Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
#include <nn_ops.h> Calcola i gradienti della convoluzione in profondità rispetto all'input.
Riepilogo
Argomenti:
- scope: un oggetto Scope
- input_sizes: un vettore intero che rappresenta la forma di
input , in base a data_format . Ad esempio, se data_format è "NHWC", input è un tensore 4-D [batch, height, width, channels] . - filter: 4-D con forma
[filter_height, filter_width, in_channels, depthwise_multiplier] . - out_backprop: 4-D con forma basata su
data_format . Ad esempio, se data_format è 'NHWC', la forma out_backprop è [batch, out_height, out_width, out_channels] . I gradienti rappresentano l'output della convoluzione. - passi: il passo della finestra scorrevole per ogni dimensione dell'input della convoluzione.
- riempimento: il tipo di algoritmo di riempimento da utilizzare.
Attributi facoltativi (vedi Attrs ):
- data_format: specifica il formato dei dati di input e output. Con il formato predefinito "NHWC", i dati vengono memorizzati nell'ordine di: [lotto, altezza, larghezza, canali]. In alternativa, il formato potrebbe essere "NCHW", l'ordine di archiviazione dei dati di: [batch, canali, altezza, larghezza].
- dilatazioni: tensore 1-D di lunghezza 4. Il fattore di dilatazione per ciascuna dimensione di
input . Se impostato su k > 1, ci saranno k-1 celle saltate tra ciascun elemento filtro su quella dimensione. L'ordine delle dimensioni è determinato dal valore di data_format , vedi sopra per i dettagli. Le dilatazioni delle dimensioni del lotto e della profondità devono essere pari a 1.
Resi:
-
Output : 4-D con forma secondo data_format . Ad esempio, se data_format è 'NHWC', la forma di output è [batch, in_height, in_width, in_channels] . Gradiente rispetto all'input della convoluzione.
Costruttori e distruttori |
|---|
DepthwiseConv2dNativeBackpropInput (const :: tensorflow::Scope & scope, :: tensorflow::Input input_sizes, :: tensorflow::Input filter, :: tensorflow::Input out_backprop, const gtl::ArraySlice< int > & strides, StringPiece padding)
|
DepthwiseConv2dNativeBackpropInput (const :: tensorflow::Scope & scope, :: tensorflow::Input input_sizes, :: tensorflow::Input filter, :: tensorflow::Input out_backprop, const gtl::ArraySlice< int > & strides, StringPiece padding, const DepthwiseConv2dNativeBackpropInput::Attrs & attrs)
|
Attributi pubblici
Funzioni pubbliche
Funzioni pubbliche statiche
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 2025-07-27 UTC.
[null,null,["Ultimo aggiornamento 2025-07-27 UTC."],[],[],null,["# tensorflow::ops::DepthwiseConv2dNativeBackpropInput Class Reference\n\ntensorflow::ops::DepthwiseConv2dNativeBackpropInput\n===================================================\n\n`#include \u003cnn_ops.h\u003e`\n\nComputes the gradients of depthwise 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 shape of `input`, based on `data_format`. For example, if `data_format` is 'NHWC' then `input` is a 4-D `[batch, height, width, channels]` tensor.\n- filter: 4-D with shape `[filter_height, filter_width, in_channels, depthwise_multiplier]`.\n- out_backprop: 4-D with shape based on `data_format`. For example, if `data_format` is 'NHWC' then out_backprop shape is `[batch, out_height, out_width, out_channels]`. Gradients w.r.t. the output of the convolution.\n- strides: The stride of the sliding window for each dimension of the input of the convolution.\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/depthwise-conv2d-native-backprop-input/attrs#structtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1_1_attrs)):\n\n- data_format: Specify the data format of the input and output data. With the default format \"NHWC\", the data is stored in the order of: \\[batch, height, width, channels\\]. Alternatively, the format could be \"NCHW\", the data storage order of: \\[batch, channels, height, width\\].\n- dilations: 1-D tensor of length 4. 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): 4-D with shape according to `data_format`. For example, if `data_format` is 'NHWC', output shape is `[batch, in_height, in_width, in_channels]`. Gradient w.r.t. the input of the convolution.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [DepthwiseConv2dNativeBackpropInput](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1a44860b426baf7a003c44728e835f9d05)`(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| [DepthwiseConv2dNativeBackpropInput](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1a014c3bb2ee403a82ec24f10992c7b580)`(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 `[DepthwiseConv2dNativeBackpropInput::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native-backprop-input/attrs#structtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|--------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1a66a4628fc7014482be2512ecff5a7f06) | [Operation](/versions/r2.3/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1a024ccdda3b9ee57913c71eb5dae1929c) | `::`[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_depthwise_conv2d_native_backprop_input_1a6e062166cae2aa251281f02dcec6154c)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1a4d40006ebcb3defcaf1f2e6e469516d9)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1af4f0b912eeeefe1eecf1c33eb20dd4b4)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|---------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [DataFormat](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1a3120c51e47ec70855e85f50c57743e34)`(StringPiece x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native-backprop-input/attrs#structtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1_1_attrs) |\n| [Dilations](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1a94c81fcd8b2ef27c98cec5ec75a8819b)`(const gtl::ArraySlice\u003c int \u003e & x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native-backprop-input/attrs#structtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1_1_attrs) |\n| [ExplicitPaddings](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1abc58e411afeb3fc0f3bdae0dafef12bc)`(const gtl::ArraySlice\u003c int \u003e & x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native-backprop-input/attrs#structtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input_1_1_attrs) |\n\n| ### Structs ||\n|-------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::DepthwiseConv2dNativeBackpropInput::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native-backprop-input/attrs) | Optional attribute setters for [DepthwiseConv2dNativeBackpropInput](/versions/r2.3/api_docs/cc/class/tensorflow/ops/depthwise-conv2d-native-backprop-input#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_backprop_input). |\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### DepthwiseConv2dNativeBackpropInput\n\n```gdscript\n DepthwiseConv2dNativeBackpropInput(\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### DepthwiseConv2dNativeBackpropInput\n\n```gdscript\n DepthwiseConv2dNativeBackpropInput(\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 DepthwiseConv2dNativeBackpropInput::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``` \n\n### ExplicitPaddings\n\n```gdscript\nAttrs ExplicitPaddings(\n const gtl::ArraySlice\u003c int \u003e & x\n)\n```"]]
