Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
aliran tensor:: operasi:: TopK
#include <nn_ops.h> Menemukan nilai dan indeks k elemen terbesar untuk dimensi terakhir.
Ringkasan
Jika masukannya adalah vektor (peringkat-1), carilah k entri terbesar dalam vektor tersebut dan keluarkan nilai dan indeksnya sebagai vektor. Jadi values[j] adalah entri terbesar ke- j di input , dan indeksnya adalah indices[j] .
Untuk matriks (masing-masing masukan dengan peringkat lebih tinggi), hitung k entri teratas di setiap baris (masing-masing vektor sepanjang dimensi terakhir). Dengan demikian,
values.shape = indices.shape = input.shape[:-1] + [k]
Jika dua elemen sama, elemen dengan indeks lebih rendah akan muncul terlebih dahulu.
Argumen:
- ruang lingkup: Objek Lingkup
- input: 1-D atau lebih tinggi dengan dimensi terakhir setidaknya
k . - k: 0-D. Jumlah elemen teratas yang harus dicari sepanjang dimensi terakhir (sepanjang setiap baris matriks).
Atribut opsional (lihat Attrs ):
- diurutkan: Jika benar,
k elemen yang dihasilkan akan diurutkan berdasarkan nilai dalam urutan menurun.
Pengembalian:
- Nilai
Output : k elemen terbesar sepanjang setiap potongan dimensi terakhir. - Indeks
Output : Indeks values dalam dimensi terakhir input .
Fungsi statis publik |
|---|
Sorted (bool x) | |
Atribut publik
Fungsi publik
Fungsi statis publik
Diurutkan
Attrs Sorted(
bool x
)
Kecuali dinyatakan lain, konten di halaman ini dilisensikan berdasarkan Lisensi Creative Commons Attribution 4.0, sedangkan contoh kode dilisensikan berdasarkan Lisensi Apache 2.0. Untuk mengetahui informasi selengkapnya, lihat Kebijakan Situs Google Developers. Java adalah merek dagang terdaftar dari Oracle dan/atau afiliasinya.
Terakhir diperbarui pada 2025-07-27 UTC.
[null,null,["Terakhir diperbarui pada 2025-07-27 UTC."],[],[],null,["# tensorflow::ops::TopK Class Reference\n\ntensorflow::ops::TopK\n=====================\n\n`#include \u003cnn_ops.h\u003e`\n\nFinds values and indices of the `k` largest elements for the last dimension.\n\nSummary\n-------\n\nIf the input is a vector (rank-1), finds the `k` largest entries in the vector and outputs their values and indices as vectors. Thus `values[j]` is the `j`-th largest entry in `input`, and its index is `indices[j]`.\n\nFor matrices (resp. higher rank input), computes the top `k` entries in each row (resp. vector along the last dimension). Thus, \n\n```cplint\nvalues.shape = indices.shape = input.shape[:-1] + [k]\n```\n\n\u003cbr /\u003e\n\nIf two elements are equal, the lower-index element appears first.\n\nArguments:\n\n- scope: A [Scope](/versions/r2.1/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- input: 1-D or higher with last dimension at least `k`.\n- k: 0-D. Number of top elements to look for along the last dimension (along each row for matrices).\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/top-k/attrs#structtensorflow_1_1ops_1_1_top_k_1_1_attrs)):\n\n- sorted: If true the resulting `k` elements will be sorted by the values in descending order.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.1/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) values: The `k` largest elements along each last dimensional slice.\n- [Output](/versions/r2.1/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) indices: The indices of `values` within the last dimension of `input`.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [TopK](#classtensorflow_1_1ops_1_1_top_k_1a0c8404c5e20cae7d52b460b213d13bf4)`(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)` input, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` k)` ||\n| [TopK](#classtensorflow_1_1ops_1_1_top_k_1ad55e14f1c8e36a07ae7e3e5189ce1de6)`(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)` input, ::`[tensorflow::Input](/versions/r2.1/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` k, const `[TopK::Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/top-k/attrs#structtensorflow_1_1ops_1_1_top_k_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|-----------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [indices](#classtensorflow_1_1ops_1_1_top_k_1a702b5fcc223806a5b43892c840294e6e) | `::`[tensorflow::Output](/versions/r2.1/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [operation](#classtensorflow_1_1ops_1_1_top_k_1a6772614af084e9178999f8b10e356ce4) | [Operation](/versions/r2.1/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [values](#classtensorflow_1_1ops_1_1_top_k_1a3d754e075cd5e04093e27e60a6a07727) | `::`[tensorflow::Output](/versions/r2.1/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public static functions ||\n|------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------|\n| [Sorted](#classtensorflow_1_1ops_1_1_top_k_1ac5e55d49539ee3457dc1a432480e85c2)`(bool x)` | [Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/top-k/attrs#structtensorflow_1_1ops_1_1_top_k_1_1_attrs) |\n\n| ### Structs ||\n|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::TopK::Attrs](/versions/r2.1/api_docs/cc/struct/tensorflow/ops/top-k/attrs) | Optional attribute setters for [TopK](/versions/r2.1/api_docs/cc/class/tensorflow/ops/top-k#classtensorflow_1_1ops_1_1_top_k). |\n\nPublic attributes\n-----------------\n\n### indices\n\n```text\n::tensorflow::Output indices\n``` \n\n### operation\n\n```text\nOperation operation\n``` \n\n### values\n\n```text\n::tensorflow::Output values\n``` \n\nPublic functions\n----------------\n\n### TopK\n\n```gdscript\n TopK(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input,\n ::tensorflow::Input k\n)\n``` \n\n### TopK\n\n```gdscript\n TopK(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input,\n ::tensorflow::Input k,\n const TopK::Attrs & attrs\n)\n``` \n\nPublic static functions\n-----------------------\n\n### Sorted\n\n```text\nAttrs Sorted(\n bool x\n)\n```"]]
