Python v1.ones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 ones [as 别名]
def _ensure_keep_mask(self, x):
    if self._keep_mask is None or not self._share_mask:
      shape = tf.shape(x)
      k = shape[1]
      # To make this class a drop-in replacement for bernoulli dropout we
      # paramaterize it with keep_prob. Set alpha of the dirichlet so that the
      # variance is equal to the variance of the bernoulli with p=keep_prob
      # divided by keep_prob.
      # Now the variance of the dirichlet with k equal alphas is
      # (k-1)/(k^2(k*alpha+1). Solve that for alpha.
      kf = tf.cast(k, tf.float32)
      alpha = self._keep_prob * (kf - 1.0) / ((1-self._keep_prob)*kf) - 1.0/kf
      dist = tfp.distributions.Dirichlet(tf.ones(shape=k) * alpha)
      assert (dist.reparameterization_type ==
              tfp.distributions.FULLY_REPARAMETERIZED)
      # The E[dir(alpha)] = 1/k for all elements, but we want the expectation to
      # be keep_prob, hence the multiplication.
      self._keep_mask = kf * dist.sample(shape[0])
      self._keep_mask.set_shape(x.get_shape())
    return self._keep_mask 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def uniform_binning_correction(x, n_bits=8):
  """Replaces x^i with q^i(x) = U(x, x + 1.0 / 256.0).

  Args:
    x: 4-D Tensor of shape (NHWC)
    n_bits: optional.
  Returns:
    x: x ~ U(x, x + 1.0 / 256)
    objective: Equivalent to -q(x)*log(q(x)).
  """
  n_bins = 2**n_bits
  batch_size, height, width, n_channels = common_layers.shape_list(x)
  hwc = float(height * width * n_channels)

  x = x + tf.random_uniform(
      shape=(batch_size, height, width, n_channels),
      minval=0.0, maxval=1.0/n_bins)
  objective = -np.log(n_bins) * hwc * tf.ones(batch_size)
  return x, objective 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def compute_last_embedding(input_embeddings, input_lengths, hparams):
  """Computes average of last K embedding.

  Args:
    input_embeddings: <tf.float32>[bs, max_seq_len, emb_dim]
    input_lengths: <tf.int64>[bs, 1]
    hparams: model hparams

  Returns:
    last_k_embedding: <tf.float32>[bs, emb_dim]
  """
  max_seq_len = tf.shape(input_embeddings)[1]
  # <tf.float32>[bs, 1, max_seq_len]
  mask = tf.sequence_mask(input_lengths, max_seq_len, dtype=tf.float32)
  del_mask = tf.sequence_mask(
      input_lengths - hparams.last_k, max_seq_len, dtype=tf.float32)
  final_mask = mask - del_mask
  # <tf.float32>[bs, 1, emb_dim]
  sum_embedding = tf.matmul(final_mask, input_embeddings)
  # <tf.float32>[bs, 1, emb_dim]
  last_k_embedding = sum_embedding / tf.to_float(
      tf.expand_dims(
          tf.ones([tf.shape(input_embeddings)[0], 1]) * hparams.last_k, 2))
  # <tf.float32>[bs, dim]
  return tf.squeeze(last_k_embedding, 1) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def testLossCostDecorated(self):
    image = tf.constant(0.0, shape=[1, 3, 3, 3])
    kernel = tf.ones([1, 1, 3, 2])

    pred = tf.nn.conv2d(image, kernel, strides=[1, 1, 1, 1], padding='SAME')
    conv = pred.op

    self.group_lasso_reg = flop_regularizer.GroupLassoFlopsRegularizer(
        [conv],
        0.1,
        l1_fraction=0,
        regularizer_decorator=dummy_decorator.DummyDecorator,
        decorator_parameters={'scale': 0.5})
    # we compare the computed cost and regularization calculated as follows:
    # reg_term = op_coeff * (number_of_inputs * (regularization=2 * 0.5) +
    # number_of_outputs * (input_regularization=0))
    # number_of_flops = coeff * number_of_inputs * number_of_outputs.
    with self.cached_session():
      pred_reg = self.group_lasso_reg.get_regularization_term([conv]).eval()
      self.assertEqual(_coeff(conv) * 3 * 1, pred_reg)
      pred_cost = self.group_lasso_reg.get_cost([conv]).eval()
      self.assertEqual(_coeff(conv) * 2 * NUM_CHANNELS, pred_cost) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def __init__(self, regularizers_to_group):
    """Creates an instance.

    Args:
      regularizers_to_group: A list of generic_regularizers.OpRegularizer
        objects.Their regularization_vector (alive_vector) are expected to be of
        the same length.

    Raises:
      ValueError: regularizers_to_group is not of length at least 2.
    """
    if len(regularizers_to_group) < 2:
      raise ValueError('Groups must be of at least size 2.')
    self._regularization_vector = tf.add_n(
        [r.regularization_vector for r in regularizers_to_group])
    self._alive_vector = tf.cast(
        tf.ones(self._regularization_vector.get_shape()[-1]), tf.bool) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def sample(self, n, max_length=None, z=None, c_input=None, **kwargs):
    """Sample with an optional conditional embedding `z`."""
    if z is not None and int(z.shape[0]) != n:
      raise ValueError(
          '`z` must have a first dimension that equals `n` when given. '
          'Got: %d vs %d' % (z.shape[0], n))

    if self.hparams.z_size and z is None:
      tf.logging.warning(
          'Sampling from conditional model without `z`. Using random `z`.')
      normal_shape = [n, self.hparams.z_size]
      normal_dist = tfp.distributions.Normal(
          loc=tf.zeros(normal_shape), scale=tf.ones(normal_shape))
      z = normal_dist.sample()

    return self.decoder.sample(n, max_length, z, c_input, **kwargs) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def scalar_concat(tensor, scalar):
  """Concatenates a scalar to the last dimension of a tensor.

  Args:
    tensor: A `Tensor`.
    scalar: a scalar `Tensor` to concatenate to tensor `tensor`.

  Returns:
    A `Tensor`. If `tensor` has shape [...,N], the result R has shape
    [...,N+1] and R[...,N] = scalar.

  Raises:
    ValueError: If `tensor` is a scalar `Tensor`.
  """
  ndims = tensor.shape.ndims
  if ndims < 1:
    raise ValueError('`tensor` must have number of dimensions >= 1.')
  shape = tf.shape(tensor)
  return tf.concat(
      [tensor,
       tf.ones([shape[i] for i in range(ndims - 1)] + [1]) * scalar],
      axis=ndims - 1) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def nearest_upsampling(data, height_scale, width_scale, data_format):
  """Nearest neighbor upsampling implementation."""
  with tf.name_scope('nearest_upsampling'):
    # Use reshape to quickly upsample the input. The nearest pixel is selected
    # implicitly via broadcasting.
    if data_format == 'channels_first':
      # Possibly faster for certain GPUs only.
      bs, c, h, w = data.get_shape().as_list()
      bs = -1 if bs is None else bs
      data = tf.reshape(data, [bs, c, h, 1, w, 1]) * tf.ones(
          [1, 1, 1, height_scale, 1, width_scale], dtype=data.dtype)
      return tf.reshape(data, [bs, c, h * height_scale, w * width_scale])

    # Normal format for CPU/TPU/GPU.
    bs, h, w, c = data.get_shape().as_list()
    bs = -1 if bs is None else bs
    data = tf.reshape(data, [bs, h, 1, w, 1, c]) * tf.ones(
        [1, 1, height_scale, 1, width_scale, 1], dtype=data.dtype)
    return tf.reshape(data, [bs, h * height_scale, w * width_scale, c]) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def pad_to_fixed_size(data, pad_value, output_shape):
  """Pad data to a fixed length at the first dimension.

  Args:
    data: Tensor to be padded to output_shape.
    pad_value: A constant value assigned to the paddings.
    output_shape: The output shape of a 2D tensor.

  Returns:
    The Padded tensor with output_shape [max_num_instances, dimension].
  """
  max_num_instances = output_shape[0]
  dimension = output_shape[1]
  data = tf.reshape(data, [-1, dimension])
  num_instances = tf.shape(data)[0]
  assert_length = tf.Assert(
      tf.less_equal(num_instances, max_num_instances), [num_instances])
  with tf.control_dependencies([assert_length]):
    pad_length = max_num_instances - num_instances
  paddings = pad_value * tf.ones([pad_length, dimension])
  padded_data = tf.concat([data, paddings], axis=0)
  padded_data = tf.reshape(padded_data, output_shape)
  return padded_data 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def test_output_size_nn_upsample_conv(self):
    batch_size = 2
    height, width = 256, 256
    num_outputs = 4

    images = tf.ones((batch_size, height, width, 3))
    with slim.arg_scope(pix2pix.pix2pix_arg_scope()):
      logits, _ = pix2pix.pix2pix_generator(
          images, num_outputs, blocks=self._reduced_default_blocks(),
          upsample_method='nn_upsample_conv')

    with self.test_session() as session:
      session.run(tf.global_variables_initializer())
      np_outputs = session.run(logits)
      self.assertListEqual([batch_size, height, width, num_outputs],
                           list(np_outputs.shape)) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def test_output_size_conv2d_transpose(self):
    batch_size = 2
    height, width = 256, 256
    num_outputs = 4

    images = tf.ones((batch_size, height, width, 3))
    with slim.arg_scope(pix2pix.pix2pix_arg_scope()):
      logits, _ = pix2pix.pix2pix_generator(
          images, num_outputs, blocks=self._reduced_default_blocks(),
          upsample_method='conv2d_transpose')

    with self.test_session() as session:
      session.run(tf.global_variables_initializer())
      np_outputs = session.run(logits)
      self.assertListEqual([batch_size, height, width, num_outputs],
                           list(np_outputs.shape)) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def test_block_number_dictates_number_of_layers(self):
    batch_size = 2
    height, width = 256, 256
    num_outputs = 4

    images = tf.ones((batch_size, height, width, 3))
    blocks = [
        pix2pix.Block(64, 0.5),
        pix2pix.Block(128, 0),
    ]
    with slim.arg_scope(pix2pix.pix2pix_arg_scope()):
      _, end_points = pix2pix.pix2pix_generator(
          images, num_outputs, blocks)

    num_encoder_layers = 0
    num_decoder_layers = 0
    for end_point in end_points:
      if end_point.startswith('encoder'):
        num_encoder_layers += 1
      elif end_point.startswith('decoder'):
        num_decoder_layers += 1

    self.assertEqual(num_encoder_layers, len(blocks))
    self.assertEqual(num_decoder_layers, len(blocks)) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def test_four_layers(self):
    batch_size = 2
    input_size = 256

    output_size = self._layer_output_size(input_size)
    output_size = self._layer_output_size(output_size)
    output_size = self._layer_output_size(output_size)
    output_size = self._layer_output_size(output_size, stride=1)
    output_size = self._layer_output_size(output_size, stride=1)

    images = tf.ones((batch_size, input_size, input_size, 3))
    with slim.arg_scope(pix2pix.pix2pix_arg_scope()):
      logits, end_points = pix2pix.pix2pix_discriminator(
          images, num_filters=[64, 128, 256, 512])
    self.assertListEqual([batch_size, output_size, output_size, 1],
                         logits.shape.as_list())
    self.assertListEqual([batch_size, output_size, output_size, 1],
                         end_points['predictions'].shape.as_list()) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def native_crop_and_resize(image, boxes, crop_size, scope=None):
  """Same as `matmul_crop_and_resize` but uses tf.image.crop_and_resize."""
  def get_box_inds(proposals):
    proposals_shape = proposals.shape.as_list()
    if any(dim is None for dim in proposals_shape):
      proposals_shape = tf.shape(proposals)
    ones_mat = tf.ones(proposals_shape[:2], dtype=tf.int32)
    multiplier = tf.expand_dims(
        tf.range(start=0, limit=proposals_shape[0]), 1)
    return tf.reshape(ones_mat * multiplier, [-1])

  with tf.name_scope(scope, 'CropAndResize'):
    cropped_regions = tf.image.crop_and_resize(
        image, tf.reshape(boxes, [-1] + boxes.shape.as_list()[2:]),
        get_box_inds(boxes), crop_size)
    final_shape = tf.concat([tf.shape(boxes)[:2],
                             tf.shape(cropped_regions)[1:]], axis=0)
    return tf.reshape(cropped_regions, final_shape) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import ones [as 别名]
def expanded_shape(orig_shape, start_dim, num_dims):
  """Inserts multiple ones into a shape vector.

  Inserts an all-1 vector of length num_dims at position start_dim into a shape.
  Can be combined with tf.reshape to generalize tf.expand_dims.

  Args:
    orig_shape: the shape into which the all-1 vector is added (int32 vector)
    start_dim: insertion position (int scalar)
    num_dims: length of the inserted all-1 vector (int scalar)
  Returns:
    An int32 vector of length tf.size(orig_shape) + num_dims.
  """
  with tf.name_scope('ExpandedShape'):
    start_dim = tf.expand_dims(start_dim, 0)  # scalar to rank-1
    before = tf.slice(orig_shape, [0], start_dim)
    add_shape = tf.ones(tf.reshape(num_dims, [1]), dtype=tf.int32)
    after = tf.slice(orig_shape, start_dim, [-1])
    new_shape = tf.concat([before, add_shape, after], 0)
    return new_shape