Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
tensor akışı:: işlem:: SeyrekMatMul
#include <math_ops.h> "a" matrisini "b" matrisiyle çarpın .
Özet
Girişler iki boyutlu matrisler olmalı ve "a"nın iç boyutu "b"nin dış boyutuyla eşleşmelidir. Hem "a" hem de "b" SparseTensor değil Tensor olmalıdır. Bu işlem, "a" veya "b"den en az birinin seyrek olduğu, yani büyük oranda sıfır değerlerine sahip olduğu durum için optimize edilmiştir. Bunu bir platformda yoğun matris çarpımına karşı kullanmanın başabaş noktası, seyrek matriste %30 sıfır değeriydi.
Bu işlemin gradyan hesaplaması, yalnızca bu degrade bir Relu'dan geldiğinde giriş degradesindeki seyreklikten yararlanacaktır.
Argümanlar:
İade:
Genel özellikler
Kamu işlevleri
düğüm
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operatör::tensorflow::Çıktı
operator::tensorflow::Output() const
Genel statik işlevler
AI'ler Seyrek
Attrs AIsSparse(
bool x
)
BI'ler Seyrek
Attrs BIsSparse(
bool x
)
A'yı devrik
Attrs TransposeA(
bool x
)
B'yi devrik
Attrs TransposeB(
bool x
)
Aksi belirtilmediği sürece bu sayfanın içeriği Creative Commons Atıf 4.0 Lisansı altında ve kod örnekleri Apache 2.0 Lisansı altında lisanslanmıştır. Ayrıntılı bilgi için Google Developers Site Politikaları'na göz atın. Java, Oracle ve/veya satış ortaklarının tescilli ticari markasıdır.
Son güncelleme tarihi: 2025-07-26 UTC.
[null,null,["Son güncelleme tarihi: 2025-07-26 UTC."],[],[],null,["# tensorflow::ops::SparseMatMul Class Reference\n\ntensorflow::ops::SparseMatMul\n=============================\n\n`#include \u003cmath_ops.h\u003e`\n\n[Multiply](/versions/r2.0/api_docs/cc/class/tensorflow/ops/multiply#classtensorflow_1_1ops_1_1_multiply) matrix \"a\" by matrix \"b\".\n\nSummary\n-------\n\nThe inputs must be two-dimensional matrices and the inner dimension of \"a\" must match the outer dimension of \"b\". Both \"a\" and \"b\" must be [Tensor](/versions/r2.0/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor)s not `SparseTensor`s. This op is optimized for the case where at least one of \"a\" or \"b\" is sparse, in the sense that they have a large proportion of zero values. The breakeven for using this versus a dense matrix multiply on one platform was 30% zero values in the sparse matrix.\n\nThe gradient computation of this operation will only take advantage of sparsity in the input gradient when that gradient comes from a [Relu](/versions/r2.0/api_docs/cc/class/tensorflow/ops/relu#classtensorflow_1_1ops_1_1_relu).\n\nArguments:\n\n- scope: A [Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): The product tensor.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [SparseMatMul](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1a44ec3b9c8a4a6c27ec1e5defa921a8c2)`(const ::`[tensorflow::Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` a, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` b)` ||\n| [SparseMatMul](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1a29e8ca18f70b1f18d2d5931606fa5108)`(const ::`[tensorflow::Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` a, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` b, const `[SparseMatMul::Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/sparse-mat-mul/attrs#structtensorflow_1_1ops_1_1_sparse_mat_mul_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|--------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1af4bedc3c3ba71553d0c1e30513898430) | [Operation](/versions/r2.0/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [product](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1a9b708969f18250faa3e40edad285ae45) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|--------------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1ae461c34d275e4d996e21af14b8870531)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1a7e6d0d764e73510a120ea967abaf9250)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1a3fee7729e51d2b640d654a25a84f0185)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|-------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|\n| [AIsSparse](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1acaa26e8e9d1e5854dcfef57dcb4efd5b)`(bool x)` | [Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/sparse-mat-mul/attrs#structtensorflow_1_1ops_1_1_sparse_mat_mul_1_1_attrs) |\n| [BIsSparse](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1aaf87a4805b8269233969a514bea852ef)`(bool x)` | [Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/sparse-mat-mul/attrs#structtensorflow_1_1ops_1_1_sparse_mat_mul_1_1_attrs) |\n| [TransposeA](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1a41b864162f17688227aa34ee4d8021b2)`(bool x)` | [Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/sparse-mat-mul/attrs#structtensorflow_1_1ops_1_1_sparse_mat_mul_1_1_attrs) |\n| [TransposeB](#classtensorflow_1_1ops_1_1_sparse_mat_mul_1af58949ad4394aa0ba7869e65ba742487)`(bool x)` | [Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/sparse-mat-mul/attrs#structtensorflow_1_1ops_1_1_sparse_mat_mul_1_1_attrs) |\n\n| ### Structs ||\n|---------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::SparseMatMul::Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/sparse-mat-mul/attrs) | Optional attribute setters for [SparseMatMul](/versions/r2.0/api_docs/cc/class/tensorflow/ops/sparse-mat-mul#classtensorflow_1_1ops_1_1_sparse_mat_mul). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\n### product\n\n```text\n::tensorflow::Output product\n``` \n\nPublic functions\n----------------\n\n### SparseMatMul\n\n```gdscript\n SparseMatMul(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input a,\n ::tensorflow::Input b\n)\n``` \n\n### SparseMatMul\n\n```gdscript\n SparseMatMul(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input a,\n ::tensorflow::Input b,\n const SparseMatMul::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### AIsSparse\n\n```text\nAttrs AIsSparse(\n bool x\n)\n``` \n\n### BIsSparse\n\n```text\nAttrs BIsSparse(\n bool x\n)\n``` \n\n### TransposeA\n\n```text\nAttrs TransposeA(\n bool x\n)\n``` \n\n### TransposeB\n\n```text\nAttrs TransposeB(\n bool x\n)\n```"]]
