Organízate con las colecciones
Guarda y clasifica el contenido según tus preferencias.
flujo tensor:: operaciones:: MaxPoolGradGradWithArgmax
#include <nn_ops.h>
Calcula gradientes de segundo orden de la función maxpooling.
Resumen
Argumentos:
- alcance: un objeto de alcance
- entrada: La entrada original.
- grad: 4-D con forma
[batch, height, width, channels]
. Los gradientes corresponden a la entrada de max_pool
. - argmax: los índices de los valores máximos elegidos para cada salida de
max_pool
. - ksize: el tamaño de la ventana para cada dimensión del tensor de entrada.
- zancadas: la zancada de la ventana deslizante para cada dimensión del tensor de entrada.
- padding: el tipo de algoritmo de relleno que se utilizará.
Atributos opcionales (ver Attrs
):
- include_batch_in_index: si se debe incluir la dimensión del lote en el índice aplanado de
argmax
.
Devoluciones:
-
Output
: Los gradientes de gradientes son la entrada de max_pool
.
Constructores y destructores |
---|
MaxPoolGradGradWithArgmax (const :: tensorflow::Scope & scope, :: tensorflow::Input input, :: tensorflow::Input grad, :: tensorflow::Input argmax, const gtl::ArraySlice< int > & ksize, const gtl::ArraySlice< int > & strides, StringPiece padding)
|
MaxPoolGradGradWithArgmax (const :: tensorflow::Scope & scope, :: tensorflow::Input input, :: tensorflow::Input grad, :: tensorflow::Input argmax, const gtl::ArraySlice< int > & ksize, const gtl::ArraySlice< int > & strides, StringPiece padding, const MaxPoolGradGradWithArgmax::Attrs & attrs) |
Atributos públicos
Funciones públicas
nodo
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operador::tensorflow::Salida
operator::tensorflow::Output() const
Funciones estáticas públicas
IncluirBatchInIndex
Attrs IncludeBatchInIndex(
bool x
)
A menos que se indique lo contrario, el contenido de esta página está sujeto a la licencia Reconocimiento 4.0 de Creative Commons y las muestras de código están sujetas a la licencia Apache 2.0. Para obtener más información, consulta las políticas del sitio web de Google Developers. Java es una marca registrada de Oracle o sus afiliados.
Última actualización: 2025-07-27 (UTC).
[null,null,["Última actualización: 2025-07-27 (UTC)."],[],[],null,["# tensorflow::ops::MaxPoolGradGradWithArgmax Class Reference\n\ntensorflow::ops::MaxPoolGradGradWithArgmax\n==========================================\n\n`#include \u003cnn_ops.h\u003e`\n\nComputes second-order gradients of the maxpooling function.\n\nSummary\n-------\n\nArguments:\n\n- scope: A [Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- input: The original input.\n- grad: 4-D with shape `[batch, height, width, channels]`. Gradients w.r.t. the input of `max_pool`.\n- argmax: The indices of the maximum values chosen for each output of `max_pool`.\n- ksize: The size of the window for each dimension of the input tensor.\n- strides: The stride of the sliding window for each dimension of the input tensor.\n- padding: The type of padding algorithm to use.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/max-pool-grad-grad-with-argmax/attrs#structtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1_1_attrs)):\n\n- include_batch_in_index: Whether to include batch dimension in flattened index of `argmax`.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): Gradients of gradients w.r.t. the input of `max_pool`.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [MaxPoolGradGradWithArgmax](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1a593b2e655426fc2115b078b9fa3d58c9)`(const ::`[tensorflow::Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` input, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` argmax, const gtl::ArraySlice\u003c int \u003e & ksize, const gtl::ArraySlice\u003c int \u003e & strides, StringPiece padding)` ||\n| [MaxPoolGradGradWithArgmax](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1ae16cefddf3e2d1bc07b1be0a310d0f5f)`(const ::`[tensorflow::Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` input, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` argmax, const gtl::ArraySlice\u003c int \u003e & ksize, const gtl::ArraySlice\u003c int \u003e & strides, StringPiece padding, const `[MaxPoolGradGradWithArgmax::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/max-pool-grad-grad-with-argmax/attrs#structtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1ad7651c4aa8ab3970d854e03fea44b931) | [Operation](/versions/r2.3/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1a1df14c4bce71fd9dc7d6011430a93483) | `::`[tensorflow::Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|------------------------------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1a4fab108da33b0eca234b7b8476eadc8a)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1a1c878b05b1f1c50d0ac8b18bd8dabe5c)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1a8de5ba5ff913d7e716975d514f3a398a)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|--------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [IncludeBatchInIndex](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1a08b144b554cd408cdae86515c196fbf0)`(bool x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/max-pool-grad-grad-with-argmax/attrs#structtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax_1_1_attrs) |\n\n| ### Structs ||\n|--------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::MaxPoolGradGradWithArgmax::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/max-pool-grad-grad-with-argmax/attrs) | Optional attribute setters for [MaxPoolGradGradWithArgmax](/versions/r2.3/api_docs/cc/class/tensorflow/ops/max-pool-grad-grad-with-argmax#classtensorflow_1_1ops_1_1_max_pool_grad_grad_with_argmax). |\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### MaxPoolGradGradWithArgmax\n\n```gdscript\n MaxPoolGradGradWithArgmax(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input,\n ::tensorflow::Input grad,\n ::tensorflow::Input argmax,\n const gtl::ArraySlice\u003c int \u003e & ksize,\n const gtl::ArraySlice\u003c int \u003e & strides,\n StringPiece padding\n)\n``` \n\n### MaxPoolGradGradWithArgmax\n\n```gdscript\n MaxPoolGradGradWithArgmax(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input,\n ::tensorflow::Input grad,\n ::tensorflow::Input argmax,\n const gtl::ArraySlice\u003c int \u003e & ksize,\n const gtl::ArraySlice\u003c int \u003e & strides,\n StringPiece padding,\n const MaxPoolGradGradWithArgmax::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### IncludeBatchInIndex\n\n```text\nAttrs IncludeBatchInIndex(\n bool x\n)\n```"]]