Python array_ops.matrix_set_diag方法代码示例

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _MatrixSetDiagGrad(op, grad):
  """Gradient for MatrixSetDiag."""
  input_shape = op.inputs[0].get_shape().merge_with(grad.get_shape())
  diag_shape = op.inputs[1].get_shape()
  batch_shape = input_shape[:-2].merge_with(diag_shape[:-1])
  matrix_shape = input_shape[-2:]
  if batch_shape.is_fully_defined() and matrix_shape.is_fully_defined():
    diag_shape = batch_shape.as_list() + [min(matrix_shape.as_list())]
  else:
    with ops.colocate_with(grad):
      grad_shape = array_ops.shape(grad)
      grad_rank = array_ops.rank(grad)
      batch_shape = array_ops.slice(grad_shape, [0], [grad_rank - 2])
      matrix_shape = array_ops.slice(grad_shape, [grad_rank - 2], [2])
      min_dim = math_ops.reduce_min(matrix_shape)
      diag_shape = array_ops.concat([batch_shape, [min_dim]], 0)
  grad_input = array_ops.matrix_set_diag(
      grad, array_ops.zeros(
          diag_shape, dtype=grad.dtype))
  grad_diag = array_ops.matrix_diag_part(grad)
  return (grad_input, grad_diag) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _MatrixSetDiagGrad(op, grad):
  input_shape = op.inputs[0].get_shape().merge_with(grad.get_shape())
  diag_shape = op.inputs[1].get_shape()
  batch_shape = input_shape[:-2].merge_with(diag_shape[:-1])
  matrix_shape = input_shape[-2:]
  if batch_shape.is_fully_defined() and matrix_shape.is_fully_defined():
    diag_shape = batch_shape.as_list() + [min(matrix_shape.as_list())]
  else:
    with ops.colocate_with(grad):
      grad_shape = array_ops.shape(grad)
      grad_rank = array_ops.rank(grad)
      batch_shape = array_ops.slice(grad_shape, [0], [grad_rank - 2])
      matrix_shape = array_ops.slice(grad_shape, [grad_rank - 2], [2])
      min_dim = math_ops.reduce_min(matrix_shape)
      diag_shape = array_ops.concat([batch_shape, [min_dim]], 0)
  grad_input = array_ops.matrix_set_diag(
      grad, array_ops.zeros(
          diag_shape, dtype=grad.dtype))
  grad_diag = array_ops.matrix_diag_part(grad)
  return (grad_input, grad_diag) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def add_to_tensor(self, mat, name="add_to_tensor"):
    """Add matrix represented by this operator to `mat`.  Equiv to `I + mat`.

    Args:
      mat:  `Tensor` with same `dtype` and shape broadcastable to `self`.
      name:  A name to give this `Op`.

    Returns:
      A `Tensor` with broadcast shape and same `dtype` as `self`.
    """
    with self._name_scope(name, values=[mat]):
      # Shape [B1,...,Bb, 1]
      multiplier_vector = array_ops.expand_dims(self.multiplier, -1)

      # Shape [C1,...,Cc, M, M]
      mat = ops.convert_to_tensor(mat, name="mat")

      # Shape [C1,...,Cc, M]
      mat_diag = array_ops.matrix_diag_part(mat)

      # multiplier_vector broadcasts here.
      new_diag = multiplier_vector + mat_diag

      return array_ops.matrix_set_diag(mat, new_diag) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _MatrixSetDiagGrad(op, grad):
  input_shape = op.inputs[0].get_shape().merge_with(grad.get_shape())
  diag_shape = op.inputs[1].get_shape()
  batch_shape = input_shape[:-2].merge_with(diag_shape[:-1])
  matrix_shape = input_shape[-2:]
  if batch_shape.is_fully_defined() and matrix_shape.is_fully_defined():
    diag_shape = batch_shape.as_list() + [min(matrix_shape.as_list())]
  else:
    with ops.colocate_with(grad):
      grad_shape = array_ops.shape(grad)
      grad_rank = array_ops.rank(grad)
      batch_shape = array_ops.slice(grad_shape, [0], [grad_rank - 2])
      matrix_shape = array_ops.slice(grad_shape, [grad_rank - 2], [2])
      min_dim = math_ops.reduce_min(matrix_shape)
      diag_shape = array_ops.concat(0, [batch_shape, [min_dim]])
  grad_input = array_ops.matrix_set_diag(
      grad, array_ops.zeros(
          diag_shape, dtype=grad.dtype))
  grad_diag = array_ops.matrix_diag_part(grad)
  return (grad_input, grad_diag) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _CholeskyGrad(op, grad):
  """Gradient for Cholesky."""

  # Gradient is l^{-H} @ ((l^{H} @ grad) * (tril(ones)-1/2*eye)) @ l^{-1}
  l = op.outputs[0]
  num_rows = array_ops.shape(l)[-1]
  batch_shape = array_ops.shape(l)[:-2]
  l_inverse = linalg_ops.matrix_triangular_solve(l,
                                                 linalg_ops.eye(
                                                     num_rows,
                                                     batch_shape=batch_shape,
                                                     dtype=l.dtype))

  middle = math_ops.matmul(l, grad, adjoint_a=True)
  middle = array_ops.matrix_set_diag(middle,
                                     0.5 * array_ops.matrix_diag_part(middle))
  middle = array_ops.matrix_band_part(middle, -1, 0)

  grad_a = math_ops.matmul(
      math_ops.matmul(l_inverse, middle, adjoint_a=True), l_inverse)

  grad_a += math_ops.conj(array_ops.matrix_transpose(grad_a))
  return grad_a * 0.5 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _MatrixDiagPartGrad(op, grad):
  matrix_shape = op.inputs[0].get_shape()[-2:]
  if matrix_shape.is_fully_defined() and matrix_shape[0] == matrix_shape[1]:
    return array_ops.matrix_diag(grad)
  else:
    return array_ops.matrix_set_diag(array_ops.zeros_like(op.inputs[0]), grad) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _covariance(self):
    p = self.probs * array_ops.ones_like(
        self.total_count)[..., array_ops.newaxis]
    return array_ops.matrix_set_diag(
        -math_ops.matmul(self._mean_val[..., array_ops.newaxis],
                         p[..., array_ops.newaxis, :]),  # outer product
        self._variance()) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _covariance(self):
    x = self._variance_scale_term() * self._mean()
    return array_ops.matrix_set_diag(
        -math_ops.matmul(x[..., array_ops.newaxis],
                         x[..., array_ops.newaxis, :]),  # outer prod
        self._variance()) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _SelfAdjointEigV2Grad(op, grad_e, grad_v):
  """Gradient for SelfAdjointEigV2."""
  e = op.outputs[0]
  v = op.outputs[1]
  # a = op.inputs[0], which satisfies
  # a[...,:,:] * v[...,:,i] = e[...,i] * v[...,i]
  with ops.control_dependencies([grad_e.op, grad_v.op]):
    if grad_v is not None:
      # Construct the matrix f(i,j) = (i != j ? 1 / (e_i - e_j) : 0).
      # Notice that because of the term involving f, the gradient becomes
      # infinite (or NaN in practice) when eigenvalues are not unique.
      # Mathematically this should not be surprising, since for (k-fold)
      # degenerate eigenvalues, the corresponding eigenvectors are only defined
      # up to arbitrary rotation in a (k-dimensional) subspace.
      f = array_ops.matrix_set_diag(
          math_ops.reciprocal(
              array_ops.expand_dims(e, -2) - array_ops.expand_dims(e, -1)),
          array_ops.zeros_like(e))
      grad_a = math_ops.matmul(
          v,
          math_ops.matmul(
              array_ops.matrix_diag(grad_e) + f * math_ops.matmul(
                  v, grad_v, adjoint_a=True),
              v,
              adjoint_b=True))
    else:
      grad_a = math_ops.matmul(
          v, math_ops.matmul(
              array_ops.matrix_diag(grad_e), v, adjoint_b=True))
    # The forward op only depends on the lower triangular part of a, so here we
    # symmetrize and take the lower triangle
    grad_a = array_ops.matrix_band_part(
        grad_a + array_ops.matrix_transpose(grad_a), -1, 0)
    grad_a = array_ops.matrix_set_diag(grad_a,
                                       0.5 * array_ops.matrix_diag_part(grad_a))
    return grad_a 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _covariance(self):
    p = self.probs
    ret = -math_ops.matmul(p[..., None], p[..., None, :])
    return array_ops.matrix_set_diag(ret, self._variance()) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _add_to_tensor(self, mat):
    # Add to a tensor in O(k) time!
    mat_diag = array_ops.matrix_diag_part(mat)
    new_diag = self._scale + mat_diag
    return array_ops.matrix_set_diag(mat, new_diag) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _add_to_tensor(self, mat):
    mat_diag = array_ops.matrix_diag_part(mat)
    new_diag = self._diag + mat_diag
    return array_ops.matrix_set_diag(mat, new_diag) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _preprocess_tril(self, identity_multiplier, diag, tril, event_ndims):
    """Helper to preprocess a lower triangular matrix."""
    tril = array_ops.matrix_band_part(tril, -1, 0)  # Zero out TriU.
    if identity_multiplier is None and diag is None:
      return self._process_matrix(tril, min_rank=2, event_ndims=event_ndims)
    new_diag = array_ops.matrix_diag_part(tril)
    if identity_multiplier is not None:
      new_diag += identity_multiplier
    if diag is not None:
      new_diag += diag
    tril = array_ops.matrix_set_diag(tril, new_diag)
    return self._process_matrix(tril, min_rank=2, event_ndims=event_ndims) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def _add_to_tensor(self, x):
    x_diag = array_ops.matrix_diag_part(x)
    new_diag = self._diag + x_diag
    return array_ops.matrix_set_diag(x, new_diag) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import matrix_set_diag [as 别名]
def random_tril_matrix(shape,
                       dtype,
                       force_well_conditioned=False,
                       remove_upper=True):
  """[batch] lower triangular matrix.

  Args:
    shape:  `TensorShape` or Python `list`.  Shape of the returned matrix.
    dtype:  `TensorFlow` `dtype` or Python dtype
    force_well_conditioned:  Python `bool`. If `True`, returned matrix will have
      eigenvalues with modulus in `(1, 2)`.  Otherwise, eigenvalues are unit
      normal random variables.
    remove_upper:  Python `bool`.
      If `True`, zero out the strictly upper triangle.
      If `False`, the lower triangle of returned matrix will have desired
      properties, but will not not have the strictly upper triangle zero'd out.

  Returns:
    `Tensor` with desired shape and dtype.
  """
  with ops.name_scope("random_tril_matrix"):
    # Totally random matrix.  Has no nice properties.
    tril = random_normal(shape, dtype=dtype)
    if remove_upper:
      tril = array_ops.matrix_band_part(tril, -1, 0)

    # Create a diagonal with entries having modulus in [1, 2].
    if force_well_conditioned:
      maxval = ops.convert_to_tensor(np.sqrt(2.), dtype=dtype.real_dtype)
      diag = random_sign_uniform(
          shape[:-1], dtype=dtype, minval=1., maxval=maxval)
      tril = array_ops.matrix_set_diag(tril, diag)

    return tril