Python math_ops.matmul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 matmul [as 别名]
def xw_plus_b(x, weights, biases, name=None):  # pylint: disable=invalid-name
  """Computes matmul(x, weights) + biases.

  Args:
    x: a 2D tensor.  Dimensions typically: batch, in_units
    weights: a 2D tensor.  Dimensions typically: in_units, out_units
    biases: a 1D tensor.  Dimensions: out_units
    name: A name for the operation (optional).  If not specified
      "xw_plus_b" is used.

  Returns:
    A 2-D Tensor computing matmul(x, weights) + biases.
    Dimensions typically: batch, out_units.
  """
  with ops.name_scope(name, "xw_plus_b", [x, weights, biases]) as name:
    x = ops.convert_to_tensor(x, name="x")
    weights = ops.convert_to_tensor(weights, name="weights")
    biases = ops.convert_to_tensor(biases, name="biases")
    mm = math_ops.matmul(x, weights)
    return bias_add(mm, biases, 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 matmul [as 别名]
def xw_plus_b_v1(x, weights, biases, name=None):  # pylint: disable=invalid-name
  """Computes matmul(x, weights) + biases.

  This is a deprecated version of that will soon be removed.

  Args:
    x: a 2D tensor.  Dimensions typically: batch, in_units
    weights: a 2D tensor.  Dimensions typically: in_units, out_units
    biases: a 1D tensor.  Dimensions: out_units
    name: A name for the operation (optional).  If not specified
      "xw_plus_b_v1" is used.

  Returns:
    A 2-D Tensor computing matmul(x, weights) + biases.
    Dimensions typically: batch, out_units.
  """
  with ops.name_scope(name, "xw_plus_b_v1", [x, weights, biases]) as name:
    x = ops.convert_to_tensor(x, name="x")
    weights = ops.convert_to_tensor(weights, name="weights")
    biases = ops.convert_to_tensor(biases, name="biases")
    mm = math_ops.matmul(x, weights)
    return bias_add_v1(mm, biases, 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 matmul [as 别名]
def _MatMulGrad(op, grad):
  """Gradient for MatMul."""

  t_a = op.get_attr("transpose_a")
  t_b = op.get_attr("transpose_b")
  a = math_ops.conj(op.inputs[0])
  b = math_ops.conj(op.inputs[1])
  if not t_a and not t_b:
    grad_a = math_ops.matmul(grad, b, transpose_b=True)
    grad_b = math_ops.matmul(a, grad, transpose_a=True)
  elif not t_a and t_b:
    grad_a = math_ops.matmul(grad, b)
    grad_b = math_ops.matmul(grad, a, transpose_a=True)
  elif t_a and not t_b:
    grad_a = math_ops.matmul(b, grad, transpose_b=True)
    grad_b = math_ops.matmul(a, grad)
  elif t_a and t_b:
    grad_a = math_ops.matmul(b, grad, transpose_a=True, transpose_b=True)
    grad_b = math_ops.matmul(grad, a, transpose_a=True, transpose_b=True)
  return grad_a, grad_b 

# 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 matmul [as 别名]
def _BatchMatMul(op, grad):
  """Returns the gradient of x and y given the gradient of x * y."""
  x = op.inputs[0]
  y = op.inputs[1]
  adj_x = op.get_attr("adj_x")
  adj_y = op.get_attr("adj_y")

  if not adj_x:
    if not adj_y:
      grad_x = math_ops.matmul(grad, y, adjoint_a=False, adjoint_b=True)
      grad_y = math_ops.matmul(x, grad, adjoint_a=True, adjoint_b=False)
    else:
      grad_x = math_ops.matmul(grad, y, adjoint_a=False, adjoint_b=False)
      grad_y = math_ops.matmul(grad, x, adjoint_a=True, adjoint_b=False)
  else:
    if not adj_y:
      grad_x = math_ops.matmul(y, grad, adjoint_a=False, adjoint_b=True)
      grad_y = math_ops.matmul(x, grad, adjoint_a=False, adjoint_b=False)
    else:
      grad_x = math_ops.matmul(y, grad, adjoint_a=True, adjoint_b=True)
      grad_y = math_ops.matmul(grad, x, adjoint_a=True, adjoint_b=True)

  return grad_x, grad_y 

# 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 matmul [as 别名]
def _MatrixTriangularSolveGrad(op, grad):
  """Gradient for MatrixTriangularSolve."""
  a = op.inputs[0]
  adjoint_a = op.get_attr("adjoint")
  lower_a = op.get_attr("lower")
  c = op.outputs[0]
  grad_b = linalg_ops.matrix_triangular_solve(
      a, grad, lower=lower_a, adjoint=not adjoint_a)
  if adjoint_a:
    grad_a = -math_ops.matmul(c, grad_b, adjoint_b=True)
  else:
    grad_a = -math_ops.matmul(grad_b, c, adjoint_b=True)
  if lower_a:
    grad_a = array_ops.matrix_band_part(grad_a, -1, 0)
  else:
    grad_a = array_ops.matrix_band_part(grad_a, 0, -1)
  return (grad_a, grad_b) 

# 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 matmul [as 别名]
def relu_layer(x, weights, biases, name=None):
  """Computes Relu(x * weight + biases).

  Args:
    x: a 2D tensor.  Dimensions typically: batch, in_units
    weights: a 2D tensor.  Dimensions typically: in_units, out_units
    biases: a 1D tensor.  Dimensions: out_units
    name: A name for the operation (optional).  If not specified
      "nn_relu_layer" is used.

  Returns:
    A 2-D Tensor computing relu(matmul(x, weights) + biases).
    Dimensions typically: batch, out_units.
  """
  with ops.name_scope(name, "relu_layer", [x, weights, biases]) as name:
    x = ops.convert_to_tensor(x, name="x")
    weights = ops.convert_to_tensor(weights, name="weights")
    biases = ops.convert_to_tensor(biases, name="biases")
    xw_plus_b = nn_ops.bias_add(math_ops.matmul(x, weights), biases)
    return nn_ops.relu(xw_plus_b, 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 matmul [as 别名]
def _compute_euclidean_distance(cls, inputs, clusters):
    """Computes Euclidean distance between each input and each cluster center.

    Args:
      inputs: list of input Tensors.
      clusters: cluster Tensor.

    Returns:
      list of Tensors, where each element corresponds to each element in inputs.
      The value is the distance of each row to all the cluster centers.
    """
    output = []
    for inp in inputs:
      with ops.colocate_with(inp):
        # Computes Euclidean distance. Note the first and third terms are
        # broadcast additions.
        squared_distance = (math_ops.reduce_sum(
            math_ops.square(inp), 1, keep_dims=True) - 2 * math_ops.matmul(
                inp, clusters, transpose_b=True) + array_ops.transpose(
                    math_ops.reduce_sum(
                        math_ops.square(clusters), 1, keep_dims=True)))
        output.append(squared_distance)

    return 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 matmul [as 别名]
def _covariance(x, diag):
  """Defines the covariance operation of a matrix.

  Args:
    x: a matrix Tensor. Dimension 0 should contain the number of examples.
    diag: if True, it computes the diagonal covariance.

  Returns:
    A Tensor representing the covariance of x. In the case of
  diagonal matrix just the diagonal is returned.
  """
  num_points = math_ops.to_float(array_ops.shape(x)[0])
  x -= math_ops.reduce_mean(x, 0, keep_dims=True)
  if diag:
    cov = math_ops.reduce_sum(
        math_ops.square(x), 0, keep_dims=True) / (num_points - 1)
  else:
    cov = math_ops.matmul(x, x, transpose_a=True) / (num_points - 1)
  return cov 

# 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 matmul [as 别名]
def _define_diag_covariance_probs(self, shard_id, shard):
    """Defines the diagonal covariance probabilities per example in a class.

    Args:
      shard_id: id of the current shard.
      shard: current data shard, 1 X num_examples X dimensions.

    Returns a matrix num_examples * num_classes.
    """
    # num_classes X 1
    # TODO(xavigonzalvo): look into alternatives to log for
    # reparametrization of variance parameters.
    det_expanded = math_ops.reduce_sum(
        math_ops.log(self._covs + 1e-3), 1, keep_dims=True)
    diff = shard - self._means
    x2 = math_ops.square(diff)
    cov_expanded = array_ops.expand_dims(1.0 / (self._covs + 1e-3), 2)
    # num_classes X num_examples
    x2_cov = math_ops.matmul(x2, cov_expanded)
    x2_cov = array_ops.transpose(array_ops.squeeze(x2_cov, [2]))
    self._probs[shard_id] = -0.5 * (
        math_ops.to_float(self._dimensions) * math_ops.log(2.0 * np.pi) +
        array_ops.transpose(det_expanded) + x2_cov) 

# 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 matmul [as 别名]
def _define_partial_maximization_operation(self, shard_id, shard):
    """Computes the partial statistics of the means and covariances.

    Args:
      shard_id: current shard id.
      shard: current data shard, 1 X num_examples X dimensions.
    """
    # Soft assignment of each data point to each of the two clusters.
    self._points_in_k[shard_id] = math_ops.reduce_sum(
        self._w[shard_id], 0, keep_dims=True)
    # Partial means.
    w_mul_x = array_ops.expand_dims(
        math_ops.matmul(
            self._w[shard_id], array_ops.squeeze(shard, [0]), transpose_a=True),
        1)
    self._w_mul_x.append(w_mul_x)
    # Partial covariances.
    x = array_ops.concat([shard for _ in range(self._num_classes)], 0)
    x_trans = array_ops.transpose(x, perm=[0, 2, 1])
    x_mul_w = array_ops.concat([
        array_ops.expand_dims(x_trans[k, :, :] * self._w[shard_id][:, k], 0)
        for k in range(self._num_classes)
    ], 0)
    self._w_mul_x2.append(math_ops.matmul(x_mul_w, 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 matmul [as 别名]
def create_operator(matrix):
  """Creates a linear operator from a rank-2 tensor."""

  linear_operator = collections.namedtuple(
      "LinearOperator", ["shape", "dtype", "apply", "apply_adjoint"])

  # TODO(rmlarsen): Handle SparseTensor.
  shape = matrix.get_shape()
  if shape.is_fully_defined():
    shape = shape.as_list()
  else:
    shape = array_ops.shape(matrix)
  return linear_operator(
      shape=shape,
      dtype=matrix.dtype,
      apply=lambda v: math_ops.matmul(matrix, v, adjoint_a=False),
      apply_adjoint=lambda v: math_ops.matmul(matrix, v, adjoint_a=True))


# TODO(rmlarsen): Measure if we should just call matmul. 

# 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 matmul [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 matmul [as 别名]
def testSqrtMatmul(self):
    # Square roots are not unique, but we should have SS^T x = Ax, and in our
    # case, we should have S = S^T, so SSx = Ax.
    with self.test_session():
      for batch_shape in [(), (
          2,
          3,)]:
        for k in [1, 4]:
          operator, mat = self._build_operator_and_mat(batch_shape, k)

          # Work with 5 simultaneous systems.  5 is arbitrary.
          x = self._rng.randn(*(batch_shape + (k, 5)))

          self._compare_results(
              expected=math_ops.matmul(mat, x).eval(),
              actual=operator.sqrt_matmul(operator.sqrt_matmul(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 matmul [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 matmul [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