Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
tensor akışı:: işlem:: FakeQuantWithMinMaxVarsPerChannelGradient
#include <array_ops.h>
FakeQuantWithMinMaxVarsPerChannel işlemi için degradeleri hesaplayın.
Özet
Argümanlar:
- kapsam: Bir Kapsam nesnesi
- degradeler: FakeQuantWithMinMaxVars işleminin üzerinde geri yayılan degradeler; aşağıdakilerden birini şekillendirin:
[d]
, [b, d]
, [b, h, w, d]
. - girdiler: FakeQuantWithMinMaxVars işlemine girdi olarak iletilen değerler,
gradients
aynı şekildedir. min, max: Niceleme aralığı, [d]
şeklindeki kayan noktalar.
İsteğe bağlı özellikler (bkz. Attrs
):
- num_bits: Nicelemenin bit genişliği; 2 ile 16 arasında (dahil).
- dar_aralık: 2^num_bits - 1 farklı değer halinde nicemlenip nicelenmeyeceği.
İade:
-
Output
backprops_wrt_input: Girişlere göre geriye yayılan degradeler, inputs
aynı şekil: gradients * (inputs >= min && inputs <= max)
. -
Output
backprop_wrt_min: min parametresiyle geri yayılan degradeler, şekil [d]
: sum_per_d(gradients * (inputs < min))
. -
Output
backprop_wrt_max: Maksimum parametreye göre geriye yayılan degradeler, şekil [d]
: sum_per_d(gradients * (inputs > max))
.
Genel özellikler
Kamu işlevleri
Genel statik işlevler
Dar Aralık
Attrs NarrowRange(
bool x
)
NumBits
Attrs NumBits(
int64 x
)
Aksi belirtilmediği sürece bu sayfanın içeriği Creative Commons Atıf 4.0 Lisansı altında ve kod örnekleri Apache 2.0 Lisansı altında lisanslanmıştır. Ayrıntılı bilgi için Google Developers Site Politikaları'na göz atın. Java, Oracle ve/veya satış ortaklarının tescilli ticari markasıdır.
Son güncelleme tarihi: 2025-07-26 UTC.
[null,null,["Son güncelleme tarihi: 2025-07-26 UTC."],[],[],null,["# tensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient Class Reference\n\ntensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient\n==========================================================\n\n`#include \u003carray_ops.h\u003e`\n\nCompute gradients for a [FakeQuantWithMinMaxVarsPerChannel](/versions/r2.0/api_docs/cc/class/tensorflow/ops/fake-quant-with-min-max-vars-per-channel#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel) operation.\n\nSummary\n-------\n\nArguments:\n\n- scope: A [Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- gradients: Backpropagated gradients above the [FakeQuantWithMinMaxVars](/versions/r2.0/api_docs/cc/class/tensorflow/ops/fake-quant-with-min-max-vars#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars) operation, shape one of: `[d]`, `[b, d]`, `[b, h, w, d]`.\n- inputs: Values passed as inputs to the [FakeQuantWithMinMaxVars](/versions/r2.0/api_docs/cc/class/tensorflow/ops/fake-quant-with-min-max-vars#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars) operation, shape same as `gradients`. min, max: Quantization interval, floats of shape `[d]`.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r2.0/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)):\n\n- num_bits: The bitwidth of the quantization; between 2 and 16, inclusive.\n- narrow_range: Whether to quantize into 2\\^num_bits - 1 distinct values.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) backprops_wrt_input: Backpropagated gradients w.r.t. inputs, shape same as `inputs`: `gradients * (inputs \u003e= min && inputs \u003c= max)`.\n- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) backprop_wrt_min: Backpropagated gradients w.r.t. min parameter, shape `[d]`: `sum_per_d(gradients * (inputs \u003c min))`.\n- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) backprop_wrt_max: Backpropagated gradients w.r.t. max parameter, shape `[d]`: `sum_per_d(gradients * (inputs \u003e max))`.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [FakeQuantWithMinMaxVarsPerChannelGradient](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1a7521d0f809a9a2bab753031ec59937a1)`(const ::`[tensorflow::Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` gradients, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` inputs, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` min, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` max)` ||\n| [FakeQuantWithMinMaxVarsPerChannelGradient](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1abf40f598a2e88d6f3a163fc6ac8c5a7d)`(const ::`[tensorflow::Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` gradients, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` inputs, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` min, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` max, const `[FakeQuantWithMinMaxVarsPerChannelGradient::Attrs](/versions/r2.0/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)` & attrs)` ||\n\n| ### Public attributes ||\n|-----------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [backprop_wrt_max](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1acc9bf06f7b09f2437e913f6f32f6dfe0) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [backprop_wrt_min](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1ae7efb996b2e96e793a55decfaac3bfc4) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [backprops_wrt_input](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1a99d7e4cadd3a7b374e246edb6cc207fe) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n| [operation](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1a2054be8cb0cdd3bc1c9721baa5cca289) | [Operation](/versions/r2.0/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n\n| ### Public static functions ||\n|-------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [NarrowRange](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1a027f51a466b8dcf2dbff757b15dc7200)`(bool x)` | [Attrs](/versions/r2.0/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) |\n| [NumBits](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_per_channel_gradient_1ad2357206b80cb845d85a727dcdd2d022)`(int64 x)` | [Attrs](/versions/r2.0/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) |\n\n| ### Structs ||\n|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::FakeQuantWithMinMaxVarsPerChannelGradient::Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/fake-quant-with-min-max-vars-per-channel-gradient/attrs) | Optional attribute setters for [FakeQuantWithMinMaxVarsPerChannelGradient](/versions/r2.0/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\nPublic attributes\n-----------------\n\n### backprop_wrt_max\n\n```scdoc\n::tensorflow::Output backprop_wrt_max\n``` \n\n### backprop_wrt_min\n\n```scdoc\n::tensorflow::Output backprop_wrt_min\n``` \n\n### backprops_wrt_input\n\n```scdoc\n::tensorflow::Output backprops_wrt_input\n``` \n\n### operation\n\n```text\nOperation operation\n``` \n\nPublic functions\n----------------\n\n### FakeQuantWithMinMaxVarsPerChannelGradient\n\n```gdscript\n FakeQuantWithMinMaxVarsPerChannelGradient(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input gradients,\n ::tensorflow::Input inputs,\n ::tensorflow::Input min,\n ::tensorflow::Input max\n)\n``` \n\n### FakeQuantWithMinMaxVarsPerChannelGradient\n\n```gdscript\n FakeQuantWithMinMaxVarsPerChannelGradient(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input gradients,\n ::tensorflow::Input inputs,\n ::tensorflow::Input min,\n ::tensorflow::Input max,\n const FakeQuantWithMinMaxVarsPerChannelGradient::Attrs & attrs\n)\n``` \n\nPublic static functions\n-----------------------\n\n### NarrowRange\n\n```text\nAttrs NarrowRange(\n bool x\n)\n``` \n\n### NumBits\n\n```text\nAttrs NumBits(\n int64 x\n)\n```"]]