tensorflow :: ops :: MatrixDiagPartV3

#include <array_ops.h>

Retorna a parte diagonal em lote de um tensor em lote.

Resumo

Retorna um tensor com as diagonais k[0] a k[1] -ésimas da input lote.

Suponha que a input tenha r dimensões [I, J, ..., L, M, N] . Seja max_diag_len o comprimento máximo entre todas as diagonais a serem extraídas, max_diag_len = min(M + min(k[1], 0), N + min(-k[0], 0)) Seja num_diags o número de diagonais para extrair, num_diags = k[1] - k[0] + 1 .

Se num_diags == 1 , o tensor de saída é de classificação r - 1 com forma [I, J, ..., L, max_diag_len] e valores:

diagonal[i, j, ..., l, n]
  = input[i, j, ..., l, n+y, n+x] ; if 0 <= n+y < M and 0 <= n+x < N,
    padding_value                 ; otherwise.
onde y = max(-k[1], 0) , x = max(k[1], 0) .

Caso contrário, o tensor de saída tem classificação r com dimensões [I, J, ..., L, num_diags, max_diag_len] com valores:

diagonal[i, j, ..., l, m, n]
  = input[i, j, ..., l, n+y, n+x] ; if 0 <= n+y < M and 0 <= n+x < N,
    padding_value                 ; otherwise.
onde d = k[1] - m , y = max(-d, 0) - offset e x = max(d, 0) - offset .

offset é zero, exceto quando o alinhamento da diagonal é para a direita.

offset = max_diag_len - diag_len(d) ; if (`align` in {RIGHT_LEFT, RIGHT_RIGHT}
                                           and `d >= 0`) or
                                         (`align` in {LEFT_RIGHT, RIGHT_RIGHT}
                                           and `d <= 0`)
         0                          ; otherwise
onde diag_len(d) = min(cols - max(d, 0), rows + min(d, 0)) .

A entrada deve ser pelo menos uma matriz.

Por exemplo:

input = np.array([[[1, 2, 3, 4],  # Input shape: (2, 3, 4)
                   [5, 6, 7, 8],
                   [9, 8, 7, 6]],
                  [[5, 4, 3, 2],
                   [1, 2, 3, 4],
                   [5, 6, 7, 8]]])

# A main diagonal from each batch.
tf.matrix_diag_part(input) ==> [[1, 6, 7],  # Output shape: (2, 3)
                                [5, 2, 7]]

# A superdiagonal from each batch.
tf.matrix_diag_part(input, k = 1)
  ==> [[2, 7, 6],  # Output shape: (2, 3)
       [4, 3, 8]]

# A band from each batch.
tf.matrix_diag_part(input, k = (-1, 2))
  ==> [[[0, 3, 8],  # Output shape: (2, 4, 3)
        [2, 7, 6],
        [1, 6, 7],
        [5, 8, 0]],
       [[0, 3, 4],
        [4, 3, 8],
        [5, 2, 7],
        [1, 6, 0]]]

# LEFT_RIGHT alignment.
tf.matrix_diag_part(input, k = (-1, 2), align="LEFT_RIGHT")
  ==> [[[3, 8, 0],  # Output shape: (2, 4, 3)
        [2, 7, 6],
        [1, 6, 7],
        [0, 5, 8]],
       [[3, 4, 0],
        [4, 3, 8],
        [5, 2, 7],
        [0, 1, 6]]]

# max_diag_len can be shorter than the main diagonal.
tf.matrix_diag_part(input, k = (-2, -1))
  ==> [[[5, 8],
        [9, 0]],
       [[1, 6],
        [5, 0]]]

# padding_value = 9
tf.matrix_diag_part(input, k = (1, 3), padding_value = 9)
  ==> [[[9, 9, 4],  # Output shape: (2, 3, 3)
        [9, 3, 8],
        [2, 7, 6]],
       [[9, 9, 2],
        [9, 3, 4],
        [4, 3, 8]]]

  

Arguments:

  • scope: A Scope object
  • input: Rank r tensor where r >= 2.
  • k: Diagonal offset(s). Positive value means superdiagonal, 0 refers to the main diagonal, and negative value means subdiagonals. k can be a single integer (for a single diagonal) or a pair of integers specifying the low and high ends of a matrix band. k[0] must not be larger than k[1].
  • padding_value: The value to fill the area outside the specified diagonal band with. Default is 0.

Optional attributes (see Attrs):

  • align: Some diagonals are shorter than max_diag_len and need to be padded. align is a string specifying how superdiagonals and subdiagonals should be aligned, respectively. There are four possible alignments: "RIGHT_LEFT" (default), "LEFT_RIGHT", "LEFT_LEFT", and "RIGHT_RIGHT". "RIGHT_LEFT" aligns superdiagonals to the right (left-pads the row) and subdiagonals to the left (right-pads the row). It is the packing format LAPACK uses. cuSPARSE uses "LEFT_RIGHT", which is the opposite alignment.

Returns:

  • Output: The extracted diagonal(s).

Constructors and Destructors

MatrixDiagPartV3(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input k, ::tensorflow::Input padding_value)
MatrixDiagPartV3(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input k, ::tensorflow::Input padding_value, const MatrixDiagPartV3::Attrs & attrs)

Public attributes

diagonal
operation

Public functions

node() const
::tensorflow::Node *
operator::tensorflow::Input() const
operator::tensorflow::Output() const

Public static functions

Align(StringPiece x)

Structs

tensorflow::ops::MatrixDiagPartV3::Attrs

Optional attribute setters for MatrixDiagPartV3.

Public attributes

diagonal

::tensorflow::Output diagonal

Operação

Operation operation

Funções públicas

MatrixDiagPartV3

 MatrixDiagPartV3(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input k,
  ::tensorflow::Input padding_value
)

MatrixDiagPartV3

 MatrixDiagPartV3(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input k,
  ::tensorflow::Input padding_value,
  const MatrixDiagPartV3::Attrs & attrs
)

::tensorflow::Node * node() const 

operador :: tensorflow :: Input

 operator::tensorflow::Input() const 

operador :: tensorflow :: Saída

 operator::tensorflow::Output() const 

Funções estáticas públicas

Alinhar

Attrs Align(
  StringPiece x
)