Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
aliran tensor:: operasi:: LearnedUnigramCandidateSampler
#include <candidate_sampling_ops.h> Menghasilkan label untuk pengambilan sampel kandidat dengan distribusi unigram yang dipelajari.
Ringkasan
Lihat penjelasan mengenai pengambilan sampel kandidat dan format datanya di go/candidate-sampling.
Untuk setiap batch, operasi ini mengambil satu set sampel label kandidat.
Keuntungan pengambilan sampel kandidat per batch adalah kesederhanaan dan kemungkinan perkalian matriks padat yang efisien. Kerugiannya adalah kandidat yang dijadikan sampel harus dipilih secara independen dari konteks dan label yang sebenarnya.
Argumen:
- ruang lingkup: Objek Lingkup
- true_classes: Matriks batch_size * num_true, yang setiap barisnya berisi ID num_true target_classes dalam label asli yang sesuai.
- num_true: Jumlah label yang benar per konteks.
- num_sampled: Jumlah kandidat yang akan diambil sampelnya secara acak.
- unik: Jika unik benar, kami mengambil sampel dengan penolakan, sehingga semua kandidat sampel dalam suatu kelompok adalah unik. Hal ini memerlukan beberapa perkiraan untuk memperkirakan probabilitas pengambilan sampel pasca penolakan.
- range_max: Sampler akan mengambil sampel bilangan bulat dari interval [0, range_max).
Atribut opsional (lihat Attrs ):
- seed: Jika salah satu seed atau seed2 disetel bukan nol, pembuat angka acak akan diunggulkan berdasarkan seed yang diberikan. Jika tidak, ia akan diunggulkan dengan benih acak.
- seed2: Seed kedua untuk menghindari tabrakan seed.
Pengembalian:
-
Output sampled_candidates: Vektor dengan panjang num_sampled, yang setiap elemennya adalah ID kandidat sampel. -
Output true_expected_count: Matriks batch_size * num_true, mewakili berapa kali setiap kandidat diharapkan muncul dalam kumpulan kandidat sampel. Jika unik=benar, maka ini adalah sebuah probabilitas. -
Output sampled_expected_count: Sebuah vektor dengan panjang num_sampled, untuk setiap kandidat sampel yang mewakili berapa kali kandidat tersebut diharapkan muncul dalam kumpulan kandidat sampel. Jika unik=benar, maka ini adalah sebuah probabilitas.
Konstruktor dan Destruktor |
|---|
LearnedUnigramCandidateSampler (const :: tensorflow::Scope & scope, :: tensorflow::Input true_classes, int64 num_true, int64 num_sampled, bool unique, int64 range_max)
|
LearnedUnigramCandidateSampler (const :: tensorflow::Scope & scope, :: tensorflow::Input true_classes, int64 num_true, int64 num_sampled, bool unique, int64 range_max, const LearnedUnigramCandidateSampler::Attrs & attrs)
|
Fungsi statis publik |
|---|
Seed (int64 x) | |
Seed2 (int64 x) | |
Atribut publik
Fungsi publik
LearnedUnigramCandidateSampler
LearnedUnigramCandidateSampler(
const ::tensorflow::Scope & scope,
::tensorflow::Input true_classes,
int64 num_true,
int64 num_sampled,
bool unique,
int64 range_max
)
Fungsi statis publik
Benih
Attrs Seed(
int64 x
)
Benih2
Attrs Seed2(
int64 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 2025-07-26 UTC.
[null,null,["Terakhir diperbarui pada 2025-07-26 UTC."],[],[],null,["# tensorflow::ops::LearnedUnigramCandidateSampler Class Reference\n\ntensorflow::ops::LearnedUnigramCandidateSampler\n===============================================\n\n`#include \u003ccandidate_sampling_ops.h\u003e`\n\nGenerates labels for candidate sampling with a learned unigram distribution.\n\nSummary\n-------\n\nSee explanations of candidate sampling and the data formats at go/candidate-sampling.\n\nFor each batch, this op picks a single set of sampled candidate labels.\n\nThe advantages of sampling candidates per-batch are simplicity and the possibility of efficient dense matrix multiplication. The disadvantage is that the sampled candidates must be chosen independently of the context and of the true labels.\n\nArguments:\n\n- scope: A [Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- true_classes: A batch_size \\* num_true matrix, in which each row contains the IDs of the num_true target_classes in the corresponding original label.\n- num_true: Number of true labels per context.\n- num_sampled: Number of candidates to randomly sample.\n- unique: If unique is true, we sample with rejection, so that all sampled candidates in a batch are unique. This requires some approximation to estimate the post-rejection sampling probabilities.\n- range_max: The sampler will sample integers from the interval \\[0, range_max).\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/learned-unigram-candidate-sampler/attrs#structtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1_1_attrs)):\n\n- seed: If either seed or seed2 are set to be non-zero, the random number generator is seeded by the given seed. Otherwise, it is seeded by a random seed.\n- seed2: An second seed to avoid seed collision.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) sampled_candidates: A vector of length num_sampled, in which each element is the ID of a sampled candidate.\n- [Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) true_expected_count: A batch_size \\* num_true matrix, representing the number of times each candidate is expected to occur in a batch of sampled candidates. If unique=true, then this is a probability.\n- [Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) sampled_expected_count: A vector of length num_sampled, for each sampled candidate representing the number of times the candidate is expected to occur in a batch of sampled candidates. If unique=true, then this is a probability.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [LearnedUnigramCandidateSampler](#classtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1a7c50027fcf319a0ac7abcc8af2d8861a)`(const ::`[tensorflow::Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` true_classes, int64 num_true, int64 num_sampled, bool unique, int64 range_max)` ||\n| [LearnedUnigramCandidateSampler](#classtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1aaddf15821aae74450fc3b415e18376a9)`(const ::`[tensorflow::Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` true_classes, int64 num_true, int64 num_sampled, bool unique, int64 range_max, const `[LearnedUnigramCandidateSampler::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/learned-unigram-candidate-sampler/attrs#structtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|----------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1a446093e6e23377b91e9335fb0b762ef7) | [Operation](/versions/r2.3/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [sampled_candidates](#classtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1a590ac067c5a83a4dba8105564bc56b88) | `::`[tensorflow::Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [sampled_expected_count](#classtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1ab7da3d1ba0800e7229aedb76fafaae7b) | `::`[tensorflow::Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [true_expected_count](#classtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1a91c0061329f572532d581b4175a2a8c6) | `::`[tensorflow::Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public static functions ||\n|----------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [Seed](#classtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1a7993b832d420f9ac8835e0070689ea0d)`(int64 x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/learned-unigram-candidate-sampler/attrs#structtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1_1_attrs) |\n| [Seed2](#classtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1a043a0a13bbd736a96b60b0a030061638)`(int64 x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/learned-unigram-candidate-sampler/attrs#structtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler_1_1_attrs) |\n\n| ### Structs ||\n|----------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::LearnedUnigramCandidateSampler::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/learned-unigram-candidate-sampler/attrs) | Optional attribute setters for [LearnedUnigramCandidateSampler](/versions/r2.3/api_docs/cc/class/tensorflow/ops/learned-unigram-candidate-sampler#classtensorflow_1_1ops_1_1_learned_unigram_candidate_sampler). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\n### sampled_candidates\n\n```scdoc\n::tensorflow::Output sampled_candidates\n``` \n\n### sampled_expected_count\n\n```scdoc\n::tensorflow::Output sampled_expected_count\n``` \n\n### true_expected_count\n\n```scdoc\n::tensorflow::Output true_expected_count\n``` \n\nPublic functions\n----------------\n\n### LearnedUnigramCandidateSampler\n\n```gdscript\n LearnedUnigramCandidateSampler(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input true_classes,\n int64 num_true,\n int64 num_sampled,\n bool unique,\n int64 range_max\n)\n``` \n\n### LearnedUnigramCandidateSampler\n\n```gdscript\n LearnedUnigramCandidateSampler(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input true_classes,\n int64 num_true,\n int64 num_sampled,\n bool unique,\n int64 range_max,\n const LearnedUnigramCandidateSampler::Attrs & attrs\n)\n``` \n\nPublic static functions\n-----------------------\n\n### Seed\n\n```text\nAttrs Seed(\n int64 x\n)\n``` \n\n### Seed2\n\n```text\nAttrs Seed2(\n int64 x\n)\n```"]]
