Conozca lo último en aprendizaje automático, IA generativa y más en el
Simposio WiML 2023.
Organiza tus páginas con colecciones
Guarda y categoriza el contenido según tus preferencias.
#include <nn_ops.h>
Calcula los gradientes de convolución 3-D con respecto a la entrada.
Resumen
Argumentos:
- alcance: un objeto de alcance
- input_sizes: Un vector entero que representa la forma del tensor de
input
, donde input
es un tensor 5-D [batch, depth, rows, cols, in_channels]
. - filtro: Forma
[depth, rows, cols, in_channels, out_channels]
. in_channels
debe coincidir entre la input
y el filter
. - out_backprop: señal de backprop de forma
[batch, out_depth, out_rows, out_cols, out_channels]
. - zancadas: tensor 1-D de longitud 5. Zancada de la ventana deslizante para cada dimensión de
input
. Debe tener strides[0] = strides[4] = 1
. - padding: el tipo de algoritmo de relleno que se utilizará.
Atributos opcionales (consulte Attrs
):
- data_format: El formato de datos de los datos de entrada y salida. Con el formato predeterminado "NDHWC", los datos se almacenan en el orden de: [batch, in_depth, in_height, in_width, in_channels]. Alternativamente, el formato podría ser "NCDHW", el orden de almacenamiento de datos es: [batch, in_channels, in_depth, in_height, in_width].
- dilataciones: tensor 1-D de longitud 5. El factor de dilatación para cada dimensión de
input
. Si se establece en k> 1, habrá k-1 celdas omitidas entre cada elemento de filtro en esa dimensión. El orden de las dimensiones está determinado por el valor de data_format
; consulte más arriba para obtener más detalles. Las dilataciones en las dimensiones del lote y profundidad deben ser 1.
Devoluciones:
Constructores y Destructores |
---|
Conv3DBackpropInputV2 (const :: tensorflow::Scope & scope, :: tensorflow::Input input_sizes, :: tensorflow::Input filter, :: tensorflow::Input out_backprop, const gtl::ArraySlice< int > & strides, StringPiece padding)
|
Conv3DBackpropInputV2 (const :: tensorflow::Scope & scope, :: tensorflow::Input input_sizes, :: tensorflow::Input filter, :: tensorflow::Input out_backprop, const gtl::ArraySlice< int > & strides, StringPiece padding, const Conv3DBackpropInputV2::Attrs & attrs) |
Funciones estáticas públicas |
---|
DataFormat (StringPiece x) | |
Dilations (const gtl::ArraySlice< int > & x) | |
Atributos públicos
Funciones publicas
Funciones estáticas públicas
Salvo que se indique lo contrario, el contenido de esta página está sujeto a la licencia Atribución 4.0 de Creative Commons, y los ejemplos de código están sujetos a la licencia Apache 2.0. Para obtener más información, consulta las políticas del sitio de Google Developers. Java es una marca registrada de Oracle o sus afiliados.
Última actualización: 2020-06-29 (UTC)
[null,null,["Última actualización: 2020-06-29 (UTC)"],[],[],null,["# tensorflow::ops::Conv3DBackpropInputV2 Class Reference\n\ntensorflow::ops::Conv3DBackpropInputV2\n======================================\n\n`#include \u003cnn_ops.h\u003e`\n\nComputes the gradients of 3-D convolution with respect to the input.\n\nSummary\n-------\n\nArguments:\n\n- scope: A [Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- input_sizes: An integer vector representing the tensor shape of `input`, where `input` is a 5-D `[batch, depth, rows, cols, in_channels]` tensor.\n- filter: Shape `[depth, rows, cols, in_channels, out_channels]`. `in_channels` must match between `input` and `filter`.\n- out_backprop: Backprop signal of shape `[batch, out_depth, out_rows, out_cols, out_channels]`.\n- strides: 1-D tensor of length 5. The stride of the sliding window for each dimension of `input`. Must have `strides[0] = strides[4] = 1`.\n- padding: The type of padding algorithm to use.\n\n\u003cbr /\u003e\n\nOptional attributes (see [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/conv3-d-backprop-input-v2/attrs#structtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1_1_attrs)):\n\n- data_format: The data format of the input and output data. With the default format \"NDHWC\", the data is stored in the order of: \\[batch, in_depth, in_height, in_width, in_channels\\]. Alternatively, the format could be \"NCDHW\", the data storage order is: \\[batch, in_channels, in_depth, in_height, in_width\\].\n- dilations: 1-D tensor of length 5. The dilation factor for each dimension of `input`. If set to k \\\u003e 1, there will be k-1 skipped cells between each filter element on that dimension. The dimension order is determined by the value of `data_format`, see above for details. Dilations in the batch and depth dimensions must be 1.\n\n\u003cbr /\u003e\n\nReturns:\n\n- [Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): The output tensor.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [Conv3DBackpropInputV2](#classtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1aaae19e097fea9d7fc6f815e20faaccd6)`(const ::`[tensorflow::Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` input_sizes, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` filter, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` out_backprop, const gtl::ArraySlice\u003c int \u003e & strides, StringPiece padding)` ||\n| [Conv3DBackpropInputV2](#classtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1a5c69778ddcd70862d70f7d3630d179c3)`(const ::`[tensorflow::Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` input_sizes, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` filter, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` out_backprop, const gtl::ArraySlice\u003c int \u003e & strides, StringPiece padding, const `[Conv3DBackpropInputV2::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/conv3-d-backprop-input-v2/attrs#structtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|-------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1a67a6ca650c6870d418f1fdd658f3fa6b) | [Operation](/versions/r2.3/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1af0d983aaf022b911e25e9f0615b62c20) | `::`[tensorflow::Output](/versions/r2.3/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|-------------------------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1adb36b7921921ed6c8a2684a8df5cc0ae)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1a0c617c40ac75a3540b1280f1e02147ed)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1a8b8868a10a3fac1cb6623b75a7bd556d)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|-------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [DataFormat](#classtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1a5a0f9e531569a6645dc6eb72894476c5)`(StringPiece x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/conv3-d-backprop-input-v2/attrs#structtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1_1_attrs) |\n| [Dilations](#classtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1a7c96359abb43990fc21d1cf52f468a1b)`(const gtl::ArraySlice\u003c int \u003e & x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/conv3-d-backprop-input-v2/attrs#structtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2_1_1_attrs) |\n\n| ### Structs ||\n|-----------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::Conv3DBackpropInputV2::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/conv3-d-backprop-input-v2/attrs) | Optional attribute setters for [Conv3DBackpropInputV2](/versions/r2.3/api_docs/cc/class/tensorflow/ops/conv3-d-backprop-input-v2#classtensorflow_1_1ops_1_1_conv3_d_backprop_input_v2). |\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### Conv3DBackpropInputV2\n\n```gdscript\n Conv3DBackpropInputV2(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input_sizes,\n ::tensorflow::Input filter,\n ::tensorflow::Input out_backprop,\n const gtl::ArraySlice\u003c int \u003e & strides,\n StringPiece padding\n)\n``` \n\n### Conv3DBackpropInputV2\n\n```gdscript\n Conv3DBackpropInputV2(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input_sizes,\n ::tensorflow::Input filter,\n ::tensorflow::Input out_backprop,\n const gtl::ArraySlice\u003c int \u003e & strides,\n StringPiece padding,\n const Conv3DBackpropInputV2::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### DataFormat\n\n```text\nAttrs DataFormat(\n StringPiece x\n)\n``` \n\n### Dilations\n\n```gdscript\nAttrs Dilations(\n const gtl::ArraySlice\u003c int \u003e & x\n)\n```"]]