Python v1.sin方法代碼示例

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sin [as 別名]
def get_timing_signal(length,
                      min_timescale=1,
                      max_timescale=1e4,
                      num_timescales=16):
  """Create Tensor of sinusoids of different frequencies.

  Args:
    length: Length of the Tensor to create, i.e. Number of steps.
    min_timescale: a float
    max_timescale: a float
    num_timescales: an int

  Returns:
    Tensor of shape (length, 2*num_timescales)
  """
  positions = to_float(tf.range(length))
  log_timescale_increment = (
      math.log(max_timescale / min_timescale) / (num_timescales - 1))
  inv_timescales = min_timescale * tf.exp(
      to_float(tf.range(num_timescales)) * -log_timescale_increment)
  scaled_time = tf.expand_dims(positions, 1) * tf.expand_dims(inv_timescales, 0)
  return tf.concat([tf.sin(scaled_time), tf.cos(scaled_time)], axis=1) 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sin [as 別名]
def get_timing_signal(length,
                      min_timescale=1,
                      max_timescale=1e4,
                      num_timescales=16):
  """Create Tensor of sinusoids of different frequencies.

  Args:
    length: Length of the Tensor to create, i.e. Number of steps.
    min_timescale: a float
    max_timescale: a float
    num_timescales: an int
  Returns:
    Tensor of shape [length, 2 * num_timescales].
  """
  positions = tf.to_float(tf.range(length))
  log_timescale_increment = (
      math.log(max_timescale / min_timescale) / (num_timescales - 1))
  inv_timescales = min_timescale * tf.exp(
      tf.to_float(tf.range(num_timescales)) * -log_timescale_increment)
  scaled_time = tf.expand_dims(positions, 1) * tf.expand_dims(inv_timescales, 0)
  return tf.concat([tf.sin(scaled_time), tf.cos(scaled_time)], axis=1) 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sin [as 別名]
def test_forward_unary():
    def _test_forward_unary(op, a_min=1, a_max=5, dtype=np.float32):
        """test unary operators"""
        np_data = np.random.uniform(a_min, a_max, size=(2, 3, 5)).astype(dtype)
        tf.reset_default_graph()
        with tf.Graph().as_default():
            in_data = tf.placeholder(dtype, (2, 3, 5), name="in_data")
            out = op(in_data)
            compare_tf_with_tvm([np_data], ['in_data:0'], out.name)

    _test_forward_unary(tf.acos, -1, 1)
    _test_forward_unary(tf.asin, -1, 1)
    _test_forward_unary(tf.atanh, -1, 1)
    _test_forward_unary(tf.sinh)
    _test_forward_unary(tf.cosh)
    _test_forward_unary(tf.acosh)
    _test_forward_unary(tf.asinh)
    _test_forward_unary(tf.atan)
    _test_forward_unary(tf.sin)
    _test_forward_unary(tf.cos)
    _test_forward_unary(tf.tan)
    _test_forward_unary(tf.tanh)
    _test_forward_unary(tf.erf)
    _test_forward_unary(tf.log)
    _test_forward_unary(tf.log1p) 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sin [as 別名]
def add_timing_signal(x, min_timescale=1, max_timescale=1e4, num_timescales=16):
  """Adds a bunch of sinusoids of different frequencies to a Tensor.

  This allows attention to learn to use absolute and relative positions.
  The timing signal should be added to some precursor of both the source
  and the target of the attention.

  The use of relative position is possible because sin(x+y) and cos(x+y) can be
  expressed in terms of y, sin(x) and cos(x).

  In particular, we use a geometric sequence of timescales starting with
  min_timescale and ending with max_timescale.  For each timescale, we
  generate the two sinusoidal signals sin(timestep/timescale) and
  cos(timestep/timescale).  All of these sinusoids are concatenated in
  the depth dimension, padded with zeros to be the same depth as the input,
  and added into input.

  Args:
    x: a Tensor with shape [?, length, ?, depth]
    min_timescale: a float
    max_timescale: a float
    num_timescales: an int <= depth/2

  Returns:
    a Tensor the same shape as x.
  """
  length = shape_list(x)[1]
  depth = shape_list(x)[3]
  signal = get_timing_signal(length, min_timescale, max_timescale,
                             num_timescales)
  padded_signal = tf.pad(signal, [[0, 0], [0, depth - 2 * num_timescales]])
  return x + tf.reshape(padded_signal, [1, length, 1, depth]) 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sin [as 別名]
def _compute_sdf(self, x, translations, blend_terms, points):
    """Compute signed distances between query points and hyperplanes."""
    n_parts = tf.shape(x)[1]
    n_planes = tf.shape(x)[2]
    norm_logit = x[..., 0:self._dims - 1]
    offset = (-(tf.nn.sigmoid(x[..., self._dims - 1:self._dims]) *
                self._offset_scale + self._offset_lbound))
    blend_planes = (
        tf.nn.sigmoid(blend_terms[..., :n_parts]) * self._blend_scale +
        self._blend_lbound)

    # Norm of the boundary line
    norm_rad = tf.tanh(norm_logit) * np.pi  # [..., (azimuth, altitude)]
    if self._dims == 3:
      norm = tf.stack([
          tf.sin(norm_rad[..., 1]) * tf.cos(norm_rad[..., 0]),
          tf.sin(norm_rad[..., 1]) * tf.sin(norm_rad[..., 0]),
          tf.cos(norm_rad[..., 1])
      ],
                      axis=-1)
    else:
      norm = tf.concat([tf.cos(norm_rad), tf.sin(norm_rad)], axis=-1)

    # Calculate signed distances to hyperplanes.
    points = (
        tf.expand_dims(points, axis=1) - tf.expand_dims(translations, axis=2))
    points = tf.expand_dims(points, axis=2)
    points = tf.tile(points, [1, 1, n_planes, 1, 1])
    signed_dis = tf.matmul(points, tf.expand_dims(norm, axis=-1))
    signed_dis = signed_dis + tf.expand_dims(offset, axis=-2)

    return signed_dis, translations, blend_planes, offset 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sin [as 別名]
def get_timing_signal_1d_given_position(channels,
                                        position,
                                        min_timescale=1.0,
                                        max_timescale=1.0e4):
  """Get sinusoids of diff frequencies, with timing position given.

  Adapted from add_timing_signal_1d_given_position in
  //third_party/py/tensor2tensor/layers/common_attention.py

  Args:
    channels: scalar, size of timing embeddings to create. The number of
        different timescales is equal to channels / 2.
    position: a Tensor with shape [batch, seq_len]
    min_timescale: a float
    max_timescale: a float

  Returns:
    a Tensor of timing signals [batch, seq_len, channels]
  """
  num_timescales = channels // 2
  log_timescale_increment = (
      math.log(float(max_timescale) / float(min_timescale)) /
      (tf.to_float(num_timescales) - 1))
  inv_timescales = min_timescale * tf.exp(
      tf.to_float(tf.range(num_timescales)) * -log_timescale_increment)
  scaled_time = (
      tf.expand_dims(tf.to_float(position), 2) * tf.expand_dims(
          tf.expand_dims(inv_timescales, 0), 0))
  signal = tf.concat([tf.sin(scaled_time), tf.cos(scaled_time)], axis=2)
  signal = tf.pad(signal, [[0, 0], [0, 0], [0, tf.mod(channels, 2)]])
  return signal 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sin [as 別名]
def polar2rect(mag, phase_angle):
  """Convert polar-form complex number to its rectangular form."""
  mag = tf.complex(mag, tf.convert_to_tensor(0.0, dtype=mag.dtype))
  phase = tf.complex(tf.cos(phase_angle), tf.sin(phase_angle))
  return mag * phase 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sin [as 別名]
def _rotate_bbox(bbox, image_height, image_width, degrees):
  """Rotates the bbox coordinated by degrees.

  Args:
    bbox: 1D Tensor that has 4 elements (min_y, min_x, max_y, max_x)
      of type float that represents the normalized coordinates between 0 and 1.
    image_height: Int, height of the image.
    image_width: Int, height of the image.
    degrees: Float, a scalar angle in degrees to rotate all images by. If
      degrees is positive the image will be rotated clockwise otherwise it will
      be rotated counterclockwise.

  Returns:
    A tensor of the same shape as bbox, but now with the rotated coordinates.
  """
  image_height, image_width = (
      tf.to_float(image_height), tf.to_float(image_width))

  # Convert from degrees to radians.
  degrees_to_radians = math.pi / 180.0
  radians = degrees * degrees_to_radians

  # Translate the bbox to the center of the image and turn the normalized 0-1
  # coordinates to absolute pixel locations.
  # Y coordinates are made negative as the y axis of images goes down with
  # increasing pixel values, so we negate to make sure x axis and y axis points
  # are in the traditionally positive direction.
  min_y = -tf.to_int32(image_height * (bbox[0] - 0.5))
  min_x = tf.to_int32(image_width * (bbox[1] - 0.5))
  max_y = -tf.to_int32(image_height * (bbox[2] - 0.5))
  max_x = tf.to_int32(image_width * (bbox[3] - 0.5))
  coordinates = tf.stack(
      [[min_y, min_x], [min_y, max_x], [max_y, min_x], [max_y, max_x]])
  coordinates = tf.cast(coordinates, tf.float32)
  # Rotate the coordinates according to the rotation matrix clockwise if
  # radians is positive, else negative
  rotation_matrix = tf.stack(
      [[tf.cos(radians), tf.sin(radians)],
       [-tf.sin(radians), tf.cos(radians)]])
  new_coords = tf.cast(
      tf.matmul(rotation_matrix, tf.transpose(coordinates)), tf.int32)
  # Find min/max values and convert them back to normalized 0-1 floats.
  min_y = -(tf.to_float(tf.reduce_max(new_coords[0, :])) / image_height - 0.5)
  min_x = tf.to_float(tf.reduce_min(new_coords[1, :])) / image_width + 0.5
  max_y = -(tf.to_float(tf.reduce_min(new_coords[0, :])) / image_height - 0.5)
  max_x = tf.to_float(tf.reduce_max(new_coords[1, :])) / image_width + 0.5

  # Clip the bboxes to be sure the fall between [0, 1].
  min_y, min_x, max_y, max_x = _clip_bbox(min_y, min_x, max_y, max_x)
  min_y, min_x, max_y, max_x = _check_bbox_area(min_y, min_x, max_y, max_x)
  return tf.stack([min_y, min_x, max_y, max_x])