tensorflow :: ops :: MatrixDiagPartV3
Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
#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.
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.
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
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 wherer >= 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 thank[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 functions | |
---|---|
node() const | ::tensorflow::Node * |
operator::tensorflow::Input() const |
|
operator::tensorflow::Output() const |
|