Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
fluxo tensor:: ops:: Desquantizar
#include <array_ops.h> Desquantize o tensor de 'entrada' em um Tensor flutuante.
Resumo
[min_range, max_range] são valores flutuantes escalares que especificam o intervalo para os dados de 'entrada'. O atributo 'mode' controla exatamente quais cálculos são usados para converter os valores flutuantes em seus equivalentes quantizados.
No modo 'MIN_COMBINED', cada valor do tensor passará pelo seguinte:
if T == qint8: in[i] += (range(T) + 1)/ 2.0
out[i] = min_range + (in[i]* (max_range - min_range) / range(T))
aqui
range(T) = numeric_limits ::max() - numeric_limits ::min() range(T) = numeric_limits ::max() - numeric_limits ::min() range(T) = numeric_limits ::max() - numeric_limits ::min() Exemplo de modo MIN_COMBINED
Se a entrada vier de QuantizedRelu6 , o tipo de saída será quint8 (intervalo de 0 a 255), mas o intervalo possível de QuantizedRelu6 será de 0 a 6. Os valores min_range e max_range são, portanto, 0,0 e 6,0. Dequantize em quint8 pegará cada valor, converterá em float e multiplicará por 6/255. Observe que se quantizedtype for qint8, a operação adicionará adicionalmente cada valor por 128 antes da conversão.
Se o modo for 'MIN_FIRST', esta abordagem será usada:
num_discrete_values = 1 << (# of bits in T)
range_adjust = num_discrete_values / (num_discrete_values - 1)
range = (range_max - range_min) * range_adjust
range_scale = range / num_discrete_values
const double offset_input = static_cast(input) - lowest_quantized;
result = range_min + ((input - numeric_limits::min()) * range_scale)
Exemplo de modo ESCALADO
O modo SCALED corresponde à abordagem de quantização usada em QuantizeAndDequantize{V2|V3} .
Se o modo for SCALED , não usamos toda a faixa do tipo de saída, optando por omitir o valor mais baixo possível para simetria (por exemplo, a faixa de saída é -127 a 127, não -128 a 127 para quantização de 8 bits com sinal), então 0,0 mapeia para 0.
Primeiro encontramos o intervalo de valores em nosso tensor. O intervalo que usamos é sempre centrado em 0, então encontramos m tal que
m = max(abs(input_min), abs(input_max))
Nosso intervalo de tensores de entrada é então [-m, m] .
A seguir, escolhemos nossos intervalos de quantização de ponto fixo, [min_fixed, max_fixed] . Se T estiver assinado, isso é
num_bits = sizeof(T) * 8
[min_fixed, max_fixed] =
[-(1 << (num_bits - 1) - 1), (1 << (num_bits - 1)) - 1] Caso contrário, se T não tiver sinal, o intervalo do ponto fixo é
[min_fixed, max_fixed] = [0, (1 << num_bits) - 1]
A partir disso calculamos nosso fator de escala, s:
s = (2 * m) / (max_fixed - min_fixed)
Agora podemos desquantizar os elementos do nosso tensor:
result = input * s
Argumentos:
- escopo: um objeto Escopo
- min_range: O valor escalar mínimo possivelmente produzido para a entrada.
- max_range: O valor escalar máximo possivelmente produzido para a entrada.
Retorna:
Funções estáticas públicas |
|---|
Mode (StringPiece x) | |
Atributos públicos
Funções públicas
nó
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operador::tensorflow::Saída
operator::tensorflow::Output() const
Funções estáticas públicas
Modo
Attrs Mode(
StringPiece x
)
Exceto em caso de indicação contrária, o conteúdo desta página é licenciado de acordo com a Licença de atribuição 4.0 do Creative Commons, e as amostras de código são licenciadas de acordo com a Licença Apache 2.0. Para mais detalhes, consulte as políticas do site do Google Developers. Java é uma marca registrada da Oracle e/ou afiliadas.
Última atualização 2025-07-25 UTC.
[null,null,["Última atualização 2025-07-25 UTC."],[],[],null,["# tensorflow::ops::Dequantize Class Reference\n\ntensorflow::ops::Dequantize\n===========================\n\n`#include \u003carray_ops.h\u003e`\n\n[Dequantize](/versions/r2.0/api_docs/cc/class/tensorflow/ops/dequantize#classtensorflow_1_1ops_1_1_dequantize) the 'input' tensor into a float [Tensor](/versions/r2.0/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor).\n\nSummary\n-------\n\n\\[min_range, max_range\\] are scalar floats that specify the range for the 'input' data. The 'mode' attribute controls exactly which calculations are used to convert the float values to their quantized equivalents.\n\nIn 'MIN_COMBINED' mode, each value of the tensor will undergo the following:\n\n\u003cbr /\u003e\n\n```transact-sql\nif T == qint8: in[i] += (range(T) + 1)/ 2.0\nout[i] = min_range + (in[i]* (max_range - min_range) / range(T))\n```\nhere `range(T) = numeric_limits`::max() - numeric_limits::min()\n\n\u003cbr /\u003e\n\n\n*MIN_COMBINED Mode Example*\n\nIf the input comes from a [QuantizedRelu6](/versions/r2.0/api_docs/cc/class/tensorflow/ops/quantized-relu6#classtensorflow_1_1ops_1_1_quantized_relu6), the output type is quint8 (range of 0-255) but the possible range of [QuantizedRelu6](/versions/r2.0/api_docs/cc/class/tensorflow/ops/quantized-relu6#classtensorflow_1_1ops_1_1_quantized_relu6) is 0-6. The min_range and max_range values are therefore 0.0 and 6.0. [Dequantize](/versions/r2.0/api_docs/cc/class/tensorflow/ops/dequantize#classtensorflow_1_1ops_1_1_dequantize) on quint8 will take each value, cast to float, and multiply by 6 / 255. Note that if quantizedtype is qint8, the operation will additionally add each value by 128 prior to casting.\n\nIf the mode is 'MIN_FIRST', then this approach is used:\n\n\n```gdscript\nnum_discrete_values = 1 \u003c\u003c (# of bits in T)\nrange_adjust = num_discrete_values / (num_discrete_values - 1)\nrange = (range_max - range_min) * range_adjust\nrange_scale = range / num_discrete_values\nconst double offset_input = static_cast(input) - lowest_quantized;\nresult = range_min + ((input - numeric_limits::min()) * range_scale)\n```\n\n\u003cbr /\u003e\n\n\n*SCALED mode Example*\n\n`SCALED` mode matches the quantization approach used in `QuantizeAndDequantize{V2|V3}`.\n\nIf the mode is `SCALED`, we do not use the full range of the output type, choosing to elide the lowest possible value for symmetry (e.g., output range is -127 to 127, not -128 to 127 for signed 8 bit quantization), so that 0.0 maps to 0.\n\nWe first find the range of values in our tensor. The range we use is always centered on 0, so we find m such that \n\n```scdoc\n m = max(abs(input_min), abs(input_max))\n```\n\n\u003cbr /\u003e\n\nOur input tensor range is then `[-m, m]`.\n\nNext, we choose our fixed-point quantization buckets, `[min_fixed, max_fixed]`. If T is signed, this is \n\n```scdoc\n num_bits = sizeof(T) * 8\n [min_fixed, max_fixed] =\n [-(1 \u003c\u003c (num_bits - 1) - 1), (1 \u003c\u003c (num_bits - 1)) - 1]\n```\n\n\u003cbr /\u003e\n\nOtherwise, if T is unsigned, the fixed-point range is \n\n```scdoc\n [min_fixed, max_fixed] = [0, (1 \u003c\u003c num_bits) - 1]\n```\n\n\u003cbr /\u003e\n\nFrom this we compute our scaling factor, s: \n\n```scdoc\n s = (2 * m) / (max_fixed - min_fixed)\n```\n\n\u003cbr /\u003e\n\nNow we can dequantize the elements of our tensor: \n\n```scdoc\nresult = input * s\n```\n\n\u003cbr /\u003e\n\nArguments:\n\n- scope: A [Scope](/versions/r2.0/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- min_range: The minimum scalar value possibly produced for the input.\n- max_range: The maximum scalar value possibly produced for the input.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): The output tensor.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [Dequantize](#classtensorflow_1_1ops_1_1_dequantize_1ace6411557abc00c6e59649720be7d579)`(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)` input, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` min_range, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` max_range)` ||\n| [Dequantize](#classtensorflow_1_1ops_1_1_dequantize_1afb71f46f9e4fc4922578ecd9116ad9b1)`(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)` input, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` min_range, ::`[tensorflow::Input](/versions/r2.0/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` max_range, const `[Dequantize::Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/dequantize/attrs#structtensorflow_1_1ops_1_1_dequantize_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|----------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_dequantize_1a917ce29fbec6ef49406db9a374bde9aa) | [Operation](/versions/r2.0/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_dequantize_1a5c4618ae3d058bcd8547217612f8f41e) | `::`[tensorflow::Output](/versions/r2.0/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|----------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_dequantize_1a4bdeb613e4b88880638a67528cbd01f0)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_dequantize_1ab1b62ee39a382d6e124eb62156c05525)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_dequantize_1ae01ee2df9b62f7729848ca15ed70e8fc)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|----------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------|\n| [Mode](#classtensorflow_1_1ops_1_1_dequantize_1ac9873b34c5c0eb36296e0fe726644fc9)`(StringPiece x)` | [Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/dequantize/attrs#structtensorflow_1_1ops_1_1_dequantize_1_1_attrs) |\n\n| ### Structs ||\n|---------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::Dequantize::Attrs](/versions/r2.0/api_docs/cc/struct/tensorflow/ops/dequantize/attrs) | Optional attribute setters for [Dequantize](/versions/r2.0/api_docs/cc/class/tensorflow/ops/dequantize#classtensorflow_1_1ops_1_1_dequantize). |\n\nPublic attributes\n-----------------\n\n### operation\n\n```text\nOperation operation\n``` \n\n### output\n\n```text\n::tensorflow::Output output\n``` \n\nPublic functions\n----------------\n\n### Dequantize\n\n```gdscript\n Dequantize(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input,\n ::tensorflow::Input min_range,\n ::tensorflow::Input max_range\n)\n``` \n\n### Dequantize\n\n```gdscript\n Dequantize(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input,\n ::tensorflow::Input min_range,\n ::tensorflow::Input max_range,\n const Dequantize::Attrs & attrs\n)\n``` \n\n### node\n\n```gdscript\n::tensorflow::Node * node() const \n``` \n\n### operator::tensorflow::Input\n\n```gdscript\n operator::tensorflow::Input() const \n``` \n\n### operator::tensorflow::Output\n\n```gdscript\n operator::tensorflow::Output() const \n``` \n\nPublic static functions\n-----------------------\n\n### Mode\n\n```text\nAttrs Mode(\n StringPiece x\n)\n```"]]
