Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
tensor akışı:: işlem:: QuantizedMatMul
#include <math_ops.h>
a
b
matrisiyle nicelenmiş matris çarpımını gerçekleştirin.
Özet
Girişler iki boyutlu matrisler olmalı ve a
iç boyutu ( transpose_a
sıfır değilse transpoze edildikten sonra) b
dış boyutuyla eşleşmelidir ( transposed_b
sıfır değilse transpoze edildikten sonra).
Argümanlar:
- kapsam: Bir Kapsam nesnesi
- a: İki boyutlu bir tensör olmalı.
- b: İki boyutlu bir tensör olmalı.
- min_a: En düşük niceliklendirilmiş
a
temsil ettiği kayan değer. - max_a: En yüksek nicelenmiş
a
temsil ettiği kayan değer. - min_b: En düşük nicelenmiş
b
değerinin temsil ettiği float değeri. - max_b: En yüksek nicelenmiş
b
değerinin temsil ettiği float değeri.
İsteğe bağlı özellikler (bkz. Attrs
):
- transpose_a: Eğer doğruysa,
a
çarpmadan önce transpoze edilir. - transpose_b: Eğer doğruysa,
b
çarpmadan önce transpoze edilir. - Dokunma: Bu işlemin ardından aktivasyon fonksiyonu tarafından üretilen çıktı türüdür.
İade:
-
Output
çıkışı -
Output
min_out: En düşük nicelenmiş çıkış değerinin temsil ettiği kayan değer. -
Output
max_out: En yüksek nicelenmiş çıkış değerinin temsil ettiği kayan değer.
Yapıcılar ve Yıkıcılar |
---|
QuantizedMatMul (const :: tensorflow::Scope & scope, :: tensorflow::Input a, :: tensorflow::Input b, :: tensorflow::Input min_a, :: tensorflow::Input max_a, :: tensorflow::Input min_b, :: tensorflow::Input max_b)
|
QuantizedMatMul (const :: tensorflow::Scope & scope, :: tensorflow::Input a, :: tensorflow::Input b, :: tensorflow::Input min_a, :: tensorflow::Input max_a, :: tensorflow::Input min_b, :: tensorflow::Input max_b, const QuantizedMatMul::Attrs & attrs) |
Genel özellikler
Kamu işlevleri
Genel statik işlevler
Dokunma
Attrs Tactivation(
DataType x
)
Çıkış
Attrs Toutput(
DataType 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: 2025-07-25 UTC.
[null,null,["Son güncelleme tarihi: 2025-07-25 UTC."],[],[],null,["# tensorflow::ops::QuantizedMatMul Class Reference\n\ntensorflow::ops::QuantizedMatMul\n================================\n\n`#include \u003cmath_ops.h\u003e`\n\nPerform a quantized matrix multiplication of `a` by the matrix `b`.\n\nSummary\n-------\n\nThe inputs must be two-dimensional matrices and the inner dimension of `a` (after being transposed if `transpose_a` is non-zero) must match the outer dimension of `b` (after being transposed if `transposed_b` is non-zero).\n\nArguments:\n\n- scope: A [Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- a: Must be a two-dimensional tensor.\n- b: Must be a two-dimensional tensor.\n- min_a: The float value that the lowest quantized `a` value represents.\n- max_a: The float value that the highest quantized `a` value represents.\n- min_b: The float value that the lowest quantized `b` value represents.\n- max_b: The float value that the highest quantized `b` value represents.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/quantized-mat-mul/attrs#structtensorflow_1_1ops_1_1_quantized_mat_mul_1_1_attrs)):\n\n- transpose_a: If true, `a` is transposed before multiplication.\n- transpose_b: If true, `b` is transposed before multiplication.\n- Tactivation: The type of output produced by activation function following this operation.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) out\n- [Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) min_out: The float value that the lowest quantized output value represents.\n- [Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) max_out: The float value that the highest quantized output value represents.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [QuantizedMatMul](#classtensorflow_1_1ops_1_1_quantized_mat_mul_1a0f09b0e35ddc6a6324c65db6ec69a731)`(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)` a, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` b, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` min_a, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` max_a, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` min_b, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` max_b)` ||\n| [QuantizedMatMul](#classtensorflow_1_1ops_1_1_quantized_mat_mul_1a882f02d4d46fa0c4ddb44a2e201929dc)`(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)` a, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` b, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` min_a, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` max_a, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` min_b, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` max_b, const `[QuantizedMatMul::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/quantized-mat-mul/attrs#structtensorflow_1_1ops_1_1_quantized_mat_mul_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|-----------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|\n| [max_out](#classtensorflow_1_1ops_1_1_quantized_mat_mul_1ad70908bf74ce2c40aa1f778693c60d8f) | `::`[tensorflow::Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [min_out](#classtensorflow_1_1ops_1_1_quantized_mat_mul_1a8dfe353eb1695a006f27c2cd8210b728) | `::`[tensorflow::Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [operation](#classtensorflow_1_1ops_1_1_quantized_mat_mul_1ad9abd5818d18e9d7f03c3db5ef1464ff) | [Operation](/versions/r1.15/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [out](#classtensorflow_1_1ops_1_1_quantized_mat_mul_1a891101c5425593a778947c2a3019d4a3) | `::`[tensorflow::Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public static functions ||\n|---------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------|\n| [Tactivation](#classtensorflow_1_1ops_1_1_quantized_mat_mul_1adf046668cb84feff06bb62ac8dfe9cb9)`(DataType x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/quantized-mat-mul/attrs#structtensorflow_1_1ops_1_1_quantized_mat_mul_1_1_attrs) |\n| [Toutput](#classtensorflow_1_1ops_1_1_quantized_mat_mul_1ab91328f7f63e496fbf14e3f2a7ca46fe)`(DataType x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/quantized-mat-mul/attrs#structtensorflow_1_1ops_1_1_quantized_mat_mul_1_1_attrs) |\n| [TransposeA](#classtensorflow_1_1ops_1_1_quantized_mat_mul_1afbe2add319dc39e1db4dc583f556def9)`(bool x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/quantized-mat-mul/attrs#structtensorflow_1_1ops_1_1_quantized_mat_mul_1_1_attrs) |\n| [TransposeB](#classtensorflow_1_1ops_1_1_quantized_mat_mul_1a6525a94155917583356eb70dd02f1f72)`(bool x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/quantized-mat-mul/attrs#structtensorflow_1_1ops_1_1_quantized_mat_mul_1_1_attrs) |\n\n| ### Structs ||\n|----------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::QuantizedMatMul::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/quantized-mat-mul/attrs) | Optional attribute setters for [QuantizedMatMul](/versions/r1.15/api_docs/cc/class/tensorflow/ops/quantized-mat-mul#classtensorflow_1_1ops_1_1_quantized_mat_mul). |\n\nPublic attributes\n-----------------\n\n### max_out\n\n```scdoc\n::tensorflow::Output max_out\n``` \n\n### min_out\n\n```scdoc\n::tensorflow::Output min_out\n``` \n\n### operation\n\n```text\nOperation operation\n``` \n\n### out\n\n```text\n::tensorflow::Output out\n``` \n\nPublic functions\n----------------\n\n### QuantizedMatMul\n\n```gdscript\n QuantizedMatMul(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input a,\n ::tensorflow::Input b,\n ::tensorflow::Input min_a,\n ::tensorflow::Input max_a,\n ::tensorflow::Input min_b,\n ::tensorflow::Input max_b\n)\n``` \n\n### QuantizedMatMul\n\n```gdscript\n QuantizedMatMul(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input a,\n ::tensorflow::Input b,\n ::tensorflow::Input min_a,\n ::tensorflow::Input max_a,\n ::tensorflow::Input min_b,\n ::tensorflow::Input max_b,\n const QuantizedMatMul::Attrs & attrs\n)\n``` \n\nPublic static functions\n-----------------------\n\n### Tactivation\n\n```text\nAttrs Tactivation(\n DataType x\n)\n``` \n\n### Toutput\n\n```text\nAttrs Toutput(\n DataType 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```"]]