OpenCV453
静的公開メンバ関数 | 公開変数類 | 全メンバ一覧
cv::dnn::NormalizeBBoxLayer クラス
Deep Neural Network module » Partial List of Implemented Layers

$ L_p $ - normalization layer. [詳解]

#include <all_layers.hpp>

cv::dnn::Layerを継承しています。

静的公開メンバ関数

static Ptr< NormalizeBBoxLayer > create (const LayerParams &params)
 
- 基底クラス cv::Algorithm に属する継承静的公開メンバ関数
template<typename _Tp >
static Ptr< _Tp > read (const FileNode &fn)
 Reads algorithm from the file node [詳解]
 
template<typename _Tp >
static Ptr< _Tp > load (const String &filename, const String &objname=String())
 Loads algorithm from the file [詳解]
 
template<typename _Tp >
static Ptr< _Tp > loadFromString (const String &strModel, const String &objname=String())
 Loads algorithm from a String [詳解]
 

公開変数類

float pnorm
 
float epsilon
 
CV_DEPRECATED_EXTERNAL bool acrossSpatial
 
- 基底クラス cv::dnn::Layer に属する継承公開変数類
CV_PROP_RW std::vector< Mat > blobs
 List of learned parameters must be stored here to allow read them by using Net::getParam().
 
CV_PROP String name
 Name of the layer instance, can be used for logging or other internal purposes.
 
CV_PROP String type
 Type name which was used for creating layer by layer factory.
 
CV_PROP int preferableTarget
 prefer target for layer forwarding
 

その他の継承メンバ

- 基底クラス cv::dnn::Layer に属する継承公開メンバ関数
virtual CV_DEPRECATED_EXTERNAL void finalize (const std::vector< Mat * > &input, std::vector< Mat > &output)
 Computes and sets internal parameters according to inputs, outputs and blobs. [詳解]
 
virtual CV_WRAP void finalize (InputArrayOfArrays inputs, OutputArrayOfArrays outputs)
 Computes and sets internal parameters according to inputs, outputs and blobs. [詳解]
 
virtual CV_DEPRECATED_EXTERNAL void forward (std::vector< Mat * > &input, std::vector< Mat > &output, std::vector< Mat > &internals)
 Given the input blobs, computes the output blobs. [詳解]
 
virtual void forward (InputArrayOfArrays inputs, OutputArrayOfArrays outputs, OutputArrayOfArrays internals)
 Given the input blobs, computes the output blobs. [詳解]
 
void forward_fallback (InputArrayOfArrays inputs, OutputArrayOfArrays outputs, OutputArrayOfArrays internals)
 Given the input blobs, computes the output blobs. [詳解]
 
CV_DEPRECATED_EXTERNAL void finalize (const std::vector< Mat > &inputs, CV_OUT std::vector< Mat > &outputs)
 これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。 [詳解]
 
CV_DEPRECATED std::vector< Mat > finalize (const std::vector< Mat > &inputs)
 これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。 [詳解]
 
CV_DEPRECATED CV_WRAP void run (const std::vector< Mat > &inputs, CV_OUT std::vector< Mat > &outputs, CV_IN_OUT std::vector< Mat > &internals)
 Allocates layer and computes output. [詳解]
 
virtual int inputNameToIndex (String inputName)
 Returns index of input blob into the input array. [詳解]
 
virtual CV_WRAP int outputNameToIndex (const String &outputName)
 Returns index of output blob in output array. [詳解]
 
virtual bool supportBackend (int backendId)
 Ask layer if it support specific backend for doing computations. [詳解]
 
virtual Ptr< BackendNode > initHalide (const std::vector< Ptr< BackendWrapper > > &inputs)
 Returns Halide backend node. [詳解]
 
virtual Ptr< BackendNode > initInfEngine (const std::vector< Ptr< BackendWrapper > > &inputs)
 
virtual Ptr< BackendNode > initNgraph (const std::vector< Ptr< BackendWrapper > > &inputs, const std::vector< Ptr< BackendNode > > &nodes)
 
virtual Ptr< BackendNode > initVkCom (const std::vector< Ptr< BackendWrapper > > &inputs)
 
virtual Ptr< BackendNode > initCUDA (void *context, const std::vector< Ptr< BackendWrapper > > &inputs, const std::vector< Ptr< BackendWrapper > > &outputs)
 Returns a CUDA backend node [詳解]
 
virtual void applyHalideScheduler (Ptr< BackendNode > &node, const std::vector< Mat * > &inputs, const std::vector< Mat > &outputs, int targetId) const
 Automatic Halide scheduling based on layer hyper-parameters. [詳解]
 
virtual Ptr< BackendNode > tryAttach (const Ptr< BackendNode > &node)
 Implement layers fusing. [詳解]
 
virtual bool setActivation (const Ptr< ActivationLayer > &layer)
 Tries to attach to the layer the subsequent activation layer, i.e. do the layer fusion in a partial case. [詳解]
 
virtual bool tryFuse (Ptr< Layer > &top)
 Try to fuse current layer with a next one [詳解]
 
virtual void getScaleShift (Mat &scale, Mat &shift) const
 Returns parameters of layers with channel-wise multiplication and addition. [詳解]
 
virtual void unsetAttached ()
 "Deattaches" all the layers, attached to particular layer.
 
virtual bool getMemoryShapes (const std::vector< MatShape > &inputs, const int requiredOutputs, std::vector< MatShape > &outputs, std::vector< MatShape > &internals) const
 
virtual int64 getFLOPS (const std::vector< MatShape > &inputs, const std::vector< MatShape > &outputs) const
 
virtual bool updateMemoryShapes (const std::vector< MatShape > &inputs)
 
 Layer (const LayerParams &params)
 Initializes only name, type and blobs fields.
 
void setParamsFrom (const LayerParams &params)
 Initializes only name, type and blobs fields.
 
- 基底クラス cv::Algorithm に属する継承公開メンバ関数
virtual CV_WRAP void clear ()
 Clears the algorithm state [詳解]
 
virtual void write (FileStorage &fs) const
 Stores algorithm parameters in a file storage [詳解]
 
CV_WRAP void write (const Ptr< FileStorage > &fs, const String &name=String()) const
 simplified API for language bindings これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。
 
virtual CV_WRAP void read (const FileNode &fn)
 Reads algorithm parameters from a file storage [詳解]
 
virtual CV_WRAP bool empty () const
 Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read [詳解]
 
virtual CV_WRAP void save (const String &filename) const
 
virtual CV_WRAP String getDefaultName () const
 
- 基底クラス cv::Algorithm に属する継承限定公開メンバ関数
void writeFormat (FileStorage &fs) const
 

詳解

$ L_p $ - normalization layer.

引数
pNormalization factor. The most common p = 1 for $ L_1 $ - normalization or p = 2 for $ L_2 $ - normalization or a custom one.
epsParameter $ \epsilon $ to prevent a division by zero.
across_spatialIf true, normalize an input across all non-batch dimensions. Otherwise normalize an every channel separately.

Across spatial:

\[ norm = \sqrt[p]{\epsilon + \sum_{x, y, c} |src(x, y, c)|^p } \\ dst(x, y, c) = \frac{ src(x, y, c) }{norm} \]

Channel wise normalization:

\[ norm(c) = \sqrt[p]{\epsilon + \sum_{x, y} |src(x, y, c)|^p } \\ dst(x, y, c) = \frac{ src(x, y, c) }{norm(c)} \]

Where x, y - spatial coordinates, c - channel.

An every sample in the batch is normalized separately. Optionally, output is scaled by the trained parameters.

このクラス詳解は次のファイルから抽出されました:
構築: doxygen 1.9.2