Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
tensoreflusso:: ops:: FakeQuantWithMinMaxVarsPerChannelGradient:: Attr
#include <array_ops.h> Setter di attributi facoltativi per FakeQuantWithMinMaxVarsPerChannelGradient .
Riepilogo
Funzioni pubbliche |
|---|
NarrowRange (bool x) | Indica se quantizzare in 2^num_bits - 1 valori distinti. |
NumBits (int64 x) | La larghezza di bit della quantizzazione; dai 2 ai 16 anni compresi. |
Attributi pubblici
intervallo_ristretto_
bool tensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient::Attrs::narrow_range_ = false
num_bit_
int64 tensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient::Attrs::num_bits_ = 8
Funzioni pubbliche
Raggio ristretto
TF_MUST_USE_RESULT Attrs tensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient::Attrs::NarrowRange(
bool x
)
Indica se quantizzare in 2^num_bits - 1 valori distinti.
Il valore predefinito è falso
NumBits
TF_MUST_USE_RESULT Attrs tensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient::Attrs::NumBits(
int64 x
)
La larghezza di bit della quantizzazione; dai 2 ai 16 anni compresi.
Il valore predefinito è 8
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 2025-07-26 UTC.
[null,null,["Ultimo aggiornamento 2025-07-26 UTC."],[],[],null,["# tensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient::Attrs Struct Reference\n\ntensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient::Attrs\n=================================================================\n\n`#include \u003carray_ops.h\u003e`\n\nOptional attribute setters for [FakeQuantWithMinMaxVarsPerChannelGradient](/versions/r2.3/api_docs/cc/class/tensorflow/ops/fake-quant-with-min-max-vars-per-channel-gradient#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient).\n\nSummary\n-------\n\n| ### Public attributes ||\n|--------------------------------------------------------------------------------------------------------------------------------------------------------|---------|\n| [narrow_range_](#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1_1_attrs_1a19bcc6e3056cc06a975a5a7236e38607)` = false` | `bool` |\n| [num_bits_](#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1_1_attrs_1a1d8955c276cd7afe9a8cc3b3cec65b80)` = 8` | `int64` |\n\n| ### Public functions ||\n|------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [NarrowRange](#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1_1_attrs_1a7c6086869fd2c913591598734e50c734)`(bool x)` | `TF_MUST_USE_RESULT `[Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/fake-quant-with-min-max-vars-per-channel-gradient/attrs#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_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_per_channel_gradient_1_1_attrs_1aa00e6a2d0d011a7cec018693b25d8311)`(int64 x)` | `TF_MUST_USE_RESULT `[Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/fake-quant-with-min-max-vars-per-channel-gradient/attrs#structtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1_1_attrs) The bitwidth of the quantization; between 2 and 16, inclusive. |\n\nPublic attributes\n-----------------\n\n### narrow_range_\n\n```scdoc\nbool tensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient::Attrs::narrow_range_ = false\n``` \n\n### num_bits_\n\n```scdoc\nint64 tensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient::Attrs::num_bits_ = 8\n``` \n\nPublic functions\n----------------\n\n### NarrowRange\n\n```scdoc\nTF_MUST_USE_RESULT Attrs tensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient::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::FakeQuantWithMinMaxVarsPerChannelGradient::Attrs::NumBits(\n int64 x\n)\n``` \nThe bitwidth of the quantization; between 2 and 16, inclusive.\n\nDefaults to 8"]]
