Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
#include <nn_ops.h> Girişe göre derinlemesine evrişimin gradyanlarını hesaplar.
Özet
Argümanlar:
- kapsam: Bir Kapsam nesnesi
- girdi_boyutları:
data_format dayalı olarak input şeklini temsil eden bir tamsayı vektörü. Örneğin, data_format 'NHWC' ise input 4 boyutlu bir [batch, height, width, channels] tensörüdür. - filtre: 4-D şekilli
[filter_height, filter_width, in_channels, depthwise_multiplier] . - out_backprop:
data_format dayalı şekle sahip 4 boyutlu. Örneğin, data_format 'NHWC' ise out_backprop şekli [batch, out_height, out_width, out_channels] olur. Degradeler evrişimin çıktısına göredir. - adımlar: Evrişim girişinin her boyutu için kayan pencerenin adımı.
- padding: Kullanılacak dolgu algoritmasının türü.
İsteğe bağlı özellikler (bkz. Attrs ):
- data_format: Giriş ve çıkış verilerinin veri formatını belirtin. Varsayılan format "NHWC" ile veriler şu sırayla saklanır: [toplu iş, yükseklik, genişlik, kanallar]. Alternatif olarak format, veri depolama sırası olan "NCHW" olabilir: [toplu iş, kanallar, yükseklik, genişlik].
- genişlemeler: 1-D uzunluk tensörü 4.
input her boyutu için genişleme faktörü. k > 1 olarak ayarlanırsa, o boyuttaki her filtre elemanı arasında k-1 atlanan hücre olacaktır. Boyut sırası data_format değerine göre belirlenir; ayrıntılar için yukarıya bakın. Parti ve derinlik boyutlarındaki genişlemeler 1 olmalıdır.
İade:
-
Output : data_format göre şekilli 4-D. Örneğin, data_format 'NHWC' ise çıktı şekli şöyle olur: [batch, in_height, in_width, in_channels] . Evrişimin girişine göre gradyan.
Yapıcılar ve Yıkıcılar |
|---|
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)
|
Genel özellikler
Kamu işlevleri
Genel statik işlevler
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: 2025-07-27 UTC.
[null,null,["Son güncelleme tarihi: 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/r2.2/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/r2.2/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/r2.2/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/r2.2/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.2/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` input_sizes, ::`[tensorflow::Input](/versions/r2.2/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` filter, ::`[tensorflow::Input](/versions/r2.2/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/r2.2/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r2.2/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` input_sizes, ::`[tensorflow::Input](/versions/r2.2/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` filter, ::`[tensorflow::Input](/versions/r2.2/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/r2.2/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/r2.2/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/r2.2/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/r2.2/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/r2.2/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/r2.2/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native-backprop-input/attrs) | Optional attribute setters for [DepthwiseConv2dNativeBackpropInput](/versions/r2.2/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```"]]
