Python tensorflow.python.ops.math_ops 模块，rsqrt() 实例源码

def _sample_n(self, n, seed=None):
    # The sampling method comes from the fact that if:
    #   X ~ Normal(0, 1)
    #   Z ~ Chi2(df)
    #   Y = X / sqrt(Z / df)
    # then:
    #   Y ~ StudentT(df).
    shape = array_ops.concat([[n], self.batch_shape()], 0)
    normal_sample = random_ops.random_normal(shape, dtype=self.dtype, seed=seed)
    df = self.df * array_ops.ones(self.batch_shape(), dtype=self.dtype)
    gamma_sample = random_ops.random_gamma(
        [n],
        0.5 * df,
        beta=0.5,
        dtype=self.dtype,
        seed=distribution_util.gen_new_seed(seed, salt="student_t"))
    samples = normal_sample * math_ops.rsqrt(gamma_sample / df)
    return samples * self.scale + self.loc  # Abs(scale) not wanted.

def _layer_norm_compute_python(x, epsilon, scale, bias):
    """Layer norm raw computation."""
    mean = tf.reduce_mean(x, axis=[-1], keep_dims=True)
    variance = tf.reduce_mean(tf.square(x - mean), axis=[-1], keep_dims=True)
    norm_x = (x - mean) * tf.rsqrt(variance + epsilon)

    return norm_x * scale + bias

def setUp(self):
    super(CoreUnaryOpsTest, self).setUp()

    self.ops = [
        ('abs', operator.abs, math_ops.abs, core.abs_function),
        ('neg', operator.neg, math_ops.negative, core.neg),
        # TODO(shoyer): add unary + to core TensorFlow
        ('pos', None, None, None),
        ('sign', None, math_ops.sign, core.sign),
        ('reciprocal', None, math_ops.reciprocal, core.reciprocal),
        ('square', None, math_ops.square, core.square),
        ('round', None, math_ops.round, core.round_function),
        ('sqrt', None, math_ops.sqrt, core.sqrt),
        ('rsqrt', None, math_ops.rsqrt, core.rsqrt),
        ('log', None, math_ops.log, core.log),
        ('exp', None, math_ops.exp, core.exp),
        ('log', None, math_ops.log, core.log),
        ('ceil', None, math_ops.ceil, core.ceil),
        ('floor', None, math_ops.floor, core.floor),
        ('cos', None, math_ops.cos, core.cos),
        ('sin', None, math_ops.sin, core.sin),
        ('tan', None, math_ops.tan, core.tan),
        ('acos', None, math_ops.acos, core.acos),
        ('asin', None, math_ops.asin, core.asin),
        ('atan', None, math_ops.atan, core.atan),
        ('lgamma', None, math_ops.lgamma, core.lgamma),
        ('digamma', None, math_ops.digamma, core.digamma),
        ('erf', None, math_ops.erf, core.erf),
        ('erfc', None, math_ops.erfc, core.erfc),
        ('lgamma', None, math_ops.lgamma, core.lgamma),
    ]
    total_size = np.prod([v.size for v in self.original_lt.axes.values()])
    self.test_lt = core.LabeledTensor(
        math_ops.cast(self.original_lt, dtypes.float32) / total_size,
        self.original_lt.axes)

def _variance_scale_term(self):
    """Helper to `_covariance` and `_variance` which computes a shared scale."""
    return math_ops.rsqrt(1. + self.alpha_sum[..., None])

def __call__(self, query, previous_alignments):
    """Score the query based on the keys and values.

    Args:
      query: Tensor of dtype matching `self.values` and shape
        `[batch_size, query_depth]`.
      previous_alignments: Tensor of dtype matching `self.values` and shape
        `[batch_size, alignments_size]`
        (`alignments_size` is memory's `max_time`).

    Returns:
      alignments: Tensor of dtype matching `self.values` and shape
        `[batch_size, alignments_size]` (`alignments_size` is memory's
        `max_time`).
    """
    with variable_scope.variable_scope(None, "bahdanau_attention", [query]):
      processed_query = self.query_layer(query) if self.query_layer else query
      # Reshape from [batch_size, ...] to [batch_size, 1, ...] for broadcasting.
      processed_query = array_ops.expand_dims(processed_query, 1)
      keys = self._keys
      dtype = query.dtype
      v = variable_scope.get_variable(
              "attention_v", [self._num_units], dtype=dtype)


      if self._normalize:
        # Scalar used in weight normalization
        g = variable_scope.get_variable(
            "attention_g", dtype=dtype,
            initializer=math.sqrt((1. / self._num_units)))

        # normed_v = g * v / ||v||
        normed_v = g * v * math_ops.rsqrt(
            math_ops.reduce_sum(math_ops.square(v)))
        score = math_ops.reduce_sum(
            normed_v * math_ops.tanh(keys + processed_query + b), [2])
      else:
        score = math_ops.reduce_sum(v * math_ops.tanh(keys + processed_query),
                                    [2])

    alignments = self._probability_fn(score, previous_alignments)
    return alignments, self.mask_func(score)