Python v1.sign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 sign [as 別名]
def _quantize(x, params, randomize=True):
  """Quantize x according to params, optionally randomizing the rounding."""
  if not params.quantize:
    return x

  if not randomize:
    return tf.bitcast(
        tf.cast(x / params.quantization_scale, tf.int16), tf.float16)

  abs_x = tf.abs(x)
  sign_x = tf.sign(x)
  y = abs_x / params.quantization_scale
  y = tf.floor(y + tf.random_uniform(common_layers.shape_list(x)))
  y = tf.minimum(y, tf.int16.max) * sign_x
  q = tf.bitcast(tf.cast(y, tf.int16), tf.float16)
  return q 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
def _to_bfloat16_unbiased(x, noise):
  """Convert a float32 to a bfloat16 using randomized roundoff.

  Args:
    x: A float32 Tensor.
    noise: a float32 Tensor with values in [0, 1), broadcastable to tf.shape(x)
  Returns:
    A float32 Tensor.
  """
  x_sign = tf.sign(x)
  # Make sure x is positive.  If it is zero, the two candidates are identical.
  x = x * x_sign + 1e-30
  cand1 = tf.to_bfloat16(x)
  cand1_f = tf.to_float(cand1)
  # This relies on the fact that for a positive bfloat16 b,
  # b * 1.005 gives you the next higher bfloat16 and b*0.995 gives you the
  # next lower one. Both 1.005 and 0.995 are ballpark estimation.
  cand2 = tf.to_bfloat16(
      tf.where(tf.greater(x, cand1_f), cand1_f * 1.005, cand1_f * 0.995))
  ret = _randomized_roundoff_to_bfloat16(x, noise, cand1, cand2)
  return ret * tf.to_bfloat16(x_sign) 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
def mu_law(x, mu=255, int8=False):
  """A TF implementation of Mu-Law encoding.

  Args:
    x: The audio samples to encode.
    mu: The Mu to use in our Mu-Law.
    int8: Use int8 encoding.

  Returns:
    out: The Mu-Law encoded int8 data.
  """
  out = tf.sign(x) * tf.log(1 + mu * tf.abs(x)) / np.log(1 + mu)
  out = tf.floor(out * 128)
  if int8:
    out = tf.cast(out, tf.int8)
  return out 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
def hamming_loss(preds, targets, sign=False):
  """Implements hamming loss.

  Args:
    preds: Tensor of predicted values.
    targets: Tensor of target values.
    sign (bool): Set to True if targets={-1, 1} to take the sign of preds
    before calculating loss.

  Returns:
    A tf.metrics tuple containing the proportion of incorrect predictions and an
    update op for the metric.
  """
  if sign:
    preds = tf.sign(preds)
  equal = tf.equal(preds, tf.cast(targets, preds.dtype))
  proportion_correct, update_op = tf.metrics.mean(tf.cast(equal, tf.float32))
  return 1 - proportion_correct, update_op 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
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 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
def encode(self, x, noise):
    x = tf.to_float(x)
    # we can't use tf.pow(..., 8.0) because of a high-error approximation
    # on TPU.  Instead we square three times.
    x = tf.sign(x) * tf.square(tf.square(tf.square(tf.abs(x) * 128.0)))
    x = _to_bfloat16_unbiased(x, noise)
    return x 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
def decode(self, x):
    x = tf.to_float(x)
    # we can't use tf.pow(..., 0.125) because of a high-error approximation
    # on TPU.  Instead we sqrt three times.
    return tf.sign(x) * (tf.sqrt(tf.sqrt(tf.sqrt(tf.abs(x)))) / 128.0) 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
def inv_mu_law(x, mu=255):
  """A TF implementation of inverse Mu-Law.

  Args:
    x: The Mu-Law samples to decode.
    mu: The Mu we used to encode these samples.

  Returns:
    out: The decoded data.
  """
  x = tf.cast(x, tf.float32)
  out = (x + 0.5) * 2. / (mu + 1)
  out = tf.sign(out) / mu * ((1 + mu)**tf.abs(out) - 1)
  out = tf.where(tf.equal(x, 0), x, out)
  return out 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
def inv_mu_law_numpy(x, mu=255.0):
  """A numpy implementation of inverse Mu-Law.

  Args:
    x: The Mu-Law samples to decode.
    mu: The Mu we used to encode these samples.

  Returns:
    out: The decoded data.
  """
  x = np.array(x).astype(np.float32)
  out = (x + 0.5) * 2. / (mu + 1)
  out = np.sign(out) / mu * ((1 + mu)**np.abs(out) - 1)
  out = np.where(np.equal(x, 0), x, out)
  return out 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
def minimize(self, loss, x, optim_state):
    """Refer to parent class documentation."""
    lr = self._lr_fn(optim_state.iteration)
    grads = self.gradients(loss, x)
    if self._fgsm:
      grads = [tf.sign(g) for g in grads]
    new_x = [None] * len(x)
    for i in range(len(x)):
      new_x[i] = x[i] - lr * grads[i]
    new_optim_state = self._State(optim_state.iteration + 1)
    return new_x, new_optim_state 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
def test_forward_sign():
    """test Sign"""
    np_data = np.random.uniform(-10, 10, size=(5, 7, 11)).astype(np.float32)
    tf.reset_default_graph()
    with tf.Graph().as_default():
        in_data = tf.placeholder(tf.float32, (5, 7, 11), name="in_data")
        tf.sign(in_data, name="sign")
        compare_tf_with_tvm([np_data], ['in_data:0'], 'sign:0') 

# 需要導入模塊: from tensorflow.compat import v1 [as 別名]
# 或者: from tensorflow.compat.v1 import sign [as 別名]
def optimize_feat_grid(self, point_coords, point_vals, steps=10000,
                         print_every_n_steps=1000):
    """Optimize feature grid.

    Args:
      point_coords: [npts, 3] point coordinates.
      point_vals: [npts, 1] point values.
      steps: int, number of steps for gradient descent.
      print_every_n_steps: int, print every n steps.
    Returns:

    """
    print_every_n_steps = int(print_every_n_steps)

    point_coords = point_coords.copy()
    point_vals = np.sign(point_vals.copy())

    if point_coords.ndim == 3:
      point_coords = point_coords[0]
    if point_vals.ndim == 3:
      point_vals = point_vals[0]
    elif point_vals.ndim == 1:
      point_vals = point_vals[:, np.newaxis]

    # clip
    point_coords = np.clip(point_coords, self.xmin, self.xmax)

    # shuffle points
    seq = np.random.permutation(point_coords.shape[0])
    point_coords = point_coords[seq]
    point_vals = point_vals[seq]

    point_coords = point_coords[np.newaxis]
    point_vals = point_vals[np.newaxis]

    # random point sampling function
    def random_point_sample():
      sid = np.random.choice(point_coords.shape[1]-self.npts+1)
      eid = sid + self.npts
      return point_coords[:, sid:eid], point_vals[:, sid:eid]

    with self.graph.as_default():
      for i in range(steps):
        pc, pv = random_point_sample()
        accu_, loss_, _ = self.sess.run([self.accu, self.loss, self.train_op],
                                        feed_dict={
                                            self.point_coords_ph: pc,
                                            self.point_values_ph: pv})
        if i % print_every_n_steps == 0:
          print('Step [{:6d}] Accu: {:5.4f} Loss: {:5.4f}'.format(i,
                                                                  accu_, loss_))