Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
#include <nn_ops.h> Girişe göre evrişimin gradyanlarını hesaplar.
Özet
Argümanlar:
- kapsam: Bir Kapsam nesnesi
- input_sizes:
input şeklini temsil eden bir tamsayı vektörü; burada input 4 boyutlu [batch, height, width, channels] tensörüdür. - filtre: 4-D şekilli
[filter_height, filter_width, in_channels, out_channels] . - out_backprop: Şekilli 4-D
[batch, out_height, out_width, out_channels] . Degradeler evrişimin çıktısına göredir. - adımlar: Evrişim girişinin her boyutu için kayan pencerenin adımı. Formatla belirtilen boyutla aynı sırada olmalıdır.
- padding: Kullanılacak dolgu algoritmasının türü.
İsteğe bağlı özellikler (bkz. Attrs ):
- açık_paddingler:
padding "EXPLICIT" ise, açık dolgu miktarlarının listesi. i. boyut için, boyuttan önce ve sonra eklenen dolgu miktarı sırasıyla explicit_paddings[2 * i] ve explicit_paddings[2 * i + 1] şeklindedir. padding "EXPLICIT" değilse, explicit_paddings boş olmalıdır. - data_format: Giriş ve çıkış verilerinin veri formatını belirtin. Varsayılan format "NHWC" ile veriler şu sırayla saklanır: [batch, in_height, in_width, in_channels]. Alternatif olarak format, veri depolama sırası olan "NCHW" olabilir: [batch, in_channels, in_height, in_width].
- 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 : Şekilli 4-D [batch, in_height, in_width, in_channels] . Evrişimin girişine göre gradyan.
Yapıcılar ve Yıkıcılar |
|---|
Conv2DBackpropInput (const :: tensorflow::Scope & scope, :: tensorflow::Input input_sizes, :: tensorflow::Input filter, :: tensorflow::Input out_backprop, const gtl::ArraySlice< int > & strides, StringPiece padding)
|
Conv2DBackpropInput (const :: tensorflow::Scope & scope, :: tensorflow::Input input_sizes, :: tensorflow::Input filter, :: tensorflow::Input out_backprop, const gtl::ArraySlice< int > & strides, StringPiece padding, const Conv2DBackpropInput::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::Conv2DBackpropInput Class Reference\n\ntensorflow::ops::Conv2DBackpropInput\n====================================\n\n`#include \u003cnn_ops.h\u003e`\n\nComputes the gradients of 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`, where `input` is a 4-D `[batch, height, width, channels]` tensor.\n- filter: 4-D with shape `[filter_height, filter_width, in_channels, out_channels]`.\n- out_backprop: 4-D with shape `[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. Must be in the same order as the dimension specified with format.\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/conv2-d-backprop-input/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_input_1_1_attrs)):\n\n- explicit_paddings: If `padding` is `\"EXPLICIT\"`, the list of explicit padding amounts. For the ith dimension, the amount of padding inserted before and after the dimension is `explicit_paddings[2 * i]` and `explicit_paddings[2 * i + 1]`, respectively. If `padding` is not `\"EXPLICIT\"`, `explicit_paddings` must be empty.\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, in_height, in_width, in_channels\\]. Alternatively, the format could be \"NCHW\", the data storage order of: \\[batch, in_channels, in_height, in_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 `[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| [Conv2DBackpropInput](#classtensorflow_1_1ops_1_1_conv2_d_backprop_input_1aa5357992b64dbb43b51d35c084d442d8)`(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| [Conv2DBackpropInput](#classtensorflow_1_1ops_1_1_conv2_d_backprop_input_1a01da97aaaf681a4f6f45d3bda57f0f82)`(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 `[Conv2DBackpropInput::Attrs](/versions/r2.2/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-input/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_input_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|----------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_conv2_d_backprop_input_1aebb0f66b81bb602fa8600e2e32f621b2) | [Operation](/versions/r2.2/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_conv2_d_backprop_input_1a53bf3bf2eb2af62764981f62c794fbe2) | `::`[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_conv2_d_backprop_input_1acf62af3e404315cfe9622e3d1295033b)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_conv2_d_backprop_input_1a94315c7d6148fb6451deb58f91955405)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_conv2_d_backprop_input_1a1bced60701935dddacef1af9398879df)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|-----------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------|\n| [DataFormat](#classtensorflow_1_1ops_1_1_conv2_d_backprop_input_1ac762988224740afda86e2a852ef11774)`(StringPiece x)` | [Attrs](/versions/r2.2/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-input/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_input_1_1_attrs) |\n| [Dilations](#classtensorflow_1_1ops_1_1_conv2_d_backprop_input_1a01b3b905a6bba3d7c7e61238d45109e4)`(const gtl::ArraySlice\u003c int \u003e & x)` | [Attrs](/versions/r2.2/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-input/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_input_1_1_attrs) |\n| [ExplicitPaddings](#classtensorflow_1_1ops_1_1_conv2_d_backprop_input_1a4f19fe8f8ae4c3b237038489ba58a721)`(const gtl::ArraySlice\u003c int \u003e & x)` | [Attrs](/versions/r2.2/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-input/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_input_1_1_attrs) |\n| [UseCudnnOnGpu](#classtensorflow_1_1ops_1_1_conv2_d_backprop_input_1a6df425d872077ec66d9eb2e2b42f767b)`(bool x)` | [Attrs](/versions/r2.2/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-input/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_input_1_1_attrs) |\n\n| ### Structs ||\n|------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::Conv2DBackpropInput::Attrs](/versions/r2.2/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-input/attrs) | Optional attribute setters for [Conv2DBackpropInput](/versions/r2.2/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-input#classtensorflow_1_1ops_1_1_conv2_d_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### Conv2DBackpropInput\n\n```gdscript\n Conv2DBackpropInput(\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### Conv2DBackpropInput\n\n```gdscript\n Conv2DBackpropInput(\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 Conv2DBackpropInput::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``` \n\n### UseCudnnOnGpu\n\n```text\nAttrs UseCudnnOnGpu(\n bool x\n)\n```"]]
