컬렉션을 사용해 정리하기
내 환경설정을 기준으로 콘텐츠를 저장하고 분류하세요.
텐서플로우:: 작전:: MaxPoolGradGrad
#include <nn_ops.h>
maxpooling 함수의 2차 기울기를 계산합니다.
요약
인수:
- 범위: 범위 개체
- orig_input: 원래 입력 텐서.
- orig_output: 원본 출력 텐서.
- 대학원: 4-D. 그라디언트의 그라디언트는
max_pool
의 입력입니다. - ksize: 입력 텐서의 각 차원에 대한 창 크기입니다.
- strides: 입력 텐서의 각 차원에 대한 슬라이딩 윈도우의 보폭입니다.
- padding: 사용할 패딩 알고리즘 유형입니다.
선택적 속성( Attrs
참조):
- data_format: 입력 및 출력 데이터의 데이터 형식을 지정합니다. 기본 형식인 "NHWC"를 사용하면 데이터가 [batch, in_height, in_width, in_channels] 순서로 저장됩니다. 또는 형식은 [batch, in_channels, in_height, in_width]의 데이터 저장 순서인 "NCHW"일 수 있습니다.
보고:
-
Output
: 기울기의 기울기는 max_pool
에 대한 입력입니다.
생성자와 소멸자 |
---|
MaxPoolGradGrad (const :: tensorflow::Scope & scope, :: tensorflow::Input orig_input, :: tensorflow::Input orig_output, :: tensorflow::Input grad, const gtl::ArraySlice< int > & ksize, const gtl::ArraySlice< int > & strides, StringPiece padding)
|
MaxPoolGradGrad (const :: tensorflow::Scope & scope, :: tensorflow::Input orig_input, :: tensorflow::Input orig_output, :: tensorflow::Input grad, const gtl::ArraySlice< int > & ksize, const gtl::ArraySlice< int > & strides, StringPiece padding, const MaxPoolGradGrad::Attrs & attrs) |
공개 속성
공공 기능
마디
::tensorflow::Node * node() const
operator::tensorflow::Input() const
연산자::텐서플로우::출력
operator::tensorflow::Output() const
공개 정적 함수
Attrs DataFormat(
StringPiece x
)
달리 명시되지 않는 한 이 페이지의 콘텐츠에는 Creative Commons Attribution 4.0 라이선스에 따라 라이선스가 부여되며, 코드 샘플에는 Apache 2.0 라이선스에 따라 라이선스가 부여됩니다. 자세한 내용은 Google Developers 사이트 정책을 참조하세요. 자바는 Oracle 및/또는 Oracle 계열사의 등록 상표입니다.
최종 업데이트: 2025-07-26(UTC)
[null,null,["최종 업데이트: 2025-07-26(UTC)"],[],[],null,["# tensorflow::ops::MaxPoolGradGrad Class Reference\n\ntensorflow::ops::MaxPoolGradGrad\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/r2.1/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- orig_input: The original input tensor.\n- orig_output: The original output tensor.\n- grad: 4-D. Gradients of gradients w.r.t. the input 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/r2.1/api_docs/cc/struct/tensorflow/ops/max-pool-grad-grad/attrs#structtensorflow_1_1ops_1_1_max_pool_grad_grad_1_1_attrs)):\n\n- data_format: Specify the data format of the input and output data. With the default format \"NHWC\", the data is stored in the order of: \\[batch, in_height, in_width, in_channels\\]. Alternatively, the format could be \"NCHW\", the data storage order of: \\[batch, in_channels, in_height, in_width\\].\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.1/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): Gradients of gradients w.r.t. the input to `max_pool`.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [MaxPoolGradGrad](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_1a624a485e1ee030cfb203f5767164e05d)`(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)` orig_input, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` orig_output, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, const gtl::ArraySlice\u003c int \u003e & ksize, const gtl::ArraySlice\u003c int \u003e & strides, StringPiece padding)` ||\n| [MaxPoolGradGrad](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_1a105790392c03a29e7a1a93c4a25f1065)`(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)` orig_input, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` orig_output, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` grad, const gtl::ArraySlice\u003c int \u003e & ksize, const gtl::ArraySlice\u003c int \u003e & strides, StringPiece padding, const `[MaxPoolGradGrad::Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/max-pool-grad-grad/attrs#structtensorflow_1_1ops_1_1_max_pool_grad_grad_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_1aaced190ad09e9b1e03ba1758d3846c59) | [Operation](/versions/r2.1/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_1a1db2508c1fc12d0bbbaf034e1332e8e9) | `::`[tensorflow::Output](/versions/r2.1/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_1a0a817f73310d28bd0344cba01c80d9eb)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_1aa9cf85f8e08191a34aec8a97b5c7d7b5)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_1a85951360272d8bcb3d56b273d5e3a06a)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------|\n| [DataFormat](#classtensorflow_1_1ops_1_1_max_pool_grad_grad_1a2595c027a5b997820e1f11301e2f8e5b)`(StringPiece x)` | [Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/max-pool-grad-grad/attrs#structtensorflow_1_1ops_1_1_max_pool_grad_grad_1_1_attrs) |\n\n| ### Structs ||\n|----------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::MaxPoolGradGrad::Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/max-pool-grad-grad/attrs) | Optional attribute setters for [MaxPoolGradGrad](/versions/r2.1/api_docs/cc/class/tensorflow/ops/max-pool-grad-grad#classtensorflow_1_1ops_1_1_max_pool_grad_grad). |\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### MaxPoolGradGrad\n\n```gdscript\n MaxPoolGradGrad(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input orig_input,\n ::tensorflow::Input orig_output,\n ::tensorflow::Input grad,\n const gtl::ArraySlice\u003c int \u003e & ksize,\n const gtl::ArraySlice\u003c int \u003e & strides,\n StringPiece padding\n)\n``` \n\n### MaxPoolGradGrad\n\n```gdscript\n MaxPoolGradGrad(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input orig_input,\n ::tensorflow::Input orig_output,\n ::tensorflow::Input grad,\n const gtl::ArraySlice\u003c int \u003e & ksize,\n const gtl::ArraySlice\u003c int \u003e & strides,\n StringPiece padding,\n const MaxPoolGradGrad::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### DataFormat\n\n```text\nAttrs DataFormat(\n StringPiece x\n)\n```"]]