Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
tensor akışı:: işlem:: Dönüşüm3D
#include <nn_ops.h> 5 boyutlu input ve filter tensörleri verildiğinde 3 boyutlu bir evrişimi hesaplar.
Özet
Sinyal işlemede çapraz korelasyon, iki dalga biçiminin benzerliğinin, bunlardan birine uygulanan zaman gecikmesinin bir fonksiyonu olarak ölçüsüdür. Bu aynı zamanda kayan nokta çarpım veya kayan iç çarpım olarak da bilinir.
Conv3D'miz bir tür çapraz korelasyon uygular.
Argümanlar:
- kapsam: Bir Kapsam nesnesi
- giriş: Şekil
[batch, in_depth, in_height, in_width, in_channels] . - filtre: Şekil
[filter_depth, filter_height, filter_width, in_channels, out_channels] . in_channels input ve filter arasında eşleşmelidir. - adımlar: uzunluğun 1 boyutlu tensörü 5.
input her boyutu için kayan pencerenin adımı. strides[0] = strides[4] = 1 olmalıdır. - padding: Kullanılacak dolgu algoritmasının türü.
İsteğe bağlı özellikler (bkz. Attrs ):
- data_format: Giriş ve çıkış verilerinin veri formatı. Varsayılan "NDHWC" biçimiyle veriler şu sırayla saklanır: [toplu iş, derinlemesine, yükseklik, yükseklik, genişlik, kanallar içi]. Alternatif olarak format "NCDHW" olabilir ve veri depolama sırası şu şekildedir: [toplu iş, kanal içi, derinlik, yükseklik, genişlik].
- genişlemeler: 1-D uzunluk tensörü 5.
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:
Genel özellikler
Kamu işlevleri
düğüm
::tensorflow::Node * node() const
operator::tensorflow::Input() const
operatör::tensorflow::Çıktı
operator::tensorflow::Output() const
Genel statik işlevler
Attrs DataFormat(
StringPiece x
)
Dilatasyonlar
Attrs Dilations(
const gtl::ArraySlice< int > & x
)
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: 2025-07-26 UTC.
[null,null,["Son güncelleme tarihi: 2025-07-26 UTC."],[],[],null,["# tensorflow::ops::Conv3D Class Reference\n\ntensorflow::ops::Conv3D\n=======================\n\n`#include \u003cnn_ops.h\u003e`\n\nComputes a 3-D convolution given 5-D `input` and `filter` tensors.\n\nSummary\n-------\n\nIn signal processing, cross-correlation is a measure of similarity of two waveforms as a function of a time-lag applied to one of them. This is also known as a sliding dot product or sliding inner-product.\n\nOur [Conv3D](/versions/r1.15/api_docs/cc/class/tensorflow/ops/conv3-d#classtensorflow_1_1ops_1_1_conv3_d) implements a form of cross-correlation.\n\nArguments:\n\n- scope: A [Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- input: Shape `[batch, in_depth, in_height, in_width, in_channels]`.\n- filter: Shape `[filter_depth, filter_height, filter_width, in_channels, out_channels]`. `in_channels` must match between `input` and `filter`.\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/r1.15/api_docs/cc/struct/tensorflow/ops/conv3-d/attrs#structtensorflow_1_1ops_1_1_conv3_d_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/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output): The output tensor.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [Conv3D](#classtensorflow_1_1ops_1_1_conv3_d_1aef63039997c4f9586d2b8627e3cf5c5a)`(const ::`[tensorflow::Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` input, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` filter, const gtl::ArraySlice\u003c int \u003e & strides, StringPiece padding)` ||\n| [Conv3D](#classtensorflow_1_1ops_1_1_conv3_d_1abb396c1cb8bf48f57ad11862ac7406ad)`(const ::`[tensorflow::Scope](/versions/r1.15/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope)` & scope, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` input, ::`[tensorflow::Input](/versions/r1.15/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` filter, const gtl::ArraySlice\u003c int \u003e & strides, StringPiece padding, const `[Conv3D::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/conv3-d/attrs#structtensorflow_1_1ops_1_1_conv3_d_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|-------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_conv3_d_1a34a87b1c84b82ab0a1dec637ee277ced) | [Operation](/versions/r1.15/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_conv3_d_1a426b9a63272f1905184fdfd1b78ba33a) | `::`[tensorflow::Output](/versions/r1.15/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output) |\n\n| ### Public functions ||\n|-------------------------------------------------------------------------------------------------------------------|------------------------|\n| [node](#classtensorflow_1_1ops_1_1_conv3_d_1a33ab1a0f2fa69089a8f835175d1dc732)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_conv3_d_1a418b91ef5b6437901248965d572533e5)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_conv3_d_1abebfb46d5b9c472aebb4f25ad6d2eeb6)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|-------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------|\n| [DataFormat](#classtensorflow_1_1ops_1_1_conv3_d_1a148ca9c798353ee9073c60f57e45a41f)`(StringPiece x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/conv3-d/attrs#structtensorflow_1_1ops_1_1_conv3_d_1_1_attrs) |\n| [Dilations](#classtensorflow_1_1ops_1_1_conv3_d_1a90d138624ebc69f365e225d25ece6e2a)`(const gtl::ArraySlice\u003c int \u003e & x)` | [Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/conv3-d/attrs#structtensorflow_1_1ops_1_1_conv3_d_1_1_attrs) |\n\n| ### Structs ||\n|---------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::Conv3D::Attrs](/versions/r1.15/api_docs/cc/struct/tensorflow/ops/conv3-d/attrs) | Optional attribute setters for [Conv3D](/versions/r1.15/api_docs/cc/class/tensorflow/ops/conv3-d#classtensorflow_1_1ops_1_1_conv3_d). |\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### Conv3D\n\n```gdscript\n Conv3D(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input,\n ::tensorflow::Input filter,\n const gtl::ArraySlice\u003c int \u003e & strides,\n StringPiece padding\n)\n``` \n\n### Conv3D\n\n```gdscript\n Conv3D(\n const ::tensorflow::Scope & scope,\n ::tensorflow::Input input,\n ::tensorflow::Input filter,\n const gtl::ArraySlice\u003c int \u003e & strides,\n StringPiece padding,\n const Conv3D::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```"]]
