Python v1.abs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 abs [as 别名]
def __init__(self, pad_mask):
    """Compute and store the location of the padding.

    Args:
      pad_mask (tf.Tensor): Reference padding tensor of shape
        [batch_size,length] or [dim_origin] (dim_origin=batch_size*length)
        containing non-zeros positive values to indicate padding location.
    """
    self.nonpad_ids = None
    self.dim_origin = None

    with tf.name_scope("pad_reduce/get_ids"):
      pad_mask = tf.reshape(pad_mask, [-1])  # Flatten the batch
      # nonpad_ids contains coordinates of zeros rows (as pad_mask is
      # float32, checking zero equality is done with |x| < epsilon, with
      # epsilon=1e-9 as standard, here pad_mask only contains positive values
      # so tf.abs would be redundant)
      self.nonpad_ids = tf.to_int32(tf.where(pad_mask < 1e-9))
      self.dim_origin = tf.shape(pad_mask)[:1] 

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

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [as 别名]
def neural_gpu_body(inputs, hparams, name=None):
  """The core Neural GPU."""
  with tf.variable_scope(name, "neural_gpu"):

    def step(state, inp):  # pylint: disable=missing-docstring
      x = tf.nn.dropout(state, 1.0 - hparams.dropout)
      for layer in range(hparams.num_hidden_layers):
        x = common_layers.conv_gru(
            x, (hparams.kernel_height, hparams.kernel_width),
            hparams.hidden_size,
            name="cgru_%d" % layer)
      # Padding input is zeroed-out in the modality, we check this by summing.
      padding_inp = tf.less(tf.reduce_sum(tf.abs(inp), axis=[1, 2]), 0.00001)
      new_state = tf.where(padding_inp, state, x)  # No-op where inp is padding.
      return new_state

    return tf.foldl(
        step,
        tf.transpose(inputs, [1, 0, 2, 3]),
        initializer=inputs,
        parallel_iterations=1,
        swap_memory=True) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [as 别名]
def get_kl_loss(self, means, log_vars, means_p=None, log_vars_p=None):
    """Get KL loss for all the predicted Gaussians."""
    kl_loss = 0.0
    if means_p is None:
      means_p = tf.unstack(tf.zeros_like(means))
    if log_vars_p is None:
      log_vars_p = tf.unstack(tf.zeros_like(log_vars))
    enumerated_inputs = enumerate(zip(means, log_vars, means_p, log_vars_p))
    if self.is_training and self.hparams.stochastic_model:
      for i, (mean, log_var, mean_p, log_var_p) in enumerated_inputs:
        kl_loss += common_layers.kl_divergence(mean, log_var, mean_p, log_var_p)
        tf.summary.histogram("posterior_mean_%d" % i, mean)
        tf.summary.histogram("posterior_log_var_%d" % i, log_var)
        tf.summary.histogram("prior_mean_%d" % i, mean_p)
        tf.summary.histogram("prior_log_var_%d" % i, log_var_p)
      tf.summary.scalar("kl_raw", tf.reduce_mean(kl_loss))

    beta = self.get_beta(kl_loss)
    # information capacity from "Understanding disentangling in beta-VAE"
    if self.hparams.information_capacity > 0.0:
      kl_loss = tf.abs(kl_loss - self.hparams.information_capacity)
    return beta * kl_loss 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [as 别名]
def group_norm(x, filters=None, num_groups=8, epsilon=1e-5):
  """Group normalization as in https://arxiv.org/abs/1803.08494."""
  x_shape = shape_list(x)
  if filters is None:
    filters = x_shape[-1]
  assert len(x_shape) == 4
  assert filters % num_groups == 0
  # Prepare variables.
  scale = tf.get_variable(
      "group_norm_scale", [filters], initializer=tf.ones_initializer())
  bias = tf.get_variable(
      "group_norm_bias", [filters], initializer=tf.zeros_initializer())
  epsilon, scale, bias = [cast_like(t, x) for t in [epsilon, scale, bias]]
  # Reshape and compute group norm.
  x = tf.reshape(x, x_shape[:-1] + [num_groups, filters // num_groups])
  # Calculate mean and variance on heights, width, channels (not groups).
  mean, variance = tf.nn.moments(x, [1, 2, 4], keep_dims=True)
  norm_x = (x - mean) * tf.rsqrt(variance + epsilon)
  return tf.reshape(norm_x, x_shape) * scale + bias 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [as 别名]
def gated_linear_unit_layer(x, name=None):
  """Gated linear unit layer.

  Paper: Language Modeling with Gated Convolutional Networks.
  Link: https://arxiv.org/abs/1612.08083
  x = Wx * sigmoid(W'x).

  Args:
    x: A tensor
    name: A string

  Returns:
    A tensor of the same shape as x.
  """
  with tf.variable_scope(name, default_name="glu_layer", values=[x]):
    depth = shape_list(x)[-1]
    x = layers().Dense(depth * 2, activation=None)(x)
    x, gating_x = tf.split(x, 2, axis=-1)
    return x * tf.nn.sigmoid(gating_x) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [as 别名]
def stfts_to_specgrams(self, stfts):
    """Converts stfts to specgrams.

    Args:
      stfts: Complex64 tensor of stft, shape [batch, time, freq, 1].

    Returns:
      specgrams: Tensor of log magnitudes and instantaneous frequencies,
        shape [batch, time, freq, 2].
    """
    stfts = stfts[:, :, :, 0]

    logmag = self._safe_log(tf.abs(stfts))

    phase_angle = tf.angle(stfts)
    if self._ifreq:
      p = spectral_ops.instantaneous_frequency(phase_angle)
    else:
      p = phase_angle / np.pi

    return tf.concat(
        [logmag[:, :, :, tf.newaxis], p[:, :, :, tf.newaxis]], axis=-1) 

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

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [as 别名]
def apply_batch_norm(self, wrapper, mean, variance, scale, bias, epsilon):
    # Element-wise multiplier.
    multiplier = tf.rsqrt(variance + epsilon)
    if scale is not None:
      multiplier *= scale
    w = multiplier
    # Element-wise bias.
    b = -multiplier * mean
    if bias is not None:
      b += bias
    b = tf.squeeze(b, axis=0)
    # Because the scale might be negative, we need to apply a strategy similar
    # to linear.
    c = (self.lower + self.upper) / 2.
    r = (self.upper - self.lower) / 2.
    c = tf.multiply(c, w) + b
    r = tf.multiply(r, tf.abs(w))
    return IntervalBounds(c - r, c + r) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [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 abs [as 别名]
def get_perf_timing(batch_size, step_train_times, ewma_alpha=None, scale=1):
  """Calculate benchmark processing speed."""
  times = np.array(step_train_times)
  speeds = batch_size / times
  if ewma_alpha:
    weights = np.logspace(len(times)-1, 0, len(times), base=1-ewma_alpha)
    time_mean = np.average(times, weights=weights)
  else:
    time_mean = np.mean(times)
  speed_mean = scale * batch_size / time_mean
  speed_uncertainty = np.std(speeds) / np.sqrt(float(len(speeds)))
  speed_jitter = 1.4826 * np.median(np.abs(speeds - np.median(speeds)))
  return speed_mean, speed_uncertainty, speed_jitter 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [as 别名]
def gradient_histogram_summary(self, avg_grads):
    """Create histogram of log values of all non-zero gradients."""
    with tf.name_scope('log_gradients_summary'):
      all_grads = []
      for grad, _ in avg_grads:
        all_grads.append(tf.reshape(grad, [-1]))
      grads = tf.abs(tf.concat(all_grads, 0))
      # exclude grads with zero values.
      indices_for_non_zero_grads = tf.where(tf.not_equal(grads, 0))
      log_grads = tf.reshape(
          tf.log(tf.gather(grads, indices_for_non_zero_grads)), [-1])
      tf.summary.histogram('log_gradients', log_grads) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [as 别名]
def abs_error(predictions, labels, weights_fn=None):
  """Computes mean(abs(preds-target))."""
  del weights_fn  # Unused
  targets = tf.squeeze(labels, axis=[2, 3])
  batch_abs_error = tf.abs(predictions - targets)
  den = tf.ones(tf.shape(batch_abs_error), dtype=tf.float32)
  return (batch_abs_error, den) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [as 别名]
def variance_loss(self, b):
    part = tf.random_uniform(common_layers.shape_list(b))
    selection = tf.to_float(tf.less(part, tf.random_uniform([])))
    selection_size = tf.reduce_sum(selection)
    part_avg = tf.abs(tf.reduce_sum(b * selection)) / (selection_size + 1)
    return part_avg 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import abs [as 别名]
def lenpred_stats(targets_length_pred, targets_length):
  lenpred_diff = tf.abs(targets_length_pred - tf.cast(targets_length, tf.int32))
  lenpred_acc = tf.cast(tf.equal(lenpred_diff, 0), tf.float32)
  lenpred_acc = tf.reduce_mean(lenpred_acc)
  lenpred_acc5 = tf.cast(tf.less_equal(lenpred_diff, 5), tf.float32)
  lenpred_acc5 = tf.reduce_mean(lenpred_acc5)
  return lenpred_acc, lenpred_acc5