Koleksiyonlar ile düzeninizi koruyun
İçeriği tercihlerinize göre kaydedin ve kategorilere ayırın.
tensor akışı:: işlem:: DepthwiseConv2dNative
#include <nn_ops.h>
4 boyutlu input
ve filter
tensörleri verildiğinde 2 boyutlu derinlemesine evrişimi hesaplar.
Özet
Derinlik 1'in in_channels
evrişim filtrelerini içeren [batch, in_height, in_width, in_channels]
şeklinde bir giriş tensörü ve [filter_height, filter_width, in_channels, channel_multiplier]
şeklinde bir filtre / çekirdek tensörü verildiğinde, depthwise_conv2d
her giriş kanalına farklı bir filtre uygular (her biri için 1 kanaldan channel_multiplier
kanallarına genişler), ardından sonuçları birleştirir. Böylece çıktıda in_channels * channel_multiplier
kanalları bulunur.
for k in 0..in_channels-1
for q in 0..channel_multiplier-1
output[b, i, j, k * channel_multiplier + q] =
sum_{di, dj} input[b, strides[1] * i + di, strides[2] * j + dj, k] *
filter[di, dj, k, q]
strides[0] = strides[3] = 1
olmalıdır. Aynı yatay ve köşeli adımların en yaygın durumu için, strides = [1, stride, stride, 1]
.
Argümanlar:
- kapsam: Bir Kapsam nesnesi
- adımlar: 1 boyutlu uzunluk 4.
input
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:
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
)
Açık Dolgular
Attrs ExplicitPaddings(
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: 2025-07-27 UTC.
[null,null,["Son güncelleme tarihi: 2025-07-27 UTC."],[],[],null,["# tensorflow::ops::DepthwiseConv2dNative Class Reference\n\ntensorflow::ops::DepthwiseConv2dNative\n======================================\n\n`#include \u003cnn_ops.h\u003e`\n\nComputes a 2-D depthwise convolution given 4-D `input` and `filter` tensors.\n\nSummary\n-------\n\nGiven an input tensor of shape `[batch, in_height, in_width, in_channels]` and a filter / kernel tensor of shape `[filter_height, filter_width, in_channels, channel_multiplier]`, containing `in_channels` convolutional filters of depth 1, `depthwise_conv2d` applies a different filter to each input channel (expanding from 1 channel to `channel_multiplier` channels for each), then concatenates the results together. Thus, the output has `in_channels * channel_multiplier` channels.\n\n\n```scdoc\nfor k in 0..in_channels-1\n for q in 0..channel_multiplier-1\n output[b, i, j, k * channel_multiplier + q] =\n sum_{di, dj} input[b, strides[1] * i + di, strides[2] * j + dj, k] *\n filter[di, dj, k, q]\n```\n\n\u003cbr /\u003e\n\nMust have `strides[0] = strides[3] = 1`. For the most common case of the same horizontal and vertices strides, `strides = [1, stride, stride, 1]`.\n\nArguments:\n\n- scope: A [Scope](/versions/r2.3/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object\n- strides: 1-D of length 4. The stride of the sliding window for each dimension of `input`.\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/attrs#structtensorflow_1_1ops_1_1_depthwise_conv2d_native_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): The output tensor.\n\n\u003cbr /\u003e\n\n| ### Constructors and Destructors ||\n|---|---|\n| [DepthwiseConv2dNative](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_1a50c225536301350d0a2a4e15f11bb1e8)`(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, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` filter, const gtl::ArraySlice\u003c int \u003e & strides, StringPiece padding)` ||\n| [DepthwiseConv2dNative](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_1a1403cd12618eaad516b1e553b99a2dec)`(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, ::`[tensorflow::Input](/versions/r2.3/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input)` filter, const gtl::ArraySlice\u003c int \u003e & strides, StringPiece padding, const `[DepthwiseConv2dNative::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native/attrs#structtensorflow_1_1ops_1_1_depthwise_conv2d_native_1_1_attrs)` & attrs)` ||\n\n| ### Public attributes ||\n|-----------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|\n| [operation](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_1af4279f97302c2185f1577d3cee105837) | [Operation](/versions/r2.3/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation) |\n| [output](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_1a787a2254c323c4cc73067daa11e2b646) | `::`[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_1ab6d86ff41ea2b1ec8b84bd58bda5b4c7)`() const ` | `::tensorflow::Node *` |\n| [operator::tensorflow::Input](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_1ab08d7fc817e77e96f3d713f9c4536ccd)`() const ` | ` ` ` ` |\n| [operator::tensorflow::Output](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_1aaa32a9f3e246eae5adc3000f23eb8e88)`() const ` | ` ` ` ` |\n\n| ### Public static functions ||\n|------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [DataFormat](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_1a51fe0b98bda9604c4dcb4ce5156714df)`(StringPiece x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native/attrs#structtensorflow_1_1ops_1_1_depthwise_conv2d_native_1_1_attrs) |\n| [Dilations](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_1a36765465f25da5bb2ff97249302c8806)`(const gtl::ArraySlice\u003c int \u003e & x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native/attrs#structtensorflow_1_1ops_1_1_depthwise_conv2d_native_1_1_attrs) |\n| [ExplicitPaddings](#classtensorflow_1_1ops_1_1_depthwise_conv2d_native_1a73ae4e50791a90681f92a54719605f21)`(const gtl::ArraySlice\u003c int \u003e & x)` | [Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native/attrs#structtensorflow_1_1ops_1_1_depthwise_conv2d_native_1_1_attrs) |\n\n| ### Structs ||\n|---------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tensorflow::ops::DepthwiseConv2dNative::Attrs](/versions/r2.3/api_docs/cc/struct/tensorflow/ops/depthwise-conv2d-native/attrs) | Optional attribute setters for [DepthwiseConv2dNative](/versions/r2.3/api_docs/cc/class/tensorflow/ops/depthwise-conv2d-native#classtensorflow_1_1ops_1_1_depthwise_conv2d_native). |\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### DepthwiseConv2dNative\n\n```gdscript\n DepthwiseConv2dNative(\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### DepthwiseConv2dNative\n\n```gdscript\n DepthwiseConv2dNative(\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 DepthwiseConv2dNative::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```"]]