Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Operasi Pengambilan Sampel Kandidat
Ringkasan
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,["# Candidate Sampling Ops\n======================\n\nSummary\n-------\n\n| ### Classes ||\n|--------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------|\n| [tensorflow::ops::AllCandidateSampler](/versions/r2.1/api_docs/cc/class/tensorflow/ops/all-candidate-sampler) | Generates labels for candidate sampling with a learned unigram distribution. |\n| [tensorflow::ops::ComputeAccidentalHits](/versions/r2.1/api_docs/cc/class/tensorflow/ops/compute-accidental-hits) | Computes the ids of the positions in sampled_candidates that match true_labels. |\n| [tensorflow::ops::FixedUnigramCandidateSampler](/versions/r2.1/api_docs/cc/class/tensorflow/ops/fixed-unigram-candidate-sampler) | Generates labels for candidate sampling with a learned unigram distribution. |\n| [tensorflow::ops::LearnedUnigramCandidateSampler](/versions/r2.1/api_docs/cc/class/tensorflow/ops/learned-unigram-candidate-sampler) | Generates labels for candidate sampling with a learned unigram distribution. |\n| [tensorflow::ops::LogUniformCandidateSampler](/versions/r2.1/api_docs/cc/class/tensorflow/ops/log-uniform-candidate-sampler) | Generates labels for candidate sampling with a log-uniform distribution. |\n| [tensorflow::ops::UniformCandidateSampler](/versions/r2.1/api_docs/cc/class/tensorflow/ops/uniform-candidate-sampler) | Generates labels for candidate sampling with a uniform distribution. |"]]
