted_decode_steps = decode_utils.decode_steps_from_predictions(
      predictions)

  decode_utils.assert_shapes_match(target_decode_steps, predicted_decode_steps)

  equal_tokens = decode_utils.compare_decode_steps(target_decode_steps,
                                                   predicted_decode_steps)
  target_len = labels["target_len"] - 1
  loss_mask = tf.sequence_mask(
      lengths=tf.to_int32(target_len),
      maxlen=tf.to_int32(tf.shape(equal_tokens)[1]))
  equal_tokens = tf.logical_or(equal_tokens, tf.logical_not(loss_mask))
  all_equal = tf.cast(tf.reduce_all(equal_tokens, 1), tf.float32)
  return all_equal 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def attention_bias_lower_triangle(length):
  """Create a bias tensor to be added to attention logits.

  Masked elements will have an effective negative-infinity value.

  Args:
    length: Integer specifying maximum sequence length in batch.

  Returns:
    <float>[length, length]
  """
  # First, create a sequence mask, e.g.:
  # [1, 0, ..., 0]
  # ...
  # [1, 1, ..., 1]
  sequence_mask = tf.sequence_mask(tf.range(1, length + 1), length)
  # Invert to transform to attention biases.
  attention_bias = tf.to_float(tf.logical_not(sequence_mask)) * -1e9
  return attention_bias 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def attention_bias_ignore_padding(source_len, max_length):
  """Create a bias tensor to be added to attention logits.

  Out-of-range elements will have an effective negative-infinity value.

  Args:
    source_len: <int>[batch_size]
    max_length: Integer specifying maxmimum sequence length in batch.

  Returns:
    <float>[batch_size, 1, 1, max_length]
  """
  memory_padding = tf.to_float(
      tf.logical_not(tf.sequence_mask(source_len, maxlen=max_length)))
  ret = memory_padding * -1e9
  # Expand so tensor can be broadcast across heads and query length.
  return tf.expand_dims(tf.expand_dims(ret, axis=1), axis=1) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def noise_span_to_sentinel(tokens, noise_mask, vocabulary):
  """Replace each run of consecutive noise tokens with a single sentinel.

  Args:
    tokens: a 1d integer Tensor
    noise_mask: a boolean Tensor with the same shape as tokens
    vocabulary: a vocabulary.Vocabulary
  Returns:
    a Tensor with the same shape and dtype as tokens
  """
  tokens = tf.where_v2(noise_mask,
                       tf.cast(sentinel_id(vocabulary), tokens.dtype),
                       tokens)
  prev_token_is_noise = tf.pad(noise_mask[:-1], [[1, 0]])
  subsequent_noise_tokens = tf.logical_and(noise_mask, prev_token_is_noise)
  return tf.boolean_mask(tokens, tf.logical_not(subsequent_noise_tokens)) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def filter_groundtruth_with_crowd_boxes(tensor_dict):
  """Filters out groundtruth with boxes corresponding to crowd.

  Args:
    tensor_dict: a dictionary of following groundtruth tensors -
      fields.InputDataFields.groundtruth_boxes
      fields.InputDataFields.groundtruth_classes
      fields.InputDataFields.groundtruth_confidences
      fields.InputDataFields.groundtruth_keypoints
      fields.InputDataFields.groundtruth_instance_masks
      fields.InputDataFields.groundtruth_is_crowd
      fields.InputDataFields.groundtruth_area
      fields.InputDataFields.groundtruth_label_types

  Returns:
    a dictionary of tensors containing only the groundtruth that have bounding
    boxes.
  """
  if fields.InputDataFields.groundtruth_is_crowd in tensor_dict:
    is_crowd = tensor_dict[fields.InputDataFields.groundtruth_is_crowd]
    is_not_crowd = tf.logical_not(is_crowd)
    is_not_crowd_indices = tf.where(is_not_crowd)
    tensor_dict = retain_groundtruth(tensor_dict, is_not_crowd_indices)
  return tensor_dict 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def filter_groundtruth_with_nan_box_coordinates(tensor_dict):
  """Filters out groundtruth with no bounding boxes.

  Args:
    tensor_dict: a dictionary of following groundtruth tensors -
      fields.InputDataFields.groundtruth_boxes
      fields.InputDataFields.groundtruth_classes
      fields.InputDataFields.groundtruth_confidences
      fields.InputDataFields.groundtruth_keypoints
      fields.InputDataFields.groundtruth_instance_masks
      fields.InputDataFields.groundtruth_is_crowd
      fields.InputDataFields.groundtruth_area
      fields.InputDataFields.groundtruth_label_types

  Returns:
    a dictionary of tensors containing only the groundtruth that have bounding
    boxes.
  """
  groundtruth_boxes = tensor_dict[fields.InputDataFields.groundtruth_boxes]
  nan_indicator_vector = tf.greater(tf.reduce_sum(tf.cast(
      tf.is_nan(groundtruth_boxes), dtype=tf.int32), reduction_indices=[1]), 0)
  valid_indicator_vector = tf.logical_not(nan_indicator_vector)
  valid_indices = tf.where(valid_indicator_vector)

  return retain_groundtruth(tensor_dict, valid_indices) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def aggregate_single_gradient_using_copy(grad_and_vars, use_mean,
                                         check_inf_nan):
  """Calculate the average gradient for a shared variable across all towers.

  Note that this function provides a synchronization point across all towers.

  Args:
    grad_and_vars: A list or tuple of (gradient, variable) tuples. Each
      (gradient, variable) pair within the outer list represents the gradient
      of the variable calculated for a single tower, and the number of pairs
      equals the number of towers.
    use_mean: if True, mean is taken, else sum of gradients is taken.
    check_inf_nan: check grads for nans and infs.

  Returns:
    The tuple ([(average_gradient, variable),], has_nan_or_inf) where the
      gradient has been averaged across all towers. The variable is chosen from
      the first tower. The has_nan_or_inf indicates the grads has nan or inf.
  """
  grads = [g for g, _ in grad_and_vars]
  if any(isinstance(g, tf.IndexedSlices) for g in grads):
    # TODO(reedwm): All-reduce IndexedSlices more effectively.
    grad = aggregate_indexed_slices_gradients(grads)
  else:
    grad = tf.add_n(grads)

  if use_mean and len(grads) > 1:
    grad = tf.scalar_mul(1.0 / len(grads), grad)

  v = grad_and_vars[0][1]
  if check_inf_nan:
    with tf.name_scope('check_for_inf_and_nan'):
      has_nan_or_inf = tf.logical_not(tf.reduce_all(tf.is_finite(grads)))
    return (grad, v), has_nan_or_inf
  else:
    return (grad, v), None


# This class is copied from
# https://github.com/tensorflow/tensorflow/blob/590d6eef7e91a6a7392c8ffffb7b58f2e0c8bc6b/tensorflow/contrib/training/python/training/device_setter.py#L56.
# We copy it since contrib has been removed from TensorFlow. 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def get_gradients_to_apply(self, device_num, gradient_state):
    device_grads = gradient_state
    tower_grad = device_grads[device_num]

    if self.benchmark_cnn.enable_auto_loss_scale and device_num == 0:
      # Since we don't aggregate variables in --independent mode, we cannot tell
      # if there are NaNs on all GPUs. So we arbitrarily choose to only check
      # NaNs on the first GPU.
      has_inf_nan_list = []
      for grad, _ in tower_grad:
        has_inf_nan_list.append(tf.reduce_all(tf.is_finite(grad)))
      self.grad_has_inf_nan = tf.logical_not(tf.reduce_all(has_inf_nan_list))

    return tower_grad 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def preprocess_device_grads(self, device_grads):
    compact_grads = (self.benchmark_cnn.params.use_fp16 and
                     self.benchmark_cnn.params.compact_gradient_transfer)
    defer_grads = (self.benchmark_cnn.params.variable_consistency == 'relaxed')

    grads_to_reduce = [[g for g, _ in grad_vars] for grad_vars in device_grads]
    algorithm = batch_allreduce.algorithm_from_params(self.benchmark_cnn.params)
    reduced_grads, self._warmup_ops = algorithm.batch_all_reduce(
        grads_to_reduce, self.benchmark_cnn.params.gradient_repacking,
        compact_grads, defer_grads, self.benchmark_cnn.params.xla_compile)
    if self.benchmark_cnn.enable_auto_loss_scale:
      # Check for infs or nans
      is_finite_list = []
      with tf.name_scope('check_for_inf_and_nan'):
        for tower_grads in reduced_grads:
          with tf.colocate_with(tower_grads[0]):
            # TODO(tanmingxing): Create fused op that takes in a list of tensors
            # as input and returns scalar boolean True if there are any
            # infs/nans.
            is_finite_list.append(tf.reduce_all(
                [tf.reduce_all(tf.is_finite(g)) for g in tower_grads]))
        self.grad_has_inf_nan = tf.logical_not(tf.reduce_all(is_finite_list))
    reduced_device_grads = [[
        (g, v) for g, (_, v) in zip(grads, grad_vars)
    ] for grads, grad_vars in zip(reduced_grads, device_grads)]
    return self.benchmark_cnn.devices, reduced_device_grads 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def _get_cubic_root(self):
    """Get the cubic root."""
    # We have the equation x^2 D^2 + (1-x)^4 * C / h_min^2
    # where x = sqrt(mu).
    # We substitute x, which is sqrt(mu), with x = y + 1.
    # It gives y^3 + py = q
    # where p = (D^2 h_min^2)/(2*C) and q = -p.
    # We use the Vieta's substitution to compute the root.
    # There is only one real solution y (which is in [0, 1] ).
    # http://mathworld.wolfram.com/VietasSubstitution.html
    assert_array = [
        tf.Assert(
            tf.logical_not(tf.is_nan(self._dist_to_opt_avg)),
            [self._dist_to_opt_avg,]),
        tf.Assert(
            tf.logical_not(tf.is_nan(self._h_min)),
            [self._h_min,]),
        tf.Assert(
            tf.logical_not(tf.is_nan(self._grad_var)),
            [self._grad_var,]),
        tf.Assert(
            tf.logical_not(tf.is_inf(self._dist_to_opt_avg)),
            [self._dist_to_opt_avg,]),
        tf.Assert(
            tf.logical_not(tf.is_inf(self._h_min)),
            [self._h_min,]),
        tf.Assert(
            tf.logical_not(tf.is_inf(self._grad_var)),
            [self._grad_var,])
    ]
    with tf.control_dependencies(assert_array):
      p = self._dist_to_opt_avg**2 * self._h_min**2 / 2 / self._grad_var
      w3 = (-tf.sqrt(p**2 + 4.0 / 27.0 * p**3) - p) / 2.0
      w = tf.sign(w3) * tf.pow(tf.abs(w3), 1.0/3.0)
      y = w - p / 3.0 / w
      x = y + 1
    return x 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def get_gan_loss(self, true_frames, gen_frames, name):
    """Get the discriminator + generator loss at every step.

    This performs an 1:1 update of the discriminator and generator at every
    step.

    Args:
      true_frames: 5-D Tensor of shape (num_steps, batch_size, H, W, C)
                   Assumed to be ground truth.
      gen_frames: 5-D Tensor of shape (num_steps, batch_size, H, W, C)
                  Assumed to be fake.
      name: discriminator scope.
    Returns:
      loss: 0-D Tensor, with d_loss + g_loss
    """
    # D - STEP
    with tf.variable_scope("%s_discriminator" % name, reuse=tf.AUTO_REUSE):
      gan_d_loss, _, fake_logits_stop = self.d_step(
          true_frames, gen_frames)

    # G - STEP
    with tf.variable_scope("%s_discriminator" % name, reuse=True):
      gan_g_loss_pos_d, gan_g_loss_neg_d = self.g_step(
          gen_frames, fake_logits_stop)
    gan_g_loss = gan_g_loss_pos_d + gan_g_loss_neg_d
    tf.summary.scalar("gan_loss_%s" % name, gan_g_loss_pos_d + gan_d_loss)

    if self.hparams.gan_optimization == "joint":
      gan_loss = gan_g_loss + gan_d_loss
    else:
      curr_step = self.get_iteration_num()
      gan_loss = tf.cond(
          tf.logical_not(curr_step % 2 == 0), lambda: gan_g_loss,
          lambda: gan_d_loss)
    return gan_loss 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import logical_not [as 别名]
def get_scheduled_sample_inputs(self,
                                  done_warm_start,
                                  groundtruth_items,
                                  generated_items,
                                  scheduled_sampling_func):
    """Scheduled sampling.

    Args:
      done_warm_start: whether we are done with warm start or not.
      groundtruth_items: list of ground truth items.
      generated_items: list of generated items.
      scheduled_sampling_func: scheduled sampling function to choose between
        groundtruth items and generated items.

    Returns:
      A mix list of ground truth and generated items.
    """
    def sample():
      """Calculate the scheduled sampling params based on iteration number."""
      with tf.variable_scope("scheduled_sampling", reuse=tf.AUTO_REUSE):
        return [
            scheduled_sampling_func(item_gt, item_gen)
            for item_gt, item_gen in zip(groundtruth_items, generated_items)]

    cases = [
        (tf.logical_not(done_warm_start), lambda: groundtruth_items),
        (tf.logical_not(self.is_training), lambda: generated_items),
    ]
    output_items = tf.case(cases, default=sample, strict=True)

    return output_items