Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
tensoreflusso:: ops:: Trasmetti a
#include <array_ops.h> Trasmetti un array per una forma compatibile.
Riepilogo
Il broadcasting è il processo di creazione di array in modo che abbiano forme compatibili per le operazioni aritmetiche. Due forme sono compatibili se per ciascuna coppia di dimensioni sono uguali o se una di esse è una. Quando si tenta di trasmettere un tensore a una forma, si inizia con le dimensioni finali e si procede in avanti.
Per esempio,
>>> x = tf.constant([1, 2, 3])
>>> y = tf.broadcast_to(x, [3, 3])
>>> sess.run(y)
array([[1, 2, 3],
[1, 2, 3],
[1, 2, 3]], dtype=int32) Nell'esempio precedente, il tensore di input con la forma di [1, 3] viene trasmesso al tensore di output con la forma di [3, 3] .
Argomenti:
- scope: un oggetto Scope
- input: un tensore da trasmettere.
- forma: un tensore
int 1-D . La forma dell'output desiderato.
Resi:
Attributi pubblici
Funzioni pubbliche
nodo
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operatore::tensorflow::Output
operator::tensorflow::Output() const
Salvo quando diversamente specificato, i contenuti di questa pagina sono concessi in base alla licenza Creative Commons Attribution 4.0, mentre gli esempi di codice sono concessi in base alla licenza Apache 2.0. Per ulteriori dettagli, consulta le norme del sito di Google Developers. Java è un marchio registrato di Oracle e/o delle sue consociate.
Ultimo aggiornamento 2025-07-25 UTC.
[null,null,["Ultimo aggiornamento 2025-07-25 UTC."],[],[],null,["# tensorflow::ops::BroadcastTo Class Reference\n\ntensorflow::ops::BroadcastTo\n============================\n\n`#include \u003carray_ops.h\u003e`\n\nBroadcast an array for a compatible shape.\n\nSummary\n-------\n\nBroadcasting is the process of making arrays to have compatible shapes for arithmetic operations. Two shapes are compatible if for each dimension pair they are either equal or one of them is one. When trying to broadcast a [Tensor](/versions/r2.0/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor) to a shape, it starts with the trailing dimensions, and works its way forward.\n\nFor example,\n\n\n```gdscript\n\u003e\u003e\u003e x = tf.constant([1, 2, 3])\n\u003e\u003e\u003e y = tf.broadcast_to(x, [3, 3])\n\u003e\u003e\u003e sess.run(y)\narray([[1, 2, 3],\n [1, 2, 3],\n [1, 2, 3]], dtype=int32)\n```\n\n\u003cbr /\u003e\n\nIn the above example, the input [Tensor](/versions/r2.0/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor) with the shape of `[1, 3]` is broadcasted to output [Tensor](/versions/r2.0/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor) with shape of `[3, 3]`.\n\nArguments:\n\n- scope: A [Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- input: A [Tensor](/versions/r2.0/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor) to broadcast.\n- shape: An 1-D `int`[Tensor](/versions/r2.0/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor). The shape of the desired output.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): A [Tensor](/versions/r2.0/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor).\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [BroadcastTo](#classtensorflow_1_1ops_1_1_broadcast_to_1a37bf1f8b63e588def9b3805017209ee6)`(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)` input, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` shape)` ||\n\n| ### Public attributes ||\n|------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_broadcast_to_1abb152ff71cda1cf3af84a7c656faac03) | [Operation](/versions/r2.0/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_broadcast_to_1aaa451e1fc17fe438aa744a2880efca62) | `::`[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_broadcast_to_1a2c429236acfd549d2252190a63a446f0)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_broadcast_to_1a21be2705c2eba98f1cf7560295561b58)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_broadcast_to_1a43222f4482f5ccb868548380633ce7f5)`() const ` | ` ` ` ` |\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### BroadcastTo\n\n```gdscript\n BroadcastTo(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input,\n ::tensorflow::Input shape\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```"]]
