Conozca lo último en aprendizaje automático, IA generativa y más en el
Simposio WiML 2023.
Organiza tus páginas con colecciones
Guarda y categoriza el contenido según tus preferencias.
tensorflow :: operaciones :: Multinomial
#include <random_ops.h>
Extrae muestras de una distribución multinomial.
Resumen
Argumentos:
- alcance: un objeto de alcance
- logits: Tensor 2-D con forma
[batch_size, num_classes]
. Cada segmento [i, :]
,: [i, :]
representa las probabilidades logarítmicas no normalizadas para todas las clases. - núm_muestras: 0-D. Número de muestras independientes para dibujar para cada segmento de fila.
Atributos opcionales (consulte Attrs
):
- semilla: si semilla o semilla2 se establece en un valor distinto de cero, el generador de números aleatorios interno es sembrado por la semilla dada. De lo contrario, se utiliza una semilla aleatoria.
- seed2: Una segunda semilla para evitar la colisión de semillas.
Devoluciones:
-
Output
: Tensor 2-D con forma [batch_size, num_samples]
. Cada segmento [i, :]
[0, num_classes)
[i, :]
contiene las etiquetas de clase dibujadas con rango [0, num_classes)
.
Atributos públicos
Funciones publicas
nodo
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operador :: tensorflow :: Salida
operator::tensorflow::Output() const
Funciones estáticas públicas
Tipo de salida
Attrs OutputDtype(
DataType x
)
Semilla
Attrs Seed(
int64 x
)
Semilla2
Attrs Seed2(
int64 x
)
Salvo que se indique lo contrario, el contenido de esta página está sujeto a la licencia Atribución 4.0 de Creative Commons, y los ejemplos de código están sujetos a la licencia Apache 2.0. Para obtener más información, consulta las políticas del sitio de Google Developers. Java es una marca registrada de Oracle o sus afiliados.
Última actualización: 2020-04-20 (UTC)
[null,null,["Última actualización: 2020-04-20 (UTC)"],[],[],null,["# tensorflow::ops::Multinomial Class Reference\n\ntensorflow::ops::Multinomial\n============================\n\n`#include \u003crandom_ops.h\u003e`\n\nDraws samples from a multinomial distribution.\n\nSummary\n-------\n\nArguments:\n\n- scope: A [Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- logits: 2-D [Tensor](/versions/r1.15/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor) with shape `[batch_size, num_classes]`. Each slice `[i, :]` represents the unnormalized log probabilities for all classes.\n- num_samples: 0-D. Number of independent samples to draw for each row slice.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/multinomial/attrs#structtensorflow_1_1ops_1_1_multinomial_1_1_attrs)):\n\n- seed: If either seed or seed2 is set to be non-zero, the internal random number generator is seeded by the given seed. Otherwise, a random seed is used.\n- seed2: A second seed to avoid seed collision.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): 2-D [Tensor](/versions/r1.15/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor) with shape `[batch_size, num_samples]`. Each slice `[i, :]` contains the drawn class labels with range `[0, num_classes)`.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [Multinomial](#classtensorflow_1_1ops_1_1_multinomial_1a96d252cc42db1e0cad0a64cb36e8dd17)`(const ::`[tensorflow::Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` logits, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` num_samples)` ||\n| [Multinomial](#classtensorflow_1_1ops_1_1_multinomial_1a70c0ba099add2db08773240f75d985e3)`(const ::`[tensorflow::Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` logits, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` num_samples, const `[Multinomial::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/multinomial/attrs#structtensorflow_1_1ops_1_1_multinomial_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|-----------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_multinomial_1a45b39de08c317c75ef554114ab7305f2) | [Operation](/versions/r1.15/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_multinomial_1a6a1eb6aa0ee5680c889a15fcbb64eea1) | `::`[tensorflow::Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|-----------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_multinomial_1ae386d54422fe11f8963cdb5c403c4dd5)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_multinomial_1ab7c86d59414a2504b91b5e9f6a34e7b9)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_multinomial_1a2c35c8fd690941576d7163b605d01678)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|---------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------|\n| [OutputDtype](#classtensorflow_1_1ops_1_1_multinomial_1a52a67bb622d9dc2c672d5b534e498335)`(DataType x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/multinomial/attrs#structtensorflow_1_1ops_1_1_multinomial_1_1_attrs) |\n| [Seed](#classtensorflow_1_1ops_1_1_multinomial_1a5fba481081090883283e3b7e556565ee)`(int64 x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/multinomial/attrs#structtensorflow_1_1ops_1_1_multinomial_1_1_attrs) |\n| [Seed2](#classtensorflow_1_1ops_1_1_multinomial_1ae46c069e65181a29054c3f64ac06d630)`(int64 x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/multinomial/attrs#structtensorflow_1_1ops_1_1_multinomial_1_1_attrs) |\n\n| ### Structs ||\n|------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::Multinomial::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/multinomial/attrs) | Optional attribute setters for [Multinomial](/versions/r1.15/api_docs/cc/class/tensorflow/ops/multinomial#classtensorflow_1_1ops_1_1_multinomial). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\n### output\n\n```text\n::tensorflow::Output output\n``` \n\nPublic functions\n----------------\n\n### Multinomial\n\n```gdscript\n Multinomial(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input logits,\n ::tensorflow::Input num_samples\n)\n``` \n\n### Multinomial\n\n```gdscript\n Multinomial(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input logits,\n ::tensorflow::Input num_samples,\n const Multinomial::Attrs & attrs\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``` \n\nPublic static functions\n-----------------------\n\n### OutputDtype\n\n```carbon\nAttrs OutputDtype(\n DataType x\n)\n``` \n\n### Seed\n\n```text\nAttrs Seed(\n int64 x\n)\n``` \n\n### Seed2\n\n```text\nAttrs Seed2(\n int64 x\n)\n```"]]