Python v1.cos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 cos [as 别名]
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) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
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) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
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) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
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]) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
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 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
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 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
def compute_mse_loss(x, xhat, hparams):
  """MSE loss function.

  Args:
    x: Input data tensor.
    xhat: Reconstruction tensor.
    hparams: Hyperparameters.

  Returns:
    total_loss: MSE loss scalar.
  """
  with tf.name_scope("Losses"):
    if hparams.raw_audio:
      total_loss = tf.reduce_mean((x - xhat)**2)
    else:
      # Magnitude
      m = x[:, :, :, 0] if hparams.cost_phase_mask else 1.0
      fm = utils.frequency_weighted_cost_mask(
          hparams.fw_loss_coeff,
          hz_flat=hparams.fw_loss_cutoff,
          n_fft=hparams.n_fft)
      mag_loss = tf.reduce_mean(fm * (x[:, :, :, 0] - xhat[:, :, :, 0])**2)
      if hparams.mag_only:
        total_loss = mag_loss
      else:
        # Phase
        if hparams.dphase:
          phase_loss = tf.reduce_mean(fm * m *
                                      (x[:, :, :, 1] - xhat[:, :, :, 1])**2)
        else:
          # Von Mises Distribution "Circular Normal"
          # Added constant to keep positive (Same Probability) range [0, 2]
          phase_loss = 1 - tf.reduce_mean(fm * m * tf.cos(
              (x[:, :, :, 1] - xhat[:, :, :, 1]) * np.pi))
        total_loss = mag_loss + hparams.phase_loss_coeff * phase_loss
        tf.summary.scalar("Loss/Mag", mag_loss)
        tf.summary.scalar("Loss/Phase", phase_loss)
    tf.summary.scalar("Loss/Total", total_loss)
  return total_loss 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
def build_learning_rate(initial_lr,
                        global_step,
                        steps_per_epoch=None,
                        lr_decay_type='exponential',
                        decay_factor=0.97,
                        decay_epochs=2.4,
                        total_steps=None,
                        warmup_epochs=5):
  """Build learning rate."""
  if lr_decay_type == 'exponential':
    assert steps_per_epoch is not None
    decay_steps = steps_per_epoch * decay_epochs
    lr = tf.train.exponential_decay(
        initial_lr, global_step, decay_steps, decay_factor, staircase=True)
  elif lr_decay_type == 'cosine':
    assert total_steps is not None
    lr = 0.5 * initial_lr * (
        1 + tf.cos(np.pi * tf.cast(global_step, tf.float32) / total_steps))
  elif lr_decay_type == 'constant':
    lr = initial_lr
  else:
    assert False, 'Unknown lr_decay_type : %s' % lr_decay_type

  if warmup_epochs:
    logging.info('Learning rate warmup_epochs: %d', warmup_epochs)
    warmup_steps = int(warmup_epochs * steps_per_epoch)
    warmup_lr = (
        initial_lr * tf.cast(global_step, tf.float32) / tf.cast(
            warmup_steps, tf.float32))
    lr = tf.cond(global_step < warmup_steps, lambda: warmup_lr, lambda: lr)

  return lr 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
def warmup_cosine(x, warmup=0.002):
  s = tf.cast(x <= warmup, tf.float32)
  return s*(x/warmup) + (1-s)*(0.5 * (1 + tf.cos(math.pi * x))) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
def learning_rate_factor(name, step_num, hparams):
  """Compute the designated learning rate factor from hparams."""
  if name == "constant":
    tf.logging.info("Base learning rate: %f", hparams.learning_rate_constant)
    return hparams.learning_rate_constant
  elif name == "linear_warmup":
    return tf.minimum(1.0, step_num / hparams.learning_rate_warmup_steps)
  elif name == "linear_decay":
    ret = (hparams.train_steps - step_num) / hparams.learning_rate_decay_steps
    return tf.minimum(1.0, tf.maximum(0.0, ret))
  elif name == "cosdecay":  # openai gpt
    in_warmup = tf.cast(step_num <= hparams.learning_rate_warmup_steps,
                        dtype=tf.float32)
    ret = 0.5 * (1 + tf.cos(
        np.pi * step_num / hparams.learning_rate_decay_steps))
    # if in warmup stage return 1 else return the decayed value
    return in_warmup * 1 + (1 - in_warmup) * ret
  elif name == "single_cycle_cos_decay":
    # Cosine decay to zero with a single cycle. This is different from
    # "cosdecay" because it starts at 1 when the warmup steps end.
    x = tf.maximum(step_num, hparams.learning_rate_warmup_steps)
    step = x - hparams.learning_rate_warmup_steps
    if hparams.train_steps <= hparams.learning_rate_warmup_steps:
      raise ValueError("single_cycle_cos_decay cannot be used unless "
                       "hparams.train_steps > "
                       "hparams.learning_rate_warmup_steps")
    return tf.math.cos(
        step * np.pi /
        (hparams.train_steps - hparams.learning_rate_warmup_steps)) / 2.0 + 0.5
  elif name == "multi_cycle_cos_decay":
    # Cosine decay with a variable number of cycles. This is different from
    # "cosdecay" because it starts at 1 when the warmup steps end. Use
    # hparams.learning_rate_decay_steps to determine the number of cycles.
    x = tf.maximum(step_num, hparams.learning_rate_warmup_steps)
    step = x - hparams.learning_rate_warmup_steps
    return tf.math.cos(
        step * np.pi / hparams.learning_rate_decay_steps) / 2.0 + 0.5
  elif name == "rsqrt_decay":
    return tf.rsqrt(tf.maximum(step_num, hparams.learning_rate_warmup_steps))
  elif name == "rsqrt_normalized_decay":
    scale = tf.sqrt(tf.to_float(hparams.learning_rate_warmup_steps))
    return scale * tf.rsqrt(tf.maximum(
        step_num, hparams.learning_rate_warmup_steps))
  elif name == "exp_decay":
    decay_steps = hparams.learning_rate_decay_steps
    warmup_steps = hparams.learning_rate_warmup_steps
    p = (step_num - warmup_steps) / decay_steps
    p = tf.maximum(p, 0.)
    if hparams.learning_rate_decay_staircase:
      p = tf.floor(p)
    return tf.pow(hparams.learning_rate_decay_rate, p)
  elif name == "rsqrt_hidden_size":
    return hparams.hidden_size ** -0.5
  elif name == "legacy":
    return legacy_learning_rate_schedule(hparams)
  else:
    raise ValueError("unknown learning rate factor %s" % name) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
def _learning_rate_decay(hparams, warmup_steps=0):
  """Learning rate decay multiplier."""
  scheme = hparams.learning_rate_decay_scheme
  warmup_steps = tf.to_float(warmup_steps)
  global_step = _global_step(hparams)

  if not scheme or scheme == "none":
    return tf.constant(1.)

  tf.logging.info("Applying learning rate decay: %s.", scheme)

  if scheme == "exp":
    decay_steps = hparams.learning_rate_decay_steps
    p = (global_step - warmup_steps) / decay_steps
    if hparams.learning_rate_decay_staircase:
      p = tf.floor(p)
    return tf.pow(hparams.learning_rate_decay_rate, p)

  if scheme == "piecewise":
    return _piecewise_learning_rate(global_step,
                                    hparams.learning_rate_boundaries,
                                    hparams.learning_rate_multiples)

  if scheme == "cosine":
    cycle_steps = hparams.learning_rate_cosine_cycle_steps
    cycle_position = global_step % (2 * cycle_steps)
    cycle_position = cycle_steps - tf.abs(cycle_steps - cycle_position)
    return 0.5 * (1 + tf.cos(np.pi * cycle_position / cycle_steps))

  if scheme == "cyclelinear10x":
    # Cycle the rate linearly by 10x every warmup_steps, up and down.
    cycle_steps = warmup_steps
    cycle_position = global_step % (2 * cycle_steps)
    cycle_position = tf.to_float(  # Normalize to the interval [-1, 1].
        cycle_position - cycle_steps) / float(cycle_steps)
    cycle_position = 1.0 - tf.abs(cycle_position)  # 0 to 1 and back to 0.
    return (cycle_position + 0.1) * 3.0  # 10x difference each cycle (0.3-3).

  if scheme == "sqrt":
    return _legacy_sqrt_decay(global_step - warmup_steps)

  raise ValueError("Unrecognized learning rate decay scheme: %s" %
                   hparams.learning_rate_decay_scheme) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import cos [as 别名]
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])