সেভ করা পৃষ্ঠা গুছিয়ে রাখতে 'সংগ্রহ' ব্যবহার করুন
আপনার পছন্দ অনুযায়ী কন্টেন্ট সেভ করুন ও সঠিক বিভাগে রাখুন।
টেনসরফ্লো :: অপস:: FakeQuantWithMinMaxVarsGradient
#include <array_ops.h>
FakeQuantWithMinMaxVars অপারেশনের জন্য গ্রেডিয়েন্ট গণনা করুন।
সারাংশ
যুক্তি:
ঐচ্ছিক বৈশিষ্ট্য (দেখুন Attrs
):
- num_bits: পরিমাপের বিটউইথ; 2 এবং 8 এর মধ্যে, অন্তর্ভুক্ত।
- narrow_range: 2^num_bit - 1টি স্বতন্ত্র মান-এ পরিমাপ করা হবে কিনা।
রিটার্ন:
-
Output
backprops_wrt_input: ব্যাকপ্রোপগেটেড গ্রেডিয়েন্ট wrt ইনপুট: gradients * (inputs >= min && inputs <= max)
। -
Output
backprop_wrt_min: Backpropagated gradients wrt min প্যারামিটার: sum(gradients * (inputs < min))
। -
Output
backprop_wrt_max: ব্যাকপ্রোপগেটেড গ্রেডিয়েন্ট wrt max প্যারামিটার: sum(gradients * (inputs > max))
।
পাবলিক বৈশিষ্ট্য
পাবলিক ফাংশন
পাবলিক স্ট্যাটিক ফাংশন
ন্যারোরেঞ্জ
Attrs NarrowRange(
bool x
)
NumBits
Attrs NumBits(
int64 x
)
অন্য কিছু উল্লেখ না করা থাকলে, এই পৃষ্ঠার কন্টেন্ট Creative Commons Attribution 4.0 License-এর অধীনে এবং কোডের নমুনাগুলি Apache 2.0 License-এর অধীনে লাইসেন্স প্রাপ্ত। আরও জানতে, Google Developers সাইট নীতি দেখুন। Java হল Oracle এবং/অথবা তার অ্যাফিলিয়েট সংস্থার রেজিস্টার্ড ট্রেডমার্ক।
2025-07-26 UTC-তে শেষবার আপডেট করা হয়েছে।
[null,null,["2025-07-26 UTC-তে শেষবার আপডেট করা হয়েছে।"],[],[],null,["# tensorflow::ops::FakeQuantWithMinMaxVarsGradient Class Reference\n\ntensorflow::ops::FakeQuantWithMinMaxVarsGradient\n================================================\n\n`#include \u003carray_ops.h\u003e`\n\nCompute gradients for a [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.\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.\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. min, max: Quantization interval, scalar floats.\n\n\u003cbr /\u003e\n\nOptional attributes (see [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)):\n\n- num_bits: The bitwidth of the quantization; between 2 and 8, 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: `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: `sum(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: `sum(gradients * (inputs \u003e max))`.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [FakeQuantWithMinMaxVarsGradient](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient_1ad9be97a8137f00d7e54153251f4f62ea)`(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| [FakeQuantWithMinMaxVarsGradient](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient_1a11b1c942c92067ddafc4db678f6d85b7)`(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 `[FakeQuantWithMinMaxVarsGradient::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)` & attrs)` ||\n\n| ### Public attributes ||\n|-----------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [backprop_wrt_max](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient_1abf26c1c7473251c45c87afadedb09d0a) | `::`[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_gradient_1a5230729c290e5cdc02a6498499e3214d) | `::`[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_gradient_1a2df281b7207f270927b8666d5af881dc) | `::`[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_gradient_1a916fa0e07f7154a9b6a1d1fa6b9e1ead) | [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_gradient_1a60218fbba17b3acc458fd338852f0764)`(bool x)` | [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) |\n| [NumBits](#classtensorflow_1_1ops_1_1_fake_quant_with_min_max_vars_gradient_1abbc87cb92b40cc087db232df595ab001)`(int64 x)` | [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) |\n\n| ### Structs ||\n|---------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/fake-quant-with-min-max-vars-gradient/attrs) | Optional 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\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### FakeQuantWithMinMaxVarsGradient\n\n```gdscript\n FakeQuantWithMinMaxVarsGradient(\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### FakeQuantWithMinMaxVarsGradient\n\n```gdscript\n FakeQuantWithMinMaxVarsGradient(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input gradients,\n ::tensorflow::Input inputs,\n ::tensorflow::Input min,\n ::tensorflow::Input max,\n const FakeQuantWithMinMaxVarsGradient::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```"]]