Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
aliran tensor:: operasi:: FakeQuantWithMinMaxVarsGradien:: Attr
#include <array_ops.h> Penyetel atribut opsional untuk FakeQuantWithMinMaxVarsGradient .
Ringkasan
Fungsi publik |
|---|
NarrowRange (bool x) | Apakah akan dikuantisasi menjadi 2^num_bits - 1 nilai berbeda. |
NumBits (int64 x) | Bitwidth kuantisasi; antara 2 dan 8, inklusif. |
Atribut publik
rentang_sempit_
bool tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::narrow_range_ = false
jumlah_bit_
int64 tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::num_bits_ = 8
Fungsi publik
Rentang Sempit
TF_MUST_USE_RESULT Attrs tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::NarrowRange(
bool x
)
Apakah akan dikuantisasi menjadi 2^num_bits - 1 nilai berbeda.
Defaultnya salah
NomorBits
TF_MUST_USE_RESULT Attrs tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::NumBits(
int64 x
)
Bitwidth kuantisasi; antara 2 dan 8, inklusif.
Defaultnya adalah 8
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 2025-07-25 UTC.
[null,null,["Terakhir diperbarui pada 2025-07-25 UTC."],[],[],null,["# tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs Struct Reference\n\ntensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs\n=======================================================\n\n`#include \u003carray_ops.h\u003e`\n\nOptional attribute setters for [FakeQuantWithMinMaxVarsGradient](/versions/r2.0/api_docs/cc/class/tensorflow/ops/fake-quant-with-min-max-vars-gradient#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient).\n\nSummary\n-------\n\n| ### Public attributes ||\n|--------------------------------------------------------------------------------------------------------------------------------------------|---------|\n| [narrow_range_](#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient_1_1_attrs_1acf5b622a8301951bb06a117ee8f469fd)` = false` | `bool` |\n| [num_bits_](#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient_1_1_attrs_1af26251a3f20404321f755be4909b30b0)` = 8` | `int64` |\n\n| ### Public functions ||\n|------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [NarrowRange](#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient_1_1_attrs_1a1c24ca7db4de2e1c6b9fff5ed496c742)`(bool x)` | `TF_MUST_USE_RESULT `[Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/fake-quant-with-min-max-vars-gradient/attrs#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient_1_1_attrs) Whether to quantize into 2\\^num_bits - 1 distinct values. |\n| [NumBits](#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient_1_1_attrs_1a81834c121ffed56623556a3f30798089)`(int64 x)` | `TF_MUST_USE_RESULT `[Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/fake-quant-with-min-max-vars-gradient/attrs#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient_1_1_attrs) The bitwidth of the quantization; between 2 and 8, inclusive. |\n\nPublic attributes\n-----------------\n\n### narrow_range_\n\n```scdoc\nbool tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::narrow_range_ = false\n``` \n\n### num_bits_\n\n```scdoc\nint64 tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::num_bits_ = 8\n``` \n\nPublic functions\n----------------\n\n### NarrowRange\n\n```scdoc\nTF_MUST_USE_RESULT Attrs tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::NarrowRange(\n bool x\n)\n``` \nWhether to quantize into 2\\^num_bits - 1 distinct values.\n\nDefaults to false \n\n### NumBits\n\n```scdoc\nTF_MUST_USE_RESULT Attrs tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::NumBits(\n int64 x\n)\n``` \nThe bitwidth of the quantization; between 2 and 8, inclusive.\n\nDefaults to 8"]]
