Restez organisé à l'aide des collections
Enregistrez et classez les contenus selon vos préférences.
flux tensoriel : : opérations : : QuantifiéMatMul
#include <math_ops.h>
Effectuez une multiplication matricielle quantifiée de a
par la matrice b
.
Résumé
Les entrées doivent être des matrices bidimensionnelles et la dimension intérieure de a
(après avoir été transposée si transpose_a
est non nulle) doit correspondre à la dimension extérieure de b
(après avoir été transposée si transposed_b
est non nulle).
Arguments :
- scope : un objet Scope
- a : Doit être un tenseur bidimensionnel.
- b : Doit être un tenseur bidimensionnel.
- min_a : la valeur flottante que représente
a
valeur quantifiée la plus basse. - max_a : la valeur flottante que représente
a
valeur quantifiée la plus élevée. - min_b : la valeur flottante que représente la valeur
b
quantifiée la plus basse. - max_b : la valeur flottante que représente la valeur
b
quantifiée la plus élevée.
Attributs facultatifs (voir Attrs
) :
- transpose_a : Si vrai,
a
est transposé avant la multiplication. - transpose_b : Si vrai,
b
est transposé avant la multiplication. - Tactivation : le type de sortie produite par la fonction d'activation suite à cette opération.
Retours :
-
Output
-
Output
min_out : la valeur flottante que représente la valeur de sortie quantifiée la plus basse. -
Output
max_out : la valeur flottante que représente la valeur de sortie quantifiée la plus élevée.
Constructeurs et Destructeurs |
---|
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) |
Attributs publics
Fonctions publiques
Fonctions statiques publiques
Activation
Attrs Tactivation(
DataType x
)
Sortie
Attrs Toutput(
DataType x
)
TransposerA
Attrs TransposeA(
bool x
)
TransposerB
Attrs TransposeB(
bool x
)
Sauf indication contraire, le contenu de cette page est régi par une licence Creative Commons Attribution 4.0, et les échantillons de code sont régis par une licence Apache 2.0. Pour en savoir plus, consultez les Règles du site Google Developers. Java est une marque déposée d'Oracle et/ou de ses sociétés affiliées.
Dernière mise à jour le 2025/07/25 (UTC).
[null,null,["Dernière mise à jour le 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```"]]