Python math_ops.multiply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 multiply [as 别名]
def _scale_losses(losses, weights):
  """Computes the scaled loss.

  Args:
    losses: A `Tensor` of size [batch_size, d1, ... dN].
    weights: A `Tensor` of size [1], [batch_size] or [batch_size, d1, ... dN].
      The `losses` are reduced (tf.reduce_sum) until its dimension matches
      that of `weights` at which point the reduced `losses` are element-wise
      multiplied by `weights` and a final reduce_sum is computed on the result.
      Conceptually, this operation is equivalent to broadcasting (tiling)
      `weights` to be the same size as `losses`, performing an element-wise
      multiplication, and summing the result.

  Returns:
    A scalar tf.float32 `Tensor` whose value represents the sum of the scaled
      `losses`.
  """
  # First, compute the sum of the losses over all elements:
  start_index = max(0, weights.get_shape().ndims)
  reduction_indices = list(range(start_index, losses.get_shape().ndims))
  reduced_losses = math_ops.reduce_sum(losses,
                                       reduction_indices=reduction_indices)
  reduced_losses = math_ops.multiply(reduced_losses, weights)
  return math_ops.reduce_sum(reduced_losses) 

# 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 multiply [as 别名]
def hinge_loss(logits, labels=None, scope=None):
  """Method that returns the loss tensor for hinge loss.

  Args:
    logits: The logits, a float tensor.
    labels: The ground truth output tensor. Its shape should match the shape of
      logits. The values of the tensor are expected to be 0.0 or 1.0.
    scope: The scope for the operations performed in computing the loss.

  Returns:
    A `Tensor` of same shape as `logits` and `labels` representing the loss
      values across the batch.

  Raises:
    ValueError: If the shapes of `logits` and `labels` don't match.
  """
  with ops.name_scope(scope, "hinge_loss", [logits, labels]) as scope:
    logits.get_shape().assert_is_compatible_with(labels.get_shape())
    # We first need to convert binary labels to -1/1 labels (as floats).
    labels = math_ops.to_float(labels)
    all_ones = array_ops.ones_like(labels)
    labels = math_ops.subtract(2 * labels, all_ones)
    return nn_ops.relu(
        math_ops.subtract(all_ones, math_ops.multiply(labels, logits))) 

# 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 multiply [as 别名]
def setUp(self):
    self.a = variables.Variable(10.0, name="a")
    self.b = variables.Variable(20.0, name="b")

    self.c = math_ops.add(self.a, self.b, name="c")  # Should be 30.0.
    self.d = math_ops.subtract(self.a, self.c, name="d")  # Should be -20.0.
    self.e = math_ops.multiply(self.c, self.d, name="e")  # Should be -600.0.

    self.ph = array_ops.placeholder(dtypes.float32, shape=(2, 2), name="ph")
    self.f = math_ops.multiply(self.e, self.ph, name="f")

    self.opt = gradient_descent.GradientDescentOptimizer(0.1).minimize(
        self.e, name="opt")

    self.sess = session.Session()

    self.sess.run(self.a.initializer)
    self.sess.run(self.b.initializer) 

# 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 multiply [as 别名]
def setUp(self):
    self.a = variables.Variable(2.0, name="a")
    self.b = variables.Variable(3.0, name="b")

    self.c = math_ops.multiply(self.a, self.b, name="c")  # Should be 6.0.
    self.d = math_ops.multiply(self.a, self.a, name="d")  # Should be 4.0.

    self.e = math_ops.multiply(self.d, self.c, name="e")  # Should be 24.0.

    self.f_y = constant_op.constant(0.30, name="f_y")
    self.f = math_ops.div(self.b, self.f_y, name="f")  # Should be 10.0.

    # The there nodes x, y and z form a graph with "cross-links" in. I.e., x
    # and y are both direct inputs to z, but x is also a direct input to y.
    self.x = variables.Variable(2.0, name="x")  # Should be 2.0
    self.y = math_ops.negative(self.x, name="y")  # Should be -2.0.

    self.z = math_ops.multiply(self.x, self.y, name="z")  # Should be -4.0.

    self.sess = session.Session()
    self.sess.run(variables.global_variables_initializer())

    self.sess = session.Session()
    self.sess.run(variables.global_variables_initializer()) 

# 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 multiply [as 别名]
def _scale_losses(losses, weights):
  """Computes the scaled loss.

  Args:
    losses: `Tensor` of shape `[batch_size, d1, ... dN]`.
    weights: `Tensor` of shape `[]`, `[batch_size]` or
      `[batch_size, d1, ... dN]`. The `losses` are reduced (`tf.reduce_sum`)
      until its dimension matches that of `weights` at which point the reduced
      `losses` are element-wise multiplied by `weights` and a final `reduce_sum`
      is computed on the result. Conceptually, this operation is similar to
      broadcasting (tiling) `weights` to be the same shape as `losses`,
      performing an element-wise multiplication, and summing the result. Note,
      however, that the dimension matching is right-to-left, not left-to-right;
      i.e., the opposite of standard NumPy/Tensorflow broadcasting.

  Returns:
    A scalar tf.float32 `Tensor` whose value represents the sum of the scaled
      `losses`.
  """
  weighted_losses = math_ops.multiply(losses, weights)
  return math_ops.reduce_sum(weighted_losses) 

# 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 multiply [as 别名]
def _linear_predictions(self, examples):
    """Returns predictions of the form w*x."""
    with name_scope('sdca/prediction'):
      sparse_variables = self._convert_n_to_tensor(self._variables[
          'sparse_features_weights'])
      result = 0.0
      for sfc, sv in zip(examples['sparse_features'], sparse_variables):
        # TODO(sibyl-Aix6ihai): following does not take care of missing features.
        result += math_ops.segment_sum(
            math_ops.multiply(
                array_ops.gather(sv, sfc.feature_indices), sfc.feature_values),
            sfc.example_indices)
      dense_features = self._convert_n_to_tensor(examples['dense_features'])
      dense_variables = self._convert_n_to_tensor(self._variables[
          'dense_features_weights'])

      for i in range(len(dense_variables)):
        result += math_ops.matmul(dense_features[i],
                                  array_ops.expand_dims(dense_variables[i], -1))

    # Reshaping to allow shape inference at graph construction time.
    return array_ops.reshape(result, [-1]) 

# 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 multiply [as 别名]
def call(self, inputs, state):
    """Run one time step of the IndRNN.

    Calculates the output and new hidden state using the IndRNN equation

      `output = new_state = act(W * input + u (*) state + b)`

    where `*` is the matrix multiplication and `(*)` is the Hadamard product.

    Args:
      inputs: Tensor, 2-D tensor of shape `[batch, num_units]`.
      state: Tensor, 2-D tensor of shape `[batch, num_units]` containing the
        previous hidden state.

    Returns:
      A tuple containing the output and new hidden state. Both are the same
        2-D tensor of shape `[batch, num_units]`.
    """
    gate_inputs = math_ops.matmul(inputs, self._input_kernel)
    recurrent_update = math_ops.multiply(state, self._recurrent_kernel)
    gate_inputs = math_ops.add(gate_inputs, recurrent_update)
    gate_inputs = nn_ops.bias_add(gate_inputs, self._bias)
    output = self._activation(gate_inputs)
    return output, output 

# 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 multiply [as 别名]
def _scale_losses(losses, weights):
  """Computes the scaled loss.

  Args:
    losses: A `Tensor` of size [batch_size, d1, ... dN].
    weights: A `Tensor` of size [1], [batch_size] or [batch_size, d1, ... dN].
      The `losses` are reduced (tf.reduce_sum) until its dimension matches
      that of `weights` at which point the reduced `losses` are element-wise
      multiplied by `weights` and a final reduce_sum is computed on the result.
      Conceptually, this operation is equivalent to broadcasting (tiling)
      `weights` to be the same size as `losses`, performing an element-wise
      multiplication, and summing the result.

  Returns:
    A scalar tf.float32 `Tensor` whose value represents the sum of the scaled
      `losses`.
  """
  # First, compute the sum of the losses over all elements:
  start_index = max(0, weights.get_shape().ndims)
  axis = list(range(start_index, losses.get_shape().ndims))
  reduced_losses = math_ops.reduce_sum(losses, axis=axis)
  reduced_losses = math_ops.multiply(reduced_losses, weights)
  return math_ops.reduce_sum(reduced_losses) 

# 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 multiply [as 别名]
def masked_maximum(data, mask, dim=1):
  """Computes the axis wise maximum over chosen elements.

  Args:
    data: 2-D float `Tensor` of size [n, m].
    mask: 2-D Boolean `Tensor` of size [n, m].
    dim: The dimension over which to compute the maximum.

  Returns:
    masked_maximums: N-D `Tensor`.
      The maximized dimension is of size 1 after the operation.
  """
  axis_minimums = math_ops.reduce_min(data, dim, keepdims=True)
  masked_maximums = math_ops.reduce_max(
      math_ops.multiply(data - axis_minimums, mask), dim,
      keepdims=True) + axis_minimums
  return masked_maximums 

# 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 multiply [as 别名]
def scale_gradient(inputs, gradient_multiplier):
  """Identity operation, but with the gradient multiplied by a tensor.

  The TensorFlow gradient system will compute the gradient with respect to
  `inputs` as the product of the gradient with respect to the `output`
  multiplied by a specified `gradient_multiplier` tensor.  If
  `gradient_multiplier` is equal to 1, then this results in the true gradient.
  Otherwise, it results in a scaled gradient.

  This can be useful for adjusting the relative learning rate of different
  parameter tensors when performing gradient descent, and because this rescaling
  can be inserted at arbitrary locations within a graph, is often more
  convenient to apply than simply rescaling the final computed gradients.

  Args:
    inputs: Tensor to be output.
    gradient_multiplier: Tensor by which to multiply the gradient with respect
      to `output` to compute the gradient with respect to `inputs`.  Its shape
      must be broadcastable to the shape of `inputs`.

  Returns:
    output Tensor, equal to `inputs`.
  """
  # gradient_multiplier is implicitly saved by decorator, and only used for
  # gradient computation.
  del gradient_multiplier

  return inputs 

# 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 multiply [as 别名]
def poincare_normalize(x, axis=1, epsilon=1e-5, name=None):
  """Project into the Poincare ball with norm <= 1.0 - epsilon.

  https://en.wikipedia.org/wiki/Poincare_ball_model

  Used in
  Poincare Embeddings for Learning Hierarchical Representations
  Maximilian Nickel, Douwe Kiela
  https://arxiv.org/pdf/1705.08039.pdf

  For a 1-D tensor with `axis = 0`, computes

                (x * (1 - epsilon)) / ||x||     if ||x|| > 1 - epsilon
      output =
                 x                              otherwise

  For `x` with more dimensions, independently normalizes each 1-D slice along
  dimension `axis`.

  Args:
    x: A `Tensor`.
    axis: Axis along which to normalize.  A scalar or a vector of integers.
    epsilon: A small deviation from the edge of the unit sphere for numerical
      stability.
    name: A name for this operation (optional).

  Returns:
    A `Tensor` with the same shape as `x`.
  """
  with ops.name_scope(name, 'poincare_normalize', [x]) as name:
    x = ops.convert_to_tensor(x, name='x')
    square_sum = math_ops.reduce_sum(math_ops.square(x), axis, keepdims=True)
    x_inv_norm = math_ops.rsqrt(square_sum)
    x_inv_norm = math_ops.minimum((1. - epsilon) * x_inv_norm, 1.)
    return math_ops.multiply(x, x_inv_norm, name=name) 

# 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 multiply [as 别名]
def __call__(self, input_, state, scope=None):
    return (math_ops.multiply(self._w, input_), state) 

# 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 multiply [as 别名]
def cosine_distance(
    labels, predictions, dim=None, weights=1.0, scope=None,
    loss_collection=ops.GraphKeys.LOSSES,
    reduction=Reduction.SUM_BY_NONZERO_WEIGHTS):
  """Adds a cosine-distance loss to the training procedure.

  Note that the function assumes that `predictions` and `labels` are already
  unit-normalized.

  Args:
    labels: `Tensor` whose shape matches 'predictions'
    predictions: An arbitrary matrix.
    dim: The dimension along which the cosine distance is computed.
    weights: Optional `Tensor` whose rank is either 0, or the same rank as
      `labels`, and must be broadcastable to `labels` (i.e., all dimensions must
      be either `1`, or the same as the corresponding `losses` dimension).
    scope: The scope for the operations performed in computing the loss.
    loss_collection: collection to which this loss will be added.
    reduction: Type of reduction to apply to loss.

  Returns:
    Weighted loss float `Tensor`. If `reduction` is `NONE`, this has the same
    shape as `labels`; otherwise, it is scalar.

  Raises:
    ValueError: If `predictions` shape doesn't match `labels` shape, or
      `weights` is `None`.
  """
  if dim is None:
    raise ValueError("`dim` cannot be None.")
  with ops.name_scope(scope, "cosine_distance_loss",
                      (predictions, labels, weights)) as scope:
    predictions = math_ops.to_float(predictions)
    labels = math_ops.to_float(labels)
    predictions.get_shape().assert_is_compatible_with(labels.get_shape())

    radial_diffs = math_ops.multiply(predictions, labels)
    losses = 1 - math_ops.reduce_sum(radial_diffs, axis=(dim,), keep_dims=True)
    return compute_weighted_loss(
        losses, weights, scope, loss_collection, reduction=reduction) 

# 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 multiply [as 别名]
def hinge_loss(labels, logits, weights=1.0, scope=None,
               loss_collection=ops.GraphKeys.LOSSES,
               reduction=Reduction.SUM_BY_NONZERO_WEIGHTS):
  """Adds a hinge loss to the training procedure.

  Args:
    labels: The ground truth output tensor. Its shape should match the shape of
      logits. The values of the tensor are expected to be 0.0 or 1.0.
    logits: The logits, a float tensor.
    weights: Optional `Tensor` whose rank is either 0, or the same rank as
      `labels`, and must be broadcastable to `labels` (i.e., all dimensions must
      be either `1`, or the same as the corresponding `losses` dimension).
    scope: The scope for the operations performed in computing the loss.
    loss_collection: collection to which the loss will be added.
    reduction: Type of reduction to apply to loss.

  Returns:
    Weighted loss float `Tensor`. If `reduction` is `NONE`, this has the same
    shape as `labels`; otherwise, it is scalar.

  Raises:
    ValueError: If the shapes of `logits` and `labels` don't match.
  """
  with ops.name_scope(scope, "hinge_loss", (logits, labels)) as scope:
    logits = math_ops.to_float(logits)
    labels = math_ops.to_float(labels)
    logits.get_shape().assert_is_compatible_with(labels.get_shape())
    # We first need to convert binary labels to -1/1 labels (as floats).
    all_ones = array_ops.ones_like(labels)
    labels = math_ops.subtract(2 * labels, all_ones)
    losses = nn_ops.relu(
        math_ops.subtract(all_ones, math_ops.multiply(labels, logits)))
    return compute_weighted_loss(
        losses, weights, scope, loss_collection, reduction=reduction) 

# 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 multiply [as 别名]
def normalize_moments(counts, mean_ss, variance_ss, shift, name=None):
  """Calculate the mean and variance of based on the sufficient statistics.

  Args:
    counts: A `Tensor` containing a the total count of the data (one value).
    mean_ss: A `Tensor` containing the mean sufficient statistics: the (possibly
      shifted) sum of the elements to average over.
    variance_ss: A `Tensor` containing the variance sufficient statistics: the
      (possibly shifted) squared sum of the data to compute the variance over.
    shift: A `Tensor` containing the value by which the data is shifted for
      numerical stability, or `None` if no shift was performed.
    name: Name used to scope the operations that compute the moments.

  Returns:
    Two `Tensor` objects: `mean` and `variance`.
  """
  with ops.name_scope(name, "normalize", [counts, mean_ss, variance_ss, shift]):
    divisor = math_ops.reciprocal(counts, name="divisor")
    if shift is not None:
      shifted_mean = math_ops.multiply(mean_ss, divisor, name="shifted_mean")
      mean = math_ops.add(shifted_mean, shift, name="mean")
    else:  # no shift.
      shifted_mean = math_ops.multiply(mean_ss, divisor, name="mean")
      mean = shifted_mean
    variance = math_ops.subtract(math_ops.multiply(variance_ss, divisor),
                                 math_ops.square(shifted_mean),
                                 name="variance")
  return (mean, variance)