Python math_ops.sqrt方法代码示例

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def _apply_dense(self, grad, var):
        lr_t = math_ops.cast(self._lr_t, var.dtype.base_dtype)
        beta1_t = math_ops.cast(self._beta1_t, var.dtype.base_dtype)
        beta2_t = math_ops.cast(self._beta2_t, var.dtype.base_dtype)
        epsilon_t = math_ops.cast(self._epsilon_t, var.dtype.base_dtype)

        # the following equations given in [1]
        # m_t = beta1 * m + (1 - beta1) * g_t
        m = self.get_slot(var, "m")
        m_t = state_ops.assign(m, beta1_t * m + (1. - beta1_t) * grad, use_locking=self._use_locking)

        # v_t = beta2 * v + (1 - beta2) * (g_t * g_t)
        v = self.get_slot(var, "v")
        v_t = state_ops.assign(v, beta2_t * v + (1. - beta2_t) * tf.square(grad), use_locking=self._use_locking)
        v_prime = self.get_slot(var, "v_prime")
        v_t_prime = state_ops.assign(v_prime, tf.maximum(v_prime, v_t))

        var_update = state_ops.assign_sub(var,
                                          lr_t * m_t / (tf.sqrt(v_t_prime) + epsilon_t),
                                          use_locking=self._use_locking)

        return control_flow_ops.group(*[var_update, m_t, v_t, v_t_prime])

    # keras Nadam update rule 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def loss(self, data, labels):
    """The loss to minimize while training."""

    if self.is_regression:
      diff = self.training_inference_graph(data) - math_ops.to_float(labels)
      mean_squared_error = math_ops.reduce_mean(diff * diff)
      root_mean_squared_error = math_ops.sqrt(mean_squared_error, name="loss")
      loss = root_mean_squared_error
    else:
      loss = math_ops.reduce_mean(
          nn_ops.sparse_softmax_cross_entropy_with_logits(
              labels=array_ops.squeeze(math_ops.to_int32(labels)),
              logits=self.training_inference_graph(data)),
          name="loss")
    if self.regularizer:
      loss += layers.apply_regularization(self.regularizer,
                                          variables.trainable_variables())
    return loss 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
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.sqrt(gamma_sample / df)
    return samples * self.sigma + self.mu  # Abs(sigma) not wanted. 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def sqrt_matmul(self, x):
    """Computes `matmul(self, x)`.

    Doesn't actually do the sqrt! Named as such to agree with API.

    Args:
      x: `Tensor`

    Returns:
      self_times_x: `Tensor`
    """
    m_x = math_ops.matmul(self._m, x)
    vt_x = math_ops.matmul(self._v, x, adjoint_a=True)
    d_vt_x = self._d.matmul(vt_x)
    v_d_vt_x = math_ops.matmul(self._v, d_vt_x)
    return m_x + v_d_vt_x 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def sqrt_solve(self, x):
    """Computes `solve(self, x)`.

    Doesn't actually do the sqrt! Named as such to agree with API.

    To compute (M + V D V.T), we use the the Woodbury matrix identity:
      inv(M + V D V.T) = inv(M) - inv(M) V inv(C) V.T inv(M)
    where,
      C = inv(D) + V.T inv(M) V.
    See: https://en.wikipedia.org/wiki/Woodbury_matrix_identity

    Args:
      x: `Tensor`

    Returns:
      inv_of_self_times_x: `Tensor`
    """
    minv_x = linalg_ops.matrix_triangular_solve(self._m, x)
    vt_minv_x = math_ops.matmul(self._v, minv_x, transpose_a=True)
    cinv_vt_minv_x = linalg_ops.matrix_solve(
        self._woodbury_sandwiched_term(), vt_minv_x)
    v_cinv_vt_minv_x = math_ops.matmul(self._v, cinv_vt_minv_x)
    minv_v_cinv_vt_minv_x = linalg_ops.matrix_triangular_solve(
        self._m, v_cinv_vt_minv_x)
    return minv_x - minv_v_cinv_vt_minv_x 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def _apply_sparse(self, grad, var):
        lr_t = math_ops.cast(self._lr_t, var.dtype.base_dtype)
        beta1_t = math_ops.cast(self._beta1_t, var.dtype.base_dtype)
        beta2_t = math_ops.cast(self._beta2_t, var.dtype.base_dtype)
        epsilon_t = math_ops.cast(self._epsilon_t, var.dtype.base_dtype)

        # the following equations given in [1]
        # m_t = beta1 * m + (1 - beta1) * g_t
        m = self.get_slot(var, "m")
        m_t = state_ops.scatter_update(m, grad.indices,
                                       beta1_t * array_ops.gather(m, grad.indices) +
                                       (1. - beta1_t) * grad.values,
                                       use_locking=self._use_locking)
        m_t_slice = tf.gather(m_t, grad.indices)

        # v_t = beta2 * v + (1 - beta2) * (g_t * g_t)
        v = self.get_slot(var, "v")
        v_t = state_ops.scatter_update(v, grad.indices,
                                       beta2_t * array_ops.gather(v, grad.indices) +
                                       (1. - beta2_t) * tf.square(grad.values),
                                       use_locking=self._use_locking)
        v_prime = self.get_slot(var, "v_prime")
        v_t_slice = tf.gather(v_t, grad.indices)
        v_prime_slice = tf.gather(v_prime, grad.indices)
        v_t_prime = state_ops.scatter_update(v_prime, grad.indices, tf.maximum(v_prime_slice, v_t_slice))

        v_t_prime_slice = array_ops.gather(v_t_prime, grad.indices)
        var_update = state_ops.scatter_sub(var, grad.indices,
                                           lr_t * m_t_slice / (math_ops.sqrt(v_t_prime_slice) + epsilon_t),
                                           use_locking=self._use_locking)

        return control_flow_ops.group(*[var_update, m_t, v_t, v_t_prime]) 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def _apply_dense(self, grad, var):
        beta1_power = math_ops.cast(self._beta1_power, var.dtype.base_dtype)
        beta2_power = math_ops.cast(self._beta2_power, var.dtype.base_dtype)
        lr_t = math_ops.cast(self._lr_t, var.dtype.base_dtype)
        beta1_t = math_ops.cast(self._beta1_t, var.dtype.base_dtype)
        beta2_t = math_ops.cast(self._beta2_t, var.dtype.base_dtype)
        epsilon_t = math_ops.cast(self._epsilon_t, var.dtype.base_dtype)

        lr = (lr_t * math_ops.sqrt(1 - beta2_power) / (1 - beta1_power))

        # m_t = beta1 * m + (1 - beta1) * g_t
        m = self.get_slot(var, "m")
        m_scaled_g_values = grad * (1 - beta1_t)
        m_t = state_ops.assign(m, beta1_t * m + m_scaled_g_values,
                               use_locking=self._use_locking)

        # v_t = beta2 * v + (1 - beta2) * (g_t * g_t)
        v = self.get_slot(var, "v")
        v_scaled_g_values = (grad * grad) * (1 - beta2_t)
        v_t = state_ops.assign(v, beta2_t * v + v_scaled_g_values,
                               use_locking=self._use_locking)

        # amsgrad
        vhat = self.get_slot(var, "vhat")
        vhat_t = state_ops.assign(vhat, math_ops.maximum(v_t, vhat))
        v_sqrt = math_ops.sqrt(vhat_t)

        var_update = state_ops.assign_sub(var, lr * m_t / (v_sqrt + epsilon_t),
                                          use_locking=self._use_locking)
        return control_flow_ops.group(*[var_update, m_t, v_t, vhat_t]) 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def _resource_apply_dense(self, grad, var):
        var = var.handle
        beta1_power = math_ops.cast(self._beta1_power, grad.dtype.base_dtype)
        beta2_power = math_ops.cast(self._beta2_power, grad.dtype.base_dtype)
        lr_t = math_ops.cast(self._lr_t, grad.dtype.base_dtype)
        beta1_t = math_ops.cast(self._beta1_t, grad.dtype.base_dtype)
        beta2_t = math_ops.cast(self._beta2_t, grad.dtype.base_dtype)
        epsilon_t = math_ops.cast(self._epsilon_t, grad.dtype.base_dtype)

        lr = (lr_t * math_ops.sqrt(1 - beta2_power) / (1 - beta1_power))

        # m_t = beta1 * m + (1 - beta1) * g_t
        m = self.get_slot(var, "m").handle
        m_scaled_g_values = grad * (1 - beta1_t)
        m_t = state_ops.assign(m, beta1_t * m + m_scaled_g_values,
                               use_locking=self._use_locking)

        # v_t = beta2 * v + (1 - beta2) * (g_t * g_t)
        v = self.get_slot(var, "v").handle
        v_scaled_g_values = (grad * grad) * (1 - beta2_t)
        v_t = state_ops.assign(v, beta2_t * v + v_scaled_g_values,
                               use_locking=self._use_locking)

        # amsgrad
        vhat = self.get_slot(var, "vhat").handle
        vhat_t = state_ops.assign(vhat, math_ops.maximum(v_t, vhat))
        v_sqrt = math_ops.sqrt(vhat_t)

        var_update = state_ops.assign_sub(var, lr * m_t / (v_sqrt + epsilon_t),
                                          use_locking=self._use_locking)
        return control_flow_ops.group(*[var_update, m_t, v_t, vhat_t]) 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def _apply_sparse_shared(self, grad, var, indices, scatter_add):
        beta1_power = math_ops.cast(self._beta1_power, var.dtype.base_dtype)
        beta2_power = math_ops.cast(self._beta2_power, var.dtype.base_dtype)
        lr_t = math_ops.cast(self._lr_t, var.dtype.base_dtype)
        beta1_t = math_ops.cast(self._beta1_t, var.dtype.base_dtype)
        beta2_t = math_ops.cast(self._beta2_t, var.dtype.base_dtype)
        epsilon_t = math_ops.cast(self._epsilon_t, var.dtype.base_dtype)

        lr = (lr_t * math_ops.sqrt(1 - beta2_power) / (1 - beta1_power))

        # m_t = beta1 * m + (1 - beta1) * g_t
        m = self.get_slot(var, "m")
        m_scaled_g_values = grad * (1 - beta1_t)
        m_t = state_ops.assign(m, m * beta1_t, use_locking=self._use_locking)
        with ops.control_dependencies([m_t]):
            m_t = scatter_add(m, indices, m_scaled_g_values)

        # v_t = beta2 * v + (1 - beta2) * (g_t * g_t)
        v = self.get_slot(var, "v")
        v_scaled_g_values = (grad * grad) * (1 - beta2_t)
        v_t = state_ops.assign(v, v * beta2_t, use_locking=self._use_locking)
        with ops.control_dependencies([v_t]):
            v_t = scatter_add(v, indices, v_scaled_g_values)

        # amsgrad
        vhat = self.get_slot(var, "vhat")
        vhat_t = state_ops.assign(vhat, math_ops.maximum(v_t, vhat))
        v_sqrt = math_ops.sqrt(vhat_t)
        var_update = state_ops.assign_sub(var, lr * m_t / (v_sqrt + epsilon_t),
                                          use_locking=self._use_locking)
        return control_flow_ops.group(*[var_update, m_t, v_t, vhat_t]) 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def call(self, inputs):
    inputs = ops.convert_to_tensor(inputs, dtype=self.dtype)
    ndim = self._input_rank

    shape = self.gamma.get_shape().as_list()
    gamma = array_ops.reshape(self.gamma, (ndim - 2) * [1] + shape)

    # Compute normalization pool.
    if self.data_format == 'channels_first':
      norm_pool = nn.convolution(
          math_ops.square(inputs),
          gamma,
          'VALID',
          data_format='NC' + 'DHW' [-(ndim - 2):])
      if ndim == 3:
        norm_pool = array_ops.expand_dims(norm_pool, 2)
        norm_pool = nn.bias_add(norm_pool, self.beta, data_format='NCHW')
        norm_pool = array_ops.squeeze(norm_pool, [2])
      elif ndim == 5:
        shape = array_ops.shape(norm_pool)
        norm_pool = array_ops.reshape(norm_pool, shape[:3] + [-1])
        norm_pool = nn.bias_add(norm_pool, self.beta, data_format='NCHW')
        norm_pool = array_ops.reshape(norm_pool, shape)
      else:  # ndim == 4
        norm_pool = nn.bias_add(norm_pool, self.beta, data_format='NCHW')
    else:  # channels_last
      norm_pool = nn.convolution(math_ops.square(inputs), gamma, 'VALID')
      norm_pool = nn.bias_add(norm_pool, self.beta, data_format='NHWC')
    norm_pool = math_ops.sqrt(norm_pool)

    if self.inverse:
      outputs = inputs * norm_pool
    else:
      outputs = inputs / norm_pool
    outputs.set_shape(inputs.get_shape())
    return outputs 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def unit_norm(inputs, dim, epsilon=1e-7, scope=None):
  """Normalizes the given input across the specified dimension to unit length.

  Note that the rank of `input` must be known.

  Args:
    inputs: A `Tensor` of arbitrary size.
    dim: The dimension along which the input is normalized.
    epsilon: A small value to add to the inputs to avoid dividing by zero.
    scope: Optional scope for variable_scope.

  Returns:
    The normalized `Tensor`.

  Raises:
    ValueError: If dim is smaller than the number of dimensions in 'inputs'.
  """
  with variable_scope.variable_scope(scope, 'UnitNorm', [inputs]):
    if not inputs.get_shape():
      raise ValueError('The input rank must be known.')
    input_rank = len(inputs.get_shape().as_list())
    if dim < 0 or dim >= input_rank:
      raise ValueError('dim must be positive but smaller than the input rank.')

    lengths = math_ops.sqrt(
        epsilon + math_ops.reduce_sum(math_ops.square(inputs), dim, True))
    multiples = []
    if dim > 0:
      multiples.append(array_ops.ones([dim], dtypes.int32))
    multiples.append(
        array_ops.strided_slice(array_ops.shape(inputs), [dim], [dim + 1]))
    if dim < (input_rank - 1):
      multiples.append(array_ops.ones([input_rank - 1 - dim], dtypes.int32))
    multiples = array_ops.concat(multiples, 0)
    return math_ops.div(inputs, array_ops.tile(lengths, multiples)) 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def _adaptive_max_norm(norm, std_factor, decay, global_step, epsilon, name):
  """Find max_norm given norm and previous average."""
  with vs.variable_scope(name, "AdaptiveMaxNorm", [norm]):
    log_norm = math_ops.log(norm + epsilon)

    def moving_average(name, value, decay):
      moving_average_variable = vs.get_variable(
          name,
          shape=value.get_shape(),
          dtype=value.dtype,
          initializer=init_ops.zeros_initializer(),
          trainable=False)
      return moving_averages.assign_moving_average(
          moving_average_variable, value, decay, zero_debias=False)

    # quicker adaptation at the beginning
    if global_step is not None:
      n = math_ops.cast(global_step, dtypes.float32)
      decay = math_ops.minimum(decay, n / (n + 1.))

    # update averages
    mean = moving_average("mean", log_norm, decay)
    sq_mean = moving_average("sq_mean", math_ops.square(log_norm), decay)

    variance = sq_mean - math_ops.square(mean)
    std = math_ops.sqrt(math_ops.maximum(epsilon, variance))
    max_norms = math_ops.exp(mean + std_factor * std)
    return max_norms, mean 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def _apply_dense(self, grad, var):
        beta1_power = math_ops.cast(self._beta1_power, var.dtype.base_dtype)
        beta2_power = math_ops.cast(self._beta2_power, var.dtype.base_dtype)
        lr_t = math_ops.cast(self._lr_t, var.dtype.base_dtype)
        beta1_t = math_ops.cast(self._beta1_t, var.dtype.base_dtype)
        beta2_t = math_ops.cast(self._beta2_t, var.dtype.base_dtype)
        epsilon_t = math_ops.cast(self._epsilon_t, var.dtype.base_dtype)

        lr = (lr_t * math_ops.sqrt(1 - beta2_power) / (1 - beta1_power))

        # m_t = beta1 * m + (1 - beta1) * g_t
        m = self.get_slot(var, "m")
        m_scaled_g_values = grad * (1 - beta1_t)
        m_t = state_ops.assign(m, beta1_t * m + m_scaled_g_values, use_locking=self._use_locking)

        # v_t = beta2 * v + (1 - beta2) * (g_t * g_t)
        v = self.get_slot(var, "v")
        v_scaled_g_values = (grad * grad) * (1 - beta2_t)
        v_t = state_ops.assign(v, beta2_t * v + v_scaled_g_values, use_locking=self._use_locking)

        # amsgrad
        vhat = self.get_slot(var, "vhat")
        vhat_t = state_ops.assign(vhat, math_ops.maximum(v_t, vhat))
        v_sqrt = math_ops.sqrt(vhat_t)

        var_update = state_ops.assign_sub(var, lr * m_t / (v_sqrt + epsilon_t), use_locking=self._use_locking)
        return control_flow_ops.group(*[var_update, m_t, v_t, vhat_t]) 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def _resource_apply_dense(self, grad, var):
        var = var.handle
        beta1_power = math_ops.cast(self._beta1_power, grad.dtype.base_dtype)
        beta2_power = math_ops.cast(self._beta2_power, grad.dtype.base_dtype)
        lr_t = math_ops.cast(self._lr_t, grad.dtype.base_dtype)
        beta1_t = math_ops.cast(self._beta1_t, grad.dtype.base_dtype)
        beta2_t = math_ops.cast(self._beta2_t, grad.dtype.base_dtype)
        epsilon_t = math_ops.cast(self._epsilon_t, grad.dtype.base_dtype)

        lr = (lr_t * math_ops.sqrt(1 - beta2_power) / (1 - beta1_power))

        # m_t = beta1 * m + (1 - beta1) * g_t
        m = self.get_slot(var, "m").handle
        m_scaled_g_values = grad * (1 - beta1_t)
        m_t = state_ops.assign(m, beta1_t * m + m_scaled_g_values, use_locking=self._use_locking)

        # v_t = beta2 * v + (1 - beta2) * (g_t * g_t)
        v = self.get_slot(var, "v").handle
        v_scaled_g_values = (grad * grad) * (1 - beta2_t)
        v_t = state_ops.assign(v, beta2_t * v + v_scaled_g_values, use_locking=self._use_locking)

        # amsgrad
        vhat = self.get_slot(var, "vhat").handle
        vhat_t = state_ops.assign(vhat, math_ops.maximum(v_t, vhat))
        v_sqrt = math_ops.sqrt(vhat_t)

        var_update = state_ops.assign_sub(var, lr * m_t / (v_sqrt + epsilon_t), use_locking=self._use_locking)
        return control_flow_ops.group(*[var_update, m_t, v_t, vhat_t]) 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sqrt [as 别名]
def _apply_sparse_shared(self, grad, var, indices, scatter_add):
        beta1_power = math_ops.cast(self._beta1_power, var.dtype.base_dtype)
        beta2_power = math_ops.cast(self._beta2_power, var.dtype.base_dtype)
        lr_t = math_ops.cast(self._lr_t, var.dtype.base_dtype)
        beta1_t = math_ops.cast(self._beta1_t, var.dtype.base_dtype)
        beta2_t = math_ops.cast(self._beta2_t, var.dtype.base_dtype)
        epsilon_t = math_ops.cast(self._epsilon_t, var.dtype.base_dtype)

        lr = (lr_t * math_ops.sqrt(1 - beta2_power) / (1 - beta1_power))

        # m_t = beta1 * m + (1 - beta1) * g_t
        m = self.get_slot(var, "m")
        m_scaled_g_values = grad * (1 - beta1_t)
        m_t = state_ops.assign(m, m * beta1_t, use_locking=self._use_locking)
        with ops.control_dependencies([m_t]):
            m_t = scatter_add(m, indices, m_scaled_g_values)

        # v_t = beta2 * v + (1 - beta2) * (g_t * g_t)
        v = self.get_slot(var, "v")
        v_scaled_g_values = (grad * grad) * (1 - beta2_t)
        v_t = state_ops.assign(v, v * beta2_t, use_locking=self._use_locking)
        with ops.control_dependencies([v_t]):
            v_t = scatter_add(v, indices, v_scaled_g_values)

        # amsgrad
        vhat = self.get_slot(var, "vhat")
        vhat_t = state_ops.assign(vhat, math_ops.maximum(v_t, vhat))
        v_sqrt = math_ops.sqrt(vhat_t)
        var_update = state_ops.assign_sub(var, lr * m_t / (v_sqrt + epsilon_t), use_locking=self._use_locking)
        return control_flow_ops.group(*[var_update, m_t, v_t, vhat_t])