Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
tensoreflusso:: ops:: MatrixBandPart
#include <array_ops.h> Copia un tensore posizionando tutto al di fuori di una banda centrale in ciascuna matrice più interna.
Riepilogo
a zero.
La parte band viene calcolata come segue: Supponiamo che input abbia k dimensioni [I, J, K, ..., M, N] , quindi l'output è un tensore con la stessa forma dove
band[i, j, k, ..., m, n] = in_band(m, n) * input[i, j, k, ..., m, n] .
La funzione dell'indicatore
in_band(m, n) = (num_lower < 0 || (mn) <= num_lower)) && (num_upper < 0 || (nm) <= num_upper) .
Per esempio:
# if 'input' is [[ 0, 1, 2, 3]
[-1, 0, 1, 2]
[-2, -1, 0, 1]
[-3, -2, -1, 0]],tf.matrix_band_part(input, 1, -1) ==> [[ 0, 1, 2, 3]
[-1, 0, 1, 2]
[ 0, -1, 0, 1]
[ 0, 0, -1, 0]],tf.matrix_band_part(input, 2, 1) ==> [[ 0, 1, 0, 0]
[-1, 0, 1, 0]
[-2, -1, 0, 1]
[ 0, -2, -1, 0]] Casi particolari utili:
tf.matrix_band_part(input, 0, -1) ==> Upper triangular part.
tf.matrix_band_part(input, -1, 0) ==> Lower triangular part.
tf.matrix_band_part(input, 0, 0) ==> Diagonal.
Argomenti:
- scope: un oggetto Scope
- input: tensore di rango
k . - num_lower: tensore 0-D. Numero di sottodiagonali da conservare. Se negativo, mantieni l'intero triangolo inferiore.
- num_upper: tensore 0-D. Numero di superdiagonali da conservare. Se negativo, mantieni l'intero triangolo superiore.
Resi:
-
Output : tensore di rango k con la stessa forma dell'input. Il tensore a banda estratto.
Attributi pubblici
Funzioni pubbliche
nodo
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operatore::tensorflow::Output
operator::tensorflow::Output() const
Salvo quando diversamente specificato, i contenuti di questa pagina sono concessi in base alla licenza Creative Commons Attribution 4.0, mentre gli esempi di codice sono concessi in base alla licenza Apache 2.0. Per ulteriori dettagli, consulta le norme del sito di Google Developers. Java è un marchio registrato di Oracle e/o delle sue consociate.
Ultimo aggiornamento 2025-07-26 UTC.
[null,null,["Ultimo aggiornamento 2025-07-26 UTC."],[],[],null,["# tensorflow::ops::MatrixBandPart Class Reference\n\ntensorflow::ops::MatrixBandPart\n===============================\n\n`#include \u003carray_ops.h\u003e`\n\nCopy a tensor setting everything outside a central band in each innermost matrix.\n\nSummary\n-------\n\nto zero.\n\nThe `band` part is computed as follows: Assume `input` has `k` dimensions `[I, J, K, ..., M, N]`, then the output is a tensor with the same shape where\n\n`band[i, j, k, ..., m, n] = in_band(m, n) * input[i, j, k, ..., m, n]`.\n\nThe indicator function\n\n`in_band(m, n) = (num_lower \u003c 0 || (m-n) \u003c= num_lower)) && (num_upper \u003c 0 || (n-m) \u003c= num_upper)`.\n\nFor example:\n\n\n```text\n# if 'input' is [[ 0, 1, 2, 3]\n [-1, 0, 1, 2]\n [-2, -1, 0, 1]\n [-3, -2, -1, 0]],\n```\n\n\u003cbr /\u003e\n\n\n```scdoc\ntf.matrix_band_part(input, 1, -1) ==\u003e [[ 0, 1, 2, 3]\n [-1, 0, 1, 2]\n [ 0, -1, 0, 1]\n [ 0, 0, -1, 0]],\n```\n\n\u003cbr /\u003e\n\n\n```scdoc\ntf.matrix_band_part(input, 2, 1) ==\u003e [[ 0, 1, 0, 0]\n [-1, 0, 1, 0]\n [-2, -1, 0, 1]\n [ 0, -2, -1, 0]]\n```\n\n\u003cbr /\u003e\n\nUseful special cases:\n\n\n```scdoc\n tf.matrix_band_part(input, 0, -1) ==\u003e Upper triangular part.\n tf.matrix_band_part(input, -1, 0) ==\u003e Lower triangular part.\n tf.matrix_band_part(input, 0, 0) ==\u003e Diagonal.\n```\n\n\u003cbr /\u003e\n\nArguments:\n\n- scope: A [Scope](/versions/r2.1/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- input: Rank `k` tensor.\n- num_lower: 0-D tensor. Number of subdiagonals to keep. If negative, keep entire lower triangle.\n- num_upper: 0-D tensor. Number of superdiagonals to keep. If negative, keep entire upper triangle.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.1/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): Rank `k` tensor of the same shape as input. The extracted banded tensor.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [MatrixBandPart](#classtensorflow_1_1ops_1_1_matrix_band_part_1aafbd4f5790f99aabe649a2603fab5026)`(const ::`[tensorflow::Scope](/versions/r2.1/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` input, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` num_lower, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` num_upper)` ||\n\n| ### Public attributes ||\n|----------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [band](#classtensorflow_1_1ops_1_1_matrix_band_part_1a19ddd7640d84cfeb55298dcd2d150a8c) | `::`[tensorflow::Output](/versions/r2.1/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [operation](#classtensorflow_1_1ops_1_1_matrix_band_part_1a7f11fcb9cf1a97f13cded627a9579305) | [Operation](/versions/r2.1/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n\n| ### Public functions ||\n|----------------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_matrix_band_part_1a7a9ecf47b2def85ed1a8e7ab08dfe008)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_matrix_band_part_1a1b6a750bbd105a89c4ef9a398ccf7cf1)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_matrix_band_part_1a2be19e72aeddcea40f0be7cc6d6fdf97)`() const ` | ` ` ` ` |\n\nPublic attributes\n-----------------\n\n### band\n\n```text\n::tensorflow::Output band\n``` \n\n### operation\n\n```text\nOperation operation\n``` \n\nPublic functions\n----------------\n\n### MatrixBandPart\n\n```gdscript\n MatrixBandPart(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input,\n ::tensorflow::Input num_lower,\n ::tensorflow::Input num_upper\n)\n``` \n\n### node\n\n```gdscript\n::tensorflow::Node * node() const \n``` \n\n### operator::tensorflow::Input\n\n```gdscript\n operator::tensorflow::Input() const \n``` \n\n### operator::tensorflow::Output\n\n```gdscript\n operator::tensorflow::Output() const \n```"]]
