amass/PassengerStatistics
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add zlmediakit.

Browse Source
This commit is contained in:
luocai
2024-03-13 18:01:36 +08:00
parent f34bfbc22f
commit 80b76f410e
260 changed files with 98240 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

589
3rdparty/libopencv/include/opencv2/dnn/all_layers.hpp vendored Normal file
View File

@ -0,0 +1,589 @@
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of the copyright holders may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#ifndef OPENCV_DNN_DNN_ALL_LAYERS_HPP
#define OPENCV_DNN_DNN_ALL_LAYERS_HPP
#include <opencv2/dnn.hpp>
namespace cv {
namespace dnn {
CV__DNN_EXPERIMENTAL_NS_BEGIN
//! @addtogroup dnn
//! @{
/** @defgroup dnnLayerList Partial List of Implemented Layers
@{
This subsection of dnn module contains information about built-in layers and their descriptions.
Classes listed here, in fact, provides C++ API for creating instances of built-in layers.
In addition to this way of layers instantiation, there is a more common factory API (see @ref dnnLayerFactory), it allows to create layers dynamically (by name) and register new ones.
You can use both API, but factory API is less convenient for native C++ programming and basically designed for use inside importers (see @ref readNetFromCaffe(), @ref readNetFromTorch(), @ref readNetFromTensorflow()).
Built-in layers partially reproduce functionality of corresponding Caffe and Torch7 layers.
In partuclar, the following layers and Caffe importer were tested to reproduce <a href="http://caffe.berkeleyvision.org/tutorial/layers.html">Caffe</a> functionality:
- Convolution
- Deconvolution
- Pooling
- InnerProduct
- TanH, ReLU, Sigmoid, BNLL, Power, AbsVal
- Softmax
- Reshape, Flatten, Slice, Split
- LRN
- MVN
- Dropout (since it does nothing on forward pass -))
*/
class CV_EXPORTS BlankLayer : public Layer
{
public:
static Ptr<Layer> create(const LayerParams &params);
};
//! LSTM recurrent layer
class CV_EXPORTS LSTMLayer : public Layer
{
public:
/** Creates instance of LSTM layer */
static Ptr<LSTMLayer> create(const LayerParams& params);
/** @deprecated Use LayerParams::blobs instead.
@brief Set trained weights for LSTM layer.
LSTM behavior on each step is defined by current input, previous output, previous cell state and learned weights.
Let @f$x_t@f$ be current input, @f$h_t@f$ be current output, @f$c_t@f$ be current state.
Than current output and current cell state is computed as follows:
@f{eqnarray*}{
h_t &= o_t \odot tanh(c_t), \\
c_t &= f_t \odot c_{t-1} + i_t \odot g_t, \\
@f}
where @f$\odot@f$ is per-element multiply operation and @f$i_t, f_t, o_t, g_t@f$ is internal gates that are computed using learned wights.
Gates are computed as follows:
@f{eqnarray*}{
i_t &= sigmoid&(W_{xi} x_t + W_{hi} h_{t-1} + b_i), \\
f_t &= sigmoid&(W_{xf} x_t + W_{hf} h_{t-1} + b_f), \\
o_t &= sigmoid&(W_{xo} x_t + W_{ho} h_{t-1} + b_o), \\
g_t &= tanh &(W_{xg} x_t + W_{hg} h_{t-1} + b_g), \\
@f}
where @f$W_{x?}@f$, @f$W_{h?}@f$ and @f$b_{?}@f$ are learned weights represented as matrices:
@f$W_{x?} \in R^{N_h \times N_x}@f$, @f$W_{h?} \in R^{N_h \times N_h}@f$, @f$b_? \in R^{N_h}@f$.
For simplicity and performance purposes we use @f$ W_x = [W_{xi}; W_{xf}; W_{xo}, W_{xg}] @f$
(i.e. @f$W_x@f$ is vertical contacentaion of @f$ W_{x?} @f$), @f$ W_x \in R^{4N_h \times N_x} @f$.
The same for @f$ W_h = [W_{hi}; W_{hf}; W_{ho}, W_{hg}], W_h \in R^{4N_h \times N_h} @f$
and for @f$ b = [b_i; b_f, b_o, b_g]@f$, @f$b \in R^{4N_h} @f$.
@param Wh is matrix defining how previous output is transformed to internal gates (i.e. according to abovemtioned notation is @f$ W_h @f$)
@param Wx is matrix defining how current input is transformed to internal gates (i.e. according to abovemtioned notation is @f$ W_x @f$)
@param b is bias vector (i.e. according to abovemtioned notation is @f$ b @f$)
*/
CV_DEPRECATED virtual void setWeights(const Mat &Wh, const Mat &Wx, const Mat &b) = 0;
/** @brief Specifies shape of output blob which will be [[`T`], `N`] + @p outTailShape.
* @details If this parameter is empty or unset then @p outTailShape = [`Wh`.size(0)] will be used,
* where `Wh` is parameter from setWeights().
*/
virtual void setOutShape(const MatShape &outTailShape = MatShape()) = 0;
/** @deprecated Use flag `produce_cell_output` in LayerParams.
* @brief Specifies either interpret first dimension of input blob as timestamp dimenion either as sample.
*
* If flag is set to true then shape of input blob will be interpreted as [`T`, `N`, `[data dims]`] where `T` specifies number of timestamps, `N` is number of independent streams.
* In this case each forward() call will iterate through `T` timestamps and update layer's state `T` times.
*
* If flag is set to false then shape of input blob will be interpreted as [`N`, `[data dims]`].
* In this case each forward() call will make one iteration and produce one timestamp with shape [`N`, `[out dims]`].
*/
CV_DEPRECATED virtual void setUseTimstampsDim(bool use = true) = 0;
/** @deprecated Use flag `use_timestamp_dim` in LayerParams.
* @brief If this flag is set to true then layer will produce @f$ c_t @f$ as second output.
* @details Shape of the second output is the same as first output.
*/
CV_DEPRECATED virtual void setProduceCellOutput(bool produce = false) = 0;
/* In common case it use single input with @f$x_t@f$ values to compute output(s) @f$h_t@f$ (and @f$c_t@f$).
* @param input should contain packed values @f$x_t@f$
* @param output contains computed outputs: @f$h_t@f$ (and @f$c_t@f$ if setProduceCellOutput() flag was set to true).
*
* If setUseTimstampsDim() is set to true then @p input[0] should has at least two dimensions with the following shape: [`T`, `N`, `[data dims]`],
* where `T` specifies number of timestamps, `N` is number of independent streams (i.e. @f$ x_{t_0 + t}^{stream} @f$ is stored inside @p input[0][t, stream, ...]).
*
* If setUseTimstampsDim() is set to fase then @p input[0] should contain single timestamp, its shape should has form [`N`, `[data dims]`] with at least one dimension.
* (i.e. @f$ x_{t}^{stream} @f$ is stored inside @p input[0][stream, ...]).
*/
int inputNameToIndex(String inputName);
int outputNameToIndex(String outputName);
};
/** @brief Classical recurrent layer
Accepts two inputs @f$x_t@f$ and @f$h_{t-1}@f$ and compute two outputs @f$o_t@f$ and @f$h_t@f$.
- input: should contain packed input @f$x_t@f$.
- output: should contain output @f$o_t@f$ (and @f$h_t@f$ if setProduceHiddenOutput() is set to true).
input[0] should have shape [`T`, `N`, `data_dims`] where `T` and `N` is number of timestamps and number of independent samples of @f$x_t@f$ respectively.
output[0] will have shape [`T`, `N`, @f$N_o@f$], where @f$N_o@f$ is number of rows in @f$ W_{xo} @f$ matrix.
If setProduceHiddenOutput() is set to true then @p output[1] will contain a Mat with shape [`T`, `N`, @f$N_h@f$], where @f$N_h@f$ is number of rows in @f$ W_{hh} @f$ matrix.
*/
class CV_EXPORTS RNNLayer : public Layer
{
public:
/** Creates instance of RNNLayer */
static Ptr<RNNLayer> create(const LayerParams& params);
/** Setups learned weights.
Recurrent-layer behavior on each step is defined by current input @f$ x_t @f$, previous state @f$ h_t @f$ and learned weights as follows:
@f{eqnarray*}{
h_t &= tanh&(W_{hh} h_{t-1} + W_{xh} x_t + b_h), \\
o_t &= tanh&(W_{ho} h_t + b_o),
@f}
@param Wxh is @f$ W_{xh} @f$ matrix
@param bh is @f$ b_{h} @f$ vector
@param Whh is @f$ W_{hh} @f$ matrix
@param Who is @f$ W_{xo} @f$ matrix
@param bo is @f$ b_{o} @f$ vector
*/
virtual void setWeights(const Mat &Wxh, const Mat &bh, const Mat &Whh, const Mat &Who, const Mat &bo) = 0;
/** @brief If this flag is set to true then layer will produce @f$ h_t @f$ as second output.
* @details Shape of the second output is the same as first output.
*/
virtual void setProduceHiddenOutput(bool produce = false) = 0;
};
class CV_EXPORTS BaseConvolutionLayer : public Layer
{
public:
Size kernel, stride, pad, dilation, adjustPad;
String padMode;
int numOutput;
};
class CV_EXPORTS ConvolutionLayer : public BaseConvolutionLayer
{
public:
static Ptr<BaseConvolutionLayer> create(const LayerParams& params);
};
class CV_EXPORTS DeconvolutionLayer : public BaseConvolutionLayer
{
public:
static Ptr<BaseConvolutionLayer> create(const LayerParams& params);
};
class CV_EXPORTS LRNLayer : public Layer
{
public:
int type;
int size;
float alpha, beta, bias;
bool normBySize;
static Ptr<LRNLayer> create(const LayerParams& params);
};
class CV_EXPORTS PoolingLayer : public Layer
{
public:
int type;
Size kernel, stride, pad;
bool globalPooling;
bool computeMaxIdx;
String padMode;
bool ceilMode;
// If true for average pooling with padding, divide an every output region
// by a whole kernel area. Otherwise exclude zero padded values and divide
// by number of real values.
bool avePoolPaddedArea;
// ROIPooling parameters.
Size pooledSize;
float spatialScale;
// PSROIPooling parameters.
int psRoiOutChannels;
static Ptr<PoolingLayer> create(const LayerParams& params);
};
class CV_EXPORTS SoftmaxLayer : public Layer
{
public:
bool logSoftMax;
static Ptr<SoftmaxLayer> create(const LayerParams& params);
};
class CV_EXPORTS InnerProductLayer : public Layer
{
public:
int axis;
static Ptr<InnerProductLayer> create(const LayerParams& params);
};
class CV_EXPORTS MVNLayer : public Layer
{
public:
float eps;
bool normVariance, acrossChannels;
static Ptr<MVNLayer> create(const LayerParams& params);
};
/* Reshaping */
class CV_EXPORTS ReshapeLayer : public Layer
{
public:
MatShape newShapeDesc;
Range newShapeRange;
static Ptr<ReshapeLayer> create(const LayerParams& params);
};
class CV_EXPORTS FlattenLayer : public Layer
{
public:
static Ptr<FlattenLayer> create(const LayerParams &params);
};
class CV_EXPORTS ConcatLayer : public Layer
{
public:
int axis;
/**
* @brief Add zero padding in case of concatenation of blobs with different
* spatial sizes.
*
* Details: https://github.com/torch/nn/blob/master/doc/containers.md#depthconcat
*/
bool padding;
static Ptr<ConcatLayer> create(const LayerParams &params);
};
class CV_EXPORTS SplitLayer : public Layer
{
public:
int outputsCount; //!< Number of copies that will be produced (is ignored when negative).
static Ptr<SplitLayer> create(const LayerParams &params);
};
/**
* Slice layer has several modes:
* 1. Caffe mode
* @param[in] axis Axis of split operation
* @param[in] slice_point Array of split points
*
* Number of output blobs equals to number of split points plus one. The
* first blob is a slice on input from 0 to @p slice_point[0] - 1 by @p axis,
* the second output blob is a slice of input from @p slice_point[0] to
* @p slice_point[1] - 1 by @p axis and the last output blob is a slice of
* input from @p slice_point[-1] up to the end of @p axis size.
*
* 2. TensorFlow mode
* @param begin Vector of start indices
* @param size Vector of sizes
*
* More convenient numpy-like slice. One and only output blob
* is a slice `input[begin[0]:begin[0]+size[0], begin[1]:begin[1]+size[1], ...]`
*
* 3. Torch mode
* @param axis Axis of split operation
*
* Split input blob on the equal parts by @p axis.
*/
class CV_EXPORTS SliceLayer : public Layer
{
public:
/**
* @brief Vector of slice ranges.
*
* The first dimension equals number of output blobs.
* Inner vector has slice ranges for the first number of input dimensions.
*/
std::vector<std::vector<Range> > sliceRanges;
int axis;
static Ptr<SliceLayer> create(const LayerParams &params);
};
class CV_EXPORTS PermuteLayer : public Layer
{
public:
static Ptr<PermuteLayer> create(const LayerParams& params);
};
/**
* @brief Adds extra values for specific axes.
* @param paddings Vector of paddings in format
* @code
* [ pad_before, pad_after, // [0]th dimension
* pad_before, pad_after, // [1]st dimension
* ...
* pad_before, pad_after ] // [n]th dimension
* @endcode
* that represents number of padded values at every dimension
* starting from the first one. The rest of dimensions won't
* be padded.
* @param value Value to be padded. Defaults to zero.
* @param type Padding type: 'constant', 'reflect'
* @param input_dims Torch's parameter. If @p input_dims is not equal to the
* actual input dimensionality then the `[0]th` dimension
* is considered as a batch dimension and @p paddings are shifted
* to a one dimension. Defaults to `-1` that means padding
* corresponding to @p paddings.
*/
class CV_EXPORTS PaddingLayer : public Layer
{
public:
static Ptr<PaddingLayer> create(const LayerParams& params);
};
/* Activations */
class CV_EXPORTS ActivationLayer : public Layer
{
public:
virtual void forwardSlice(const float* src, float* dst, int len,
size_t outPlaneSize, int cn0, int cn1) const = 0;
};
class CV_EXPORTS ReLULayer : public ActivationLayer
{
public:
float negativeSlope;
static Ptr<ReLULayer> create(const LayerParams &params);
};
class CV_EXPORTS ReLU6Layer : public ActivationLayer
{
public:
float minValue, maxValue;
static Ptr<ReLU6Layer> create(const LayerParams &params);
};
class CV_EXPORTS ChannelsPReLULayer : public ActivationLayer
{
public:
static Ptr<Layer> create(const LayerParams& params);
};
class CV_EXPORTS ELULayer : public ActivationLayer
{
public:
static Ptr<ELULayer> create(const LayerParams &params);
};
class CV_EXPORTS TanHLayer : public ActivationLayer
{
public:
static Ptr<TanHLayer> create(const LayerParams &params);
};
class CV_EXPORTS SigmoidLayer : public ActivationLayer
{
public:
static Ptr<SigmoidLayer> create(const LayerParams &params);
};
class CV_EXPORTS BNLLLayer : public ActivationLayer
{
public:
static Ptr<BNLLLayer> create(const LayerParams &params);
};
class CV_EXPORTS AbsLayer : public ActivationLayer
{
public:
static Ptr<AbsLayer> create(const LayerParams &params);
};
class CV_EXPORTS PowerLayer : public ActivationLayer
{
public:
float power, scale, shift;
static Ptr<PowerLayer> create(const LayerParams &params);
};
/* Layers used in semantic segmentation */
class CV_EXPORTS CropLayer : public Layer
{
public:
int startAxis;
std::vector<int> offset;
static Ptr<CropLayer> create(const LayerParams &params);
};
class CV_EXPORTS EltwiseLayer : public Layer
{
public:
static Ptr<EltwiseLayer> create(const LayerParams &params);
};
class CV_EXPORTS BatchNormLayer : public Layer
{
public:
bool hasWeights, hasBias;
float epsilon;
static Ptr<BatchNormLayer> create(const LayerParams &params);
};
class CV_EXPORTS MaxUnpoolLayer : public Layer
{
public:
Size poolKernel;
Size poolPad;
Size poolStride;
static Ptr<MaxUnpoolLayer> create(const LayerParams &params);
};
class CV_EXPORTS ScaleLayer : public Layer
{
public:
bool hasBias;
int axis;
static Ptr<ScaleLayer> create(const LayerParams& params);
};
class CV_EXPORTS ShiftLayer : public Layer
{
public:
static Ptr<ShiftLayer> create(const LayerParams& params);
};
class CV_EXPORTS PriorBoxLayer : public Layer
{
public:
static Ptr<PriorBoxLayer> create(const LayerParams& params);
};
class CV_EXPORTS ReorgLayer : public Layer
{
public:
static Ptr<ReorgLayer> create(const LayerParams& params);
};
class CV_EXPORTS RegionLayer : public Layer
{
public:
static Ptr<RegionLayer> create(const LayerParams& params);
};
class CV_EXPORTS DetectionOutputLayer : public Layer
{
public:
static Ptr<DetectionOutputLayer> create(const LayerParams& params);
};
/**
* @brief \f$ L_p \f$ - normalization layer.
* @param p Normalization factor. The most common `p = 1` for \f$ L_1 \f$ -
* normalization or `p = 2` for \f$ L_2 \f$ - normalization or a custom one.
* @param eps Parameter \f$ \epsilon \f$ to prevent a division by zero.
* @param across_spatial If true, normalize an input across all non-batch dimensions.
* Otherwise normalize an every channel separately.
*
* Across spatial:
* @f[
* norm = \sqrt[p]{\epsilon + \sum_{x, y, c} |src(x, y, c)|^p } \\
* dst(x, y, c) = \frac{ src(x, y, c) }{norm}
* @f]
*
* Channel wise normalization:
* @f[
* norm(c) = \sqrt[p]{\epsilon + \sum_{x, y} |src(x, y, c)|^p } \\
* dst(x, y, c) = \frac{ src(x, y, c) }{norm(c)}
* @f]
*
* Where `x, y` - spatial cooridnates, `c` - channel.
*
* An every sample in the batch is normalized separately. Optionally,
* output is scaled by the trained parameters.
*/
class NormalizeBBoxLayer : public Layer
{
public:
float pnorm, epsilon;
bool acrossSpatial;
static Ptr<NormalizeBBoxLayer> create(const LayerParams& params);
};
/**
* @brief Resize input 4-dimensional blob by nearest neghbor strategy.
*
* Layer is used to support TensorFlow's resize_nearest_neighbor op.
*/
class CV_EXPORTS ResizeNearestNeighborLayer : public Layer
{
public:
static Ptr<ResizeNearestNeighborLayer> create(const LayerParams& params);
};
class CV_EXPORTS ProposalLayer : public Layer
{
public:
static Ptr<ProposalLayer> create(const LayerParams& params);
};
//! @}
//! @}
CV__DNN_EXPERIMENTAL_NS_END
}
}
#endif

152
3rdparty/libopencv/include/opencv2/dnn/dict.hpp vendored Normal file
View File

@ -0,0 +1,152 @@
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of the copyright holders may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#include <opencv2/core.hpp>
#include <map>
#include <ostream>
#include <opencv2/dnn/dnn.hpp>
#ifndef OPENCV_DNN_DNN_DICT_HPP
#define OPENCV_DNN_DNN_DICT_HPP
namespace cv {
namespace dnn {
CV__DNN_EXPERIMENTAL_NS_BEGIN
//! @addtogroup dnn
//! @{
/** @brief This struct stores the scalar value (or array) of one of the following type: double, cv::String or int64.
* @todo Maybe int64 is useless because double type exactly stores at least 2^52 integers.
*/
struct CV_EXPORTS_W DictValue
{
DictValue(const DictValue &r);
DictValue(int64 i = 0) : type(Param::INT), pi(new AutoBuffer<int64,1>) { (*pi)[0] = i; } //!< Constructs integer scalar
CV_WRAP DictValue(int i) : type(Param::INT), pi(new AutoBuffer<int64,1>) { (*pi)[0] = i; } //!< Constructs integer scalar
DictValue(unsigned p) : type(Param::INT), pi(new AutoBuffer<int64,1>) { (*pi)[0] = p; } //!< Constructs integer scalar
CV_WRAP DictValue(double p) : type(Param::REAL), pd(new AutoBuffer<double,1>) { (*pd)[0] = p; } //!< Constructs floating point scalar
CV_WRAP DictValue(const String &s) : type(Param::STRING), ps(new AutoBuffer<String,1>) { (*ps)[0] = s; } //!< Constructs string scalar
DictValue(const char *s) : type(Param::STRING), ps(new AutoBuffer<String,1>) { (*ps)[0] = s; } //!< @overload
template<typename TypeIter>
static DictValue arrayInt(TypeIter begin, int size); //!< Constructs integer array
template<typename TypeIter>
static DictValue arrayReal(TypeIter begin, int size); //!< Constructs floating point array
template<typename TypeIter>
static DictValue arrayString(TypeIter begin, int size); //!< Constructs array of strings
template<typename T>
T get(int idx = -1) const; //!< Tries to convert array element with specified index to requested type and returns its.
int size() const;
CV_WRAP bool isInt() const;
CV_WRAP bool isString() const;
CV_WRAP bool isReal() const;
CV_WRAP int getIntValue(int idx = -1) const;
CV_WRAP double getRealValue(int idx = -1) const;
CV_WRAP String getStringValue(int idx = -1) const;
DictValue &operator=(const DictValue &r);
friend std::ostream &operator<<(std::ostream &stream, const DictValue &dictv);
~DictValue();
private:
int type;
union
{
AutoBuffer<int64, 1> *pi;
AutoBuffer<double, 1> *pd;
AutoBuffer<String, 1> *ps;
void *pv;
};
DictValue(int _type, void *_p) : type(_type), pv(_p) {}
void release();
};
/** @brief This class implements name-value dictionary, values are instances of DictValue. */
class CV_EXPORTS Dict
{
typedef std::map<String, DictValue> _Dict;
_Dict dict;
public:
//! Checks a presence of the @p key in the dictionary.
bool has(const String &key) const;
//! If the @p key in the dictionary then returns pointer to its value, else returns NULL.
DictValue *ptr(const String &key);
/** @overload */
const DictValue *ptr(const String &key) const;
//! If the @p key in the dictionary then returns its value, else an error will be generated.
const DictValue &get(const String &key) const;
/** @overload */
template <typename T>
T get(const String &key) const;
//! If the @p key in the dictionary then returns its value, else returns @p defaultValue.
template <typename T>
T get(const String &key, const T &defaultValue) const;
//! Sets new @p value for the @p key, or adds new key-value pair into the dictionary.
template<typename T>
const T &set(const String &key, const T &value);
friend std::ostream &operator<<(std::ostream &stream, const Dict &dict);
};
//! @}
CV__DNN_EXPERIMENTAL_NS_END
}
}
#endif

794
3rdparty/libopencv/include/opencv2/dnn/dnn.hpp vendored Normal file
View File

@ -0,0 +1,794 @@
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of the copyright holders may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#ifndef OPENCV_DNN_DNN_HPP
#define OPENCV_DNN_DNN_HPP
#include <vector>
#include <opencv2/core.hpp>
#if !defined CV_DOXYGEN && !defined CV_DNN_DONT_ADD_EXPERIMENTAL_NS
#define CV__DNN_EXPERIMENTAL_NS_BEGIN namespace experimental_dnn_v4 {
#define CV__DNN_EXPERIMENTAL_NS_END }
namespace cv { namespace dnn { namespace experimental_dnn_v4 { } using namespace experimental_dnn_v4; }}
#else
#define CV__DNN_EXPERIMENTAL_NS_BEGIN
#define CV__DNN_EXPERIMENTAL_NS_END
#endif
#include <opencv2/dnn/dict.hpp>
namespace cv {
namespace dnn {
CV__DNN_EXPERIMENTAL_NS_BEGIN
//! @addtogroup dnn
//! @{
typedef std::vector<int> MatShape;
/**
* @brief Enum of computation backends supported by layers.
*/
enum Backend
{
DNN_BACKEND_DEFAULT,
DNN_BACKEND_HALIDE,
DNN_BACKEND_INFERENCE_ENGINE
};
/**
* @brief Enum of target devices for computations.
*/
enum Target
{
DNN_TARGET_CPU,
DNN_TARGET_OPENCL
};
/** @brief This class provides all data needed to initialize layer.
*
* It includes dictionary with scalar params (which can be readed by using Dict interface),
* blob params #blobs and optional meta information: #name and #type of layer instance.
*/
class CV_EXPORTS LayerParams : public Dict
{
public:
//TODO: Add ability to name blob params
std::vector<Mat> blobs; //!< List of learned parameters stored as blobs.
String name; //!< Name of the layer instance (optional, can be used internal purposes).
String type; //!< Type name which was used for creating layer by layer factory (optional).
};
/**
* @brief Derivatives of this class encapsulates functions of certain backends.
*/
class BackendNode
{
public:
BackendNode(int backendId);
virtual ~BackendNode(); //!< Virtual destructor to make polymorphism.
int backendId; //!< Backend identifier.
};
/**
* @brief Derivatives of this class wraps cv::Mat for different backends and targets.
*/
class BackendWrapper
{
public:
BackendWrapper(int backendId, int targetId);
/**
* @brief Wrap cv::Mat for specific backend and target.
* @param[in] targetId Target identifier.
* @param[in] m cv::Mat for wrapping.
*
* Make CPU->GPU data transfer if it's require for the target.
*/
BackendWrapper(int targetId, const cv::Mat& m);
/**
* @brief Make wrapper for reused cv::Mat.
* @param[in] base Wrapper of cv::Mat that will be reused.
* @param[in] shape Specific shape.
*
* Initialize wrapper from another one. It'll wrap the same host CPU
* memory and mustn't allocate memory on device(i.e. GPU). It might
* has different shape. Use in case of CPU memory reusing for reuse
* associented memory on device too.
*/
BackendWrapper(const Ptr<BackendWrapper>& base, const MatShape& shape);
virtual ~BackendWrapper(); //!< Virtual destructor to make polymorphism.
/**
* @brief Transfer data to CPU host memory.
*/
virtual void copyToHost() = 0;
/**
* @brief Indicate that an actual data is on CPU.
*/
virtual void setHostDirty() = 0;
int backendId; //!< Backend identifier.
int targetId; //!< Target identifier.
};
class CV_EXPORTS ActivationLayer;
class CV_EXPORTS BatchNormLayer;
class CV_EXPORTS ScaleLayer;
/** @brief This interface class allows to build new Layers - are building blocks of networks.
*
* Each class, derived from Layer, must implement allocate() methods to declare own outputs and forward() to compute outputs.
* Also before using the new layer into networks you must register your layer by using one of @ref dnnLayerFactory "LayerFactory" macros.
*/
class CV_EXPORTS_W Layer : public Algorithm
{
public:
//! List of learned parameters must be stored here to allow read them by using Net::getParam().
CV_PROP_RW std::vector<Mat> blobs;
/** @brief Computes and sets internal parameters according to inputs, outputs and blobs.
* @param[in] input vector of already allocated input blobs
* @param[out] output vector of already allocated output blobs
*
* If this method is called after network has allocated all memory for input and output blobs
* and before inferencing.
*/
virtual void finalize(const std::vector<Mat*> &input, std::vector<Mat> &output);
/** @brief Given the @p input blobs, computes the output @p blobs.
* @param[in] input the input blobs.
* @param[out] output allocated output blobs, which will store results of the computation.
* @param[out] internals allocated internal blobs
*/
virtual void forward(std::vector<Mat*> &input, std::vector<Mat> &output, std::vector<Mat> &internals) = 0;
/** @brief Given the @p input blobs, computes the output @p blobs.
* @param[in] inputs the input blobs.
* @param[out] outputs allocated output blobs, which will store results of the computation.
* @param[out] internals allocated internal blobs
*/
virtual void forward(InputArrayOfArrays inputs, OutputArrayOfArrays outputs, OutputArrayOfArrays internals) = 0;
/** @brief Given the @p input blobs, computes the output @p blobs.
* @param[in] inputs the input blobs.
* @param[out] outputs allocated output blobs, which will store results of the computation.
* @param[out] internals allocated internal blobs
*/
void forward_fallback(InputArrayOfArrays inputs, OutputArrayOfArrays outputs, OutputArrayOfArrays internals);
/** @brief @overload */
CV_WRAP void finalize(const std::vector<Mat> &inputs, CV_OUT std::vector<Mat> &outputs);
/** @brief @overload */
CV_WRAP std::vector<Mat> finalize(const std::vector<Mat> &inputs);
/** @brief Allocates layer and computes output. */
CV_WRAP void run(const std::vector<Mat> &inputs, CV_OUT std::vector<Mat> &outputs,
CV_IN_OUT std::vector<Mat> &internals);
/** @brief Returns index of input blob into the input array.
* @param inputName label of input blob
*
* Each layer input and output can be labeled to easily identify them using "%<layer_name%>[.output_name]" notation.
* This method maps label of input blob to its index into input vector.
*/
virtual int inputNameToIndex(String inputName);
/** @brief Returns index of output blob in output array.
* @see inputNameToIndex()
*/
virtual int outputNameToIndex(String outputName);
/**
* @brief Ask layer if it support specific backend for doing computations.
* @param[in] backendId computation backend identifier.
* @see Backend
*/
virtual bool supportBackend(int backendId);
/**
* @brief Returns Halide backend node.
* @param[in] inputs Input Halide buffers.
* @see BackendNode, BackendWrapper
*
* Input buffers should be exactly the same that will be used in forward invocations.
* Despite we can use Halide::ImageParam based on input shape only,
* it helps prevent some memory management issues (if something wrong,
* Halide tests will be failed).
*/
virtual Ptr<BackendNode> initHalide(const std::vector<Ptr<BackendWrapper> > &inputs);
virtual Ptr<BackendNode> initInfEngine(const std::vector<Ptr<BackendWrapper> > &inputs);
/**
* @brief Automatic Halide scheduling based on layer hyper-parameters.
* @param[in] node Backend node with Halide functions.
* @param[in] inputs Blobs that will be used in forward invocations.
* @param[in] outputs Blobs that will be used in forward invocations.
* @param[in] targetId Target identifier
* @see BackendNode, Target
*
* Layer don't use own Halide::Func members because we can have applied
* layers fusing. In this way the fused function should be scheduled.
*/
virtual void applyHalideScheduler(Ptr<BackendNode>& node,
const std::vector<Mat*> &inputs,
const std::vector<Mat> &outputs,
int targetId) const;
/**
* @brief Implement layers fusing.
* @param[in] node Backend node of bottom layer.
* @see BackendNode
*
* Actual for graph-based backends. If layer attached successfully,
* returns non-empty cv::Ptr to node of the same backend.
* Fuse only over the last function.
*/
virtual Ptr<BackendNode> tryAttach(const Ptr<BackendNode>& node);
/**
* @brief Tries to attach to the layer the subsequent activation layer, i.e. do the layer fusion in a partial case.
* @param[in] layer The subsequent activation layer.
*
* Returns true if the activation layer has been attached successfully.
*/
virtual bool setActivation(const Ptr<ActivationLayer>& layer);
/**
* @brief Try to fuse current layer with a next one
* @param[in] top Next layer to be fused.
* @returns True if fusion was performed.
*/
virtual bool tryFuse(Ptr<Layer>& top);
/**
* @brief Returns parameters of layers with channel-wise multiplication and addition.
* @param[out] scale Channel-wise multipliers. Total number of values should
* be equal to number of channels.
* @param[out] shift Channel-wise offsets. Total number of values should
* be equal to number of channels.
*
* Some layers can fuse their transformations with further layers.
* In example, convolution + batch normalization. This way base layer
* use weights from layer after it. Fused layer is skipped.
* By default, @p scale and @p shift are empty that means layer has no
* element-wise multiplications or additions.
*/
virtual void getScaleShift(Mat& scale, Mat& shift) const;
/**
* @brief "Deattaches" all the layers, attached to particular layer.
*/
virtual void unsetAttached();
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 {(void)inputs; (void)outputs; return 0;}
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
Layer();
explicit Layer(const LayerParams &params); //!< Initializes only #name, #type and #blobs fields.
void setParamsFrom(const LayerParams &params); //!< Initializes only #name, #type and #blobs fields.
virtual ~Layer();
};
/** @brief This class allows to create and manipulate comprehensive artificial neural networks.
*
* Neural network is presented as directed acyclic graph (DAG), where vertices are Layer instances,
* and edges specify relationships between layers inputs and outputs.
*
* Each network layer has unique integer id and unique string name inside its network.
* LayerId can store either layer name or layer id.
*
* This class supports reference counting of its instances, i. e. copies point to the same instance.
*/
class CV_EXPORTS_W_SIMPLE Net
{
public:
CV_WRAP Net(); //!< Default constructor.
CV_WRAP ~Net(); //!< Destructor frees the net only if there aren't references to the net anymore.
/** Returns true if there are no layers in the network. */
CV_WRAP bool empty() const;
/** @brief Adds new layer to the net.
* @param name unique name of the adding layer.
* @param type typename of the adding layer (type must be registered in LayerRegister).
* @param params parameters which will be used to initialize the creating layer.
* @returns unique identifier of created layer, or -1 if a failure will happen.
*/
int addLayer(const String &name, const String &type, LayerParams &params);
/** @brief Adds new layer and connects its first input to the first output of previously added layer.
* @see addLayer()
*/
int addLayerToPrev(const String &name, const String &type, LayerParams &params);
/** @brief Converts string name of the layer to the integer identifier.
* @returns id of the layer, or -1 if the layer wasn't found.
*/
CV_WRAP int getLayerId(const String &layer);
CV_WRAP std::vector<String> getLayerNames() const;
/** @brief Container for strings and integers. */
typedef DictValue LayerId;
/** @brief Returns pointer to layer with specified id or name which the network use. */
CV_WRAP Ptr<Layer> getLayer(LayerId layerId);
/** @brief Returns pointers to input layers of specific layer. */
std::vector<Ptr<Layer> > getLayerInputs(LayerId layerId); // FIXIT: CV_WRAP
/** @brief Delete layer for the network (not implemented yet) */
CV_WRAP void deleteLayer(LayerId layer);
/** @brief Connects output of the first layer to input of the second layer.
* @param outPin descriptor of the first layer output.
* @param inpPin descriptor of the second layer input.
*
* Descriptors have the following template <DFN>&lt;layer_name&gt;[.input_number]</DFN>:
* - the first part of the template <DFN>layer_name</DFN> is sting name of the added layer.
* If this part is empty then the network input pseudo layer will be used;
* - the second optional part of the template <DFN>input_number</DFN>
* is either number of the layer input, either label one.
* If this part is omitted then the first layer input will be used.
*
* @see setNetInputs(), Layer::inputNameToIndex(), Layer::outputNameToIndex()
*/
CV_WRAP void connect(String outPin, String inpPin);
/** @brief Connects #@p outNum output of the first layer to #@p inNum input of the second layer.
* @param outLayerId identifier of the first layer
* @param inpLayerId identifier of the second layer
* @param outNum number of the first layer output
* @param inpNum number of the second layer input
*/
void connect(int outLayerId, int outNum, int inpLayerId, int inpNum);
/** @brief Sets outputs names of the network input pseudo layer.
*
* Each net always has special own the network input pseudo layer with id=0.
* This layer stores the user blobs only and don't make any computations.
* In fact, this layer provides the only way to pass user data into the network.
* As any other layer, this layer can label its outputs and this function provides an easy way to do this.
*/
CV_WRAP void setInputsNames(const std::vector<String> &inputBlobNames);
/** @brief Runs forward pass to compute output of layer with name @p outputName.
* @param outputName name for layer which output is needed to get
* @return blob for first output of specified layer.
* @details By default runs forward pass for the whole network.
*/
CV_WRAP Mat forward(const String& outputName = String());
/** @brief Runs forward pass to compute output of layer with name @p outputName.
* @param outputBlobs contains all output blobs for specified layer.
* @param outputName name for layer which output is needed to get
* @details If @p outputName is empty, runs forward pass for the whole network.
*/
CV_WRAP void forward(OutputArrayOfArrays outputBlobs, const String& outputName = String());
/** @brief Runs forward pass to compute outputs of layers listed in @p outBlobNames.
* @param outputBlobs contains blobs for first outputs of specified layers.
* @param outBlobNames names for layers which outputs are needed to get
*/
CV_WRAP void forward(OutputArrayOfArrays outputBlobs,
const std::vector<String>& outBlobNames);
/** @brief Runs forward pass to compute outputs of layers listed in @p outBlobNames.
* @param outputBlobs contains all output blobs for each layer specified in @p outBlobNames.
* @param outBlobNames names for layers which outputs are needed to get
*/
CV_WRAP_AS(forwardAndRetrieve) void forward(CV_OUT std::vector<std::vector<Mat> >& outputBlobs,
const std::vector<String>& outBlobNames);
/**
* @brief Compile Halide layers.
* @param[in] scheduler Path to YAML file with scheduling directives.
* @see setPreferableBackend
*
* Schedule layers that support Halide backend. Then compile them for
* specific target. For layers that not represented in scheduling file
* or if no manual scheduling used at all, automatic scheduling will be applied.
*/
CV_WRAP void setHalideScheduler(const String& scheduler);
/**
* @brief Ask network to use specific computation backend where it supported.
* @param[in] backendId backend identifier.
* @see Backend
*/
CV_WRAP void setPreferableBackend(int backendId);
/**
* @brief Ask network to make computations on specific target device.
* @param[in] targetId target identifier.
* @see Target
*/
CV_WRAP void setPreferableTarget(int targetId);
/** @brief Sets the new value for the layer output blob
* @param name descriptor of the updating layer output blob.
* @param blob new blob.
* @see connect(String, String) to know format of the descriptor.
* @note If updating blob is not empty then @p blob must have the same shape,
* because network reshaping is not implemented yet.
*/
CV_WRAP void setInput(InputArray blob, const String& name = "");
/** @brief Sets the new value for the learned param of the layer.
* @param layer name or id of the layer.
* @param numParam index of the layer parameter in the Layer::blobs array.
* @param blob the new value.
* @see Layer::blobs
* @note If shape of the new blob differs from the previous shape,
* then the following forward pass may fail.
*/
CV_WRAP void setParam(LayerId layer, int numParam, const Mat &blob);
/** @brief Returns parameter blob of the layer.
* @param layer name or id of the layer.
* @param numParam index of the layer parameter in the Layer::blobs array.
* @see Layer::blobs
*/
CV_WRAP Mat getParam(LayerId layer, int numParam = 0);
/** @brief Returns indexes of layers with unconnected outputs.
*/
CV_WRAP std::vector<int> getUnconnectedOutLayers() const;
/** @brief Returns input and output shapes for all layers in loaded model;
* preliminary inferencing isn't necessary.
* @param netInputShapes shapes for all input blobs in net input layer.
* @param layersIds output parameter for layer IDs.
* @param inLayersShapes output parameter for input layers shapes;
* order is the same as in layersIds
* @param outLayersShapes output parameter for output layers shapes;
* order is the same as in layersIds
*/
CV_WRAP void getLayersShapes(const std::vector<MatShape>& netInputShapes,
CV_OUT std::vector<int>& layersIds,
CV_OUT std::vector<std::vector<MatShape> >& inLayersShapes,
CV_OUT std::vector<std::vector<MatShape> >& outLayersShapes) const;
/** @overload */
CV_WRAP void getLayersShapes(const MatShape& netInputShape,
CV_OUT std::vector<int>& layersIds,
CV_OUT std::vector<std::vector<MatShape> >& inLayersShapes,
CV_OUT std::vector<std::vector<MatShape> >& outLayersShapes) const;
/** @brief Returns input and output shapes for layer with specified
* id in loaded model; preliminary inferencing isn't necessary.
* @param netInputShape shape input blob in net input layer.
* @param layerId id for layer.
* @param inLayerShapes output parameter for input layers shapes;
* order is the same as in layersIds
* @param outLayerShapes output parameter for output layers shapes;
* order is the same as in layersIds
*/
void getLayerShapes(const MatShape& netInputShape,
const int layerId,
CV_OUT std::vector<MatShape>& inLayerShapes,
CV_OUT std::vector<MatShape>& outLayerShapes) const; // FIXIT: CV_WRAP
/** @overload */
void getLayerShapes(const std::vector<MatShape>& netInputShapes,
const int layerId,
CV_OUT std::vector<MatShape>& inLayerShapes,
CV_OUT std::vector<MatShape>& outLayerShapes) const; // FIXIT: CV_WRAP
/** @brief Computes FLOP for whole loaded model with specified input shapes.
* @param netInputShapes vector of shapes for all net inputs.
* @returns computed FLOP.
*/
CV_WRAP int64 getFLOPS(const std::vector<MatShape>& netInputShapes) const;
/** @overload */
CV_WRAP int64 getFLOPS(const MatShape& netInputShape) const;
/** @overload */
CV_WRAP int64 getFLOPS(const int layerId,
const std::vector<MatShape>& netInputShapes) const;
/** @overload */
CV_WRAP int64 getFLOPS(const int layerId,
const MatShape& netInputShape) const;
/** @brief Returns list of types for layer used in model.
* @param layersTypes output parameter for returning types.
*/
CV_WRAP void getLayerTypes(CV_OUT std::vector<String>& layersTypes) const;
/** @brief Returns count of layers of specified type.
* @param layerType type.
* @returns count of layers
*/
CV_WRAP int getLayersCount(const String& layerType) const;
/** @brief Computes bytes number which are requered to store
* all weights and intermediate blobs for model.
* @param netInputShapes vector of shapes for all net inputs.
* @param weights output parameter to store resulting bytes for weights.
* @param blobs output parameter to store resulting bytes for intermediate blobs.
*/
void getMemoryConsumption(const std::vector<MatShape>& netInputShapes,
CV_OUT size_t& weights, CV_OUT size_t& blobs) const; // FIXIT: CV_WRAP
/** @overload */
CV_WRAP void getMemoryConsumption(const MatShape& netInputShape,
CV_OUT size_t& weights, CV_OUT size_t& blobs) const;
/** @overload */
CV_WRAP void getMemoryConsumption(const int layerId,
const std::vector<MatShape>& netInputShapes,
CV_OUT size_t& weights, CV_OUT size_t& blobs) const;
/** @overload */
CV_WRAP void getMemoryConsumption(const int layerId,
const MatShape& netInputShape,
CV_OUT size_t& weights, CV_OUT size_t& blobs) const;
/** @brief Computes bytes number which are requered to store
* all weights and intermediate blobs for each layer.
* @param netInputShapes vector of shapes for all net inputs.
* @param layerIds output vector to save layer IDs.
* @param weights output parameter to store resulting bytes for weights.
* @param blobs output parameter to store resulting bytes for intermediate blobs.
*/
void getMemoryConsumption(const std::vector<MatShape>& netInputShapes,
CV_OUT std::vector<int>& layerIds,
CV_OUT std::vector<size_t>& weights,
CV_OUT std::vector<size_t>& blobs) const; // FIXIT: CV_WRAP
/** @overload */
void getMemoryConsumption(const MatShape& netInputShape,
CV_OUT std::vector<int>& layerIds,
CV_OUT std::vector<size_t>& weights,
CV_OUT std::vector<size_t>& blobs) const; // FIXIT: CV_WRAP
/** @brief Enables or disables layer fusion in the network.
* @param fusion true to enable the fusion, false to disable. The fusion is enabled by default.
*/
CV_WRAP void enableFusion(bool fusion);
/** @brief Returns overall time for inference and timings (in ticks) for layers.
* Indexes in returned vector correspond to layers ids. Some layers can be fused with others,
* in this case zero ticks count will be return for that skipped layers.
* @param timings vector for tick timings for all layers.
* @return overall ticks for model inference.
*/
CV_WRAP int64 getPerfProfile(CV_OUT std::vector<double>& timings);
private:
struct Impl;
Ptr<Impl> impl;
};
/** @brief Reads a network model stored in <a href="https://pjreddie.com/darknet/">Darknet</a> model files.
* @param cfgFile path to the .cfg file with text description of the network architecture.
* @param darknetModel path to the .weights file with learned network.
* @returns Network object that ready to do forward, throw an exception in failure cases.
* @returns Net object.
*/
CV_EXPORTS_W Net readNetFromDarknet(const String &cfgFile, const String &darknetModel = String());
/** @brief Reads a network model stored in <a href="http://caffe.berkeleyvision.org">Caffe</a> framework's format.
* @param prototxt path to the .prototxt file with text description of the network architecture.
* @param caffeModel path to the .caffemodel file with learned network.
* @returns Net object.
*/
CV_EXPORTS_W Net readNetFromCaffe(const String &prototxt, const String &caffeModel = String());
/** @brief Reads a network model stored in Caffe model in memory.
* @details This is an overloaded member function, provided for convenience.
* It differs from the above function only in what argument(s) it accepts.
* @param bufferProto buffer containing the content of the .prototxt file
* @param lenProto length of bufferProto
* @param bufferModel buffer containing the content of the .caffemodel file
* @param lenModel length of bufferModel
* @returns Net object.
*/
CV_EXPORTS Net readNetFromCaffe(const char *bufferProto, size_t lenProto,
const char *bufferModel = NULL, size_t lenModel = 0);
/** @brief Reads a network model stored in <a href="https://www.tensorflow.org/">TensorFlow</a> framework's format.
* @param model path to the .pb file with binary protobuf description of the network architecture
* @param config path to the .pbtxt file that contains text graph definition in protobuf format.
* Resulting Net object is built by text graph using weights from a binary one that
* let us make it more flexible.
* @returns Net object.
*/
CV_EXPORTS_W Net readNetFromTensorflow(const String &model, const String &config = String());
/** @brief Reads a network model stored in <a href="https://www.tensorflow.org/">TensorFlow</a> framework's format.
* @details This is an overloaded member function, provided for convenience.
* It differs from the above function only in what argument(s) it accepts.
* @param bufferModel buffer containing the content of the pb file
* @param lenModel length of bufferModel
* @param bufferConfig buffer containing the content of the pbtxt file
* @param lenConfig length of bufferConfig
*/
CV_EXPORTS Net readNetFromTensorflow(const char *bufferModel, size_t lenModel,
const char *bufferConfig = NULL, size_t lenConfig = 0);
/**
* @brief Reads a network model stored in <a href="http://torch.ch">Torch7</a> framework's format.
* @param model path to the file, dumped from Torch by using torch.save() function.
* @param isBinary specifies whether the network was serialized in ascii mode or binary.
* @returns Net object.
*
* @note Ascii mode of Torch serializer is more preferable, because binary mode extensively use `long` type of C language,
* which has various bit-length on different systems.
*
* The loading file must contain serialized <a href="https://github.com/torch/nn/blob/master/doc/module.md">nn.Module</a> object
* with importing network. Try to eliminate a custom objects from serialazing data to avoid importing errors.
*
* List of supported layers (i.e. object instances derived from Torch nn.Module class):
* - nn.Sequential
* - nn.Parallel
* - nn.Concat
* - nn.Linear
* - nn.SpatialConvolution
* - nn.SpatialMaxPooling, nn.SpatialAveragePooling
* - nn.ReLU, nn.TanH, nn.Sigmoid
* - nn.Reshape
* - nn.SoftMax, nn.LogSoftMax
*
* Also some equivalents of these classes from cunn, cudnn, and fbcunn may be successfully imported.
*/
CV_EXPORTS_W Net readNetFromTorch(const String &model, bool isBinary = true);
/** @brief Loads blob which was serialized as torch.Tensor object of Torch7 framework.
* @warning This function has the same limitations as readNetFromTorch().
*/
CV_EXPORTS_W Mat readTorchBlob(const String &filename, bool isBinary = true);
/** @brief Creates 4-dimensional blob from image. Optionally resizes and crops @p image from center,
* subtract @p mean values, scales values by @p scalefactor, swap Blue and Red channels.
* @param image input image (with 1-, 3- or 4-channels).
* @param size spatial size for output image
* @param mean scalar with mean values which are subtracted from channels. Values are intended
* to be in (mean-R, mean-G, mean-B) order if @p image has BGR ordering and @p swapRB is true.
* @param scalefactor multiplier for @p image values.
* @param swapRB flag which indicates that swap first and last channels
* in 3-channel image is necessary.
* @param crop flag which indicates whether image will be cropped after resize or not
* @details if @p crop is true, input image is resized so one side after resize is equal to corresponding
* dimension in @p size and another one is equal or larger. Then, crop from the center is performed.
* If @p crop is false, direct resize without cropping and preserving aspect ratio is performed.
* @returns 4-dimansional Mat with NCHW dimensions order.
*/
CV_EXPORTS_W Mat blobFromImage(InputArray image, double scalefactor=1.0, const Size& size = Size(),
const Scalar& mean = Scalar(), bool swapRB=true, bool crop=true);
/** @brief Creates 4-dimensional blob from image.
* @details This is an overloaded member function, provided for convenience.
* It differs from the above function only in what argument(s) it accepts.
*/
CV_EXPORTS void blobFromImage(InputArray image, OutputArray blob, double scalefactor=1.0,
const Size& size = Size(), const Scalar& mean = Scalar(),
bool swapRB=true, bool crop=true);
/** @brief Creates 4-dimensional blob from series of images. Optionally resizes and
* crops @p images from center, subtract @p mean values, scales values by @p scalefactor,
* swap Blue and Red channels.
* @param images input images (all with 1-, 3- or 4-channels).
* @param size spatial size for output image
* @param mean scalar with mean values which are subtracted from channels. Values are intended
* to be in (mean-R, mean-G, mean-B) order if @p image has BGR ordering and @p swapRB is true.
* @param scalefactor multiplier for @p images values.
* @param swapRB flag which indicates that swap first and last channels
* in 3-channel image is necessary.
* @param crop flag which indicates whether image will be cropped after resize or not
* @details if @p crop is true, input image is resized so one side after resize is equal to corresponding
* dimension in @p size and another one is equal or larger. Then, crop from the center is performed.
* If @p crop is false, direct resize without cropping and preserving aspect ratio is performed.
* @returns 4-dimansional Mat with NCHW dimensions order.
*/
CV_EXPORTS_W Mat blobFromImages(InputArrayOfArrays images, double scalefactor=1.0,
Size size = Size(), const Scalar& mean = Scalar(), bool swapRB=true, bool crop=true);
/** @brief Creates 4-dimensional blob from series of images.
* @details This is an overloaded member function, provided for convenience.
* It differs from the above function only in what argument(s) it accepts.
*/
CV_EXPORTS void blobFromImages(InputArrayOfArrays images, OutputArray blob,
double scalefactor=1.0, Size size = Size(),
const Scalar& mean = Scalar(), bool swapRB=true, bool crop=true);
/** @brief Parse a 4D blob and output the images it contains as 2D arrays through a simpler data structure
* (std::vector<cv::Mat>).
* @param[in] blob_ 4 dimensional array (images, channels, height, width) in floating point precision (CV_32F) from
* which you would like to extract the images.
* @param[out] images_ array of 2D Mat containing the images extracted from the blob in floating point precision
* (CV_32F). They are non normalized neither mean added. The number of returned images equals the first dimension
* of the blob (batch size). Every image has a number of channels equals to the second dimension of the blob (depth).
*/
CV_EXPORTS_W void imagesFromBlob(const cv::Mat& blob_, OutputArrayOfArrays images_);
/** @brief Convert all weights of Caffe network to half precision floating point.
* @param src Path to origin model from Caffe framework contains single
* precision floating point weights (usually has `.caffemodel` extension).
* @param dst Path to destination model with updated weights.
* @param layersTypes Set of layers types which parameters will be converted.
* By default, converts only Convolutional and Fully-Connected layers'
* weights.
*
* @note Shrinked model has no origin float32 weights so it can't be used
* in origin Caffe framework anymore. However the structure of data
* is taken from NVidia's Caffe fork: https://github.com/NVIDIA/caffe.
* So the resulting model may be used there.
*/
CV_EXPORTS_W void shrinkCaffeModel(const String& src, const String& dst,
const std::vector<String>& layersTypes = std::vector<String>());
/** @brief Performs non maximum suppression given boxes and corresponding scores.
* @param bboxes a set of bounding boxes to apply NMS.
* @param scores a set of corresponding confidences.
* @param score_threshold a threshold used to filter boxes by score.
* @param nms_threshold a threshold used in non maximum suppression.
* @param indices the kept indices of bboxes after NMS.
* @param eta a coefficient in adaptive threshold formula: \f$nms\_threshold_{i+1}=eta\cdot nms\_threshold_i\f$.
* @param top_k if `>0`, keep at most @p top_k picked indices.
*/
CV_EXPORTS_W void NMSBoxes(const std::vector<Rect>& bboxes, const std::vector<float>& scores,
const float score_threshold, const float nms_threshold,
CV_OUT std::vector<int>& indices,
const float eta = 1.f, const int top_k = 0);
//! @}
CV__DNN_EXPERIMENTAL_NS_END
}
}
#include <opencv2/dnn/layer.hpp>
#include <opencv2/dnn/dnn.inl.hpp>
#endif /* OPENCV_DNN_DNN_HPP */

373
3rdparty/libopencv/include/opencv2/dnn/dnn.inl.hpp vendored Normal file
View File

@ -0,0 +1,373 @@
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of the copyright holders may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#ifndef OPENCV_DNN_DNN_INL_HPP
#define OPENCV_DNN_DNN_INL_HPP
#include <opencv2/dnn.hpp>
namespace cv {
namespace dnn {
CV__DNN_EXPERIMENTAL_NS_BEGIN
template<typename TypeIter>
DictValue DictValue::arrayInt(TypeIter begin, int size)
{
DictValue res(Param::INT, new AutoBuffer<int64, 1>(size));
for (int j = 0; j < size; begin++, j++)
(*res.pi)[j] = *begin;
return res;
}
template<typename TypeIter>
DictValue DictValue::arrayReal(TypeIter begin, int size)
{
DictValue res(Param::REAL, new AutoBuffer<double, 1>(size));
for (int j = 0; j < size; begin++, j++)
(*res.pd)[j] = *begin;
return res;
}
template<typename TypeIter>
DictValue DictValue::arrayString(TypeIter begin, int size)
{
DictValue res(Param::STRING, new AutoBuffer<String, 1>(size));
for (int j = 0; j < size; begin++, j++)
(*res.ps)[j] = *begin;
return res;
}
template<>
inline DictValue DictValue::get<DictValue>(int idx) const
{
CV_Assert(idx == -1);
return *this;
}
template<>
inline int64 DictValue::get<int64>(int idx) const
{
CV_Assert((idx == -1 && size() == 1) || (idx >= 0 && idx < size()));
idx = (idx == -1) ? 0 : idx;
if (type == Param::INT)
{
return (*pi)[idx];
}
else if (type == Param::REAL)
{
double doubleValue = (*pd)[idx];
double fracpart, intpart;
fracpart = std::modf(doubleValue, &intpart);
CV_Assert(fracpart == 0.0);
return (int64)doubleValue;
}
else
{
CV_Assert(isInt() || isReal());
return 0;
}
}
template<>
inline int DictValue::get<int>(int idx) const
{
return (int)get<int64>(idx);
}
inline int DictValue::getIntValue(int idx) const
{
return (int)get<int64>(idx);
}
template<>
inline unsigned DictValue::get<unsigned>(int idx) const
{
return (unsigned)get<int64>(idx);
}
template<>
inline bool DictValue::get<bool>(int idx) const
{
return (get<int64>(idx) != 0);
}
template<>
inline double DictValue::get<double>(int idx) const
{
CV_Assert((idx == -1 && size() == 1) || (idx >= 0 && idx < size()));
idx = (idx == -1) ? 0 : idx;
if (type == Param::REAL)
{
return (*pd)[idx];
}
else if (type == Param::INT)
{
return (double)(*pi)[idx];
}
else
{
CV_Assert(isReal() || isInt());
return 0;
}
}
inline double DictValue::getRealValue(int idx) const
{
return get<double>(idx);
}
template<>
inline float DictValue::get<float>(int idx) const
{
return (float)get<double>(idx);
}
template<>
inline String DictValue::get<String>(int idx) const
{
CV_Assert(isString());
CV_Assert((idx == -1 && ps->size() == 1) || (idx >= 0 && idx < (int)ps->size()));
return (*ps)[(idx == -1) ? 0 : idx];
}
inline String DictValue::getStringValue(int idx) const
{
return get<String>(idx);
}
inline void DictValue::release()
{
switch (type)
{
case Param::INT:
delete pi;
break;
case Param::STRING:
delete ps;
break;
case Param::REAL:
delete pd;
break;
}
}
inline DictValue::~DictValue()
{
release();
}
inline DictValue & DictValue::operator=(const DictValue &r)
{
if (&r == this)
return *this;
if (r.type == Param::INT)
{
AutoBuffer<int64, 1> *tmp = new AutoBuffer<int64, 1>(*r.pi);
release();
pi = tmp;
}
else if (r.type == Param::STRING)
{
AutoBuffer<String, 1> *tmp = new AutoBuffer<String, 1>(*r.ps);
release();
ps = tmp;
}
else if (r.type == Param::REAL)
{
AutoBuffer<double, 1> *tmp = new AutoBuffer<double, 1>(*r.pd);
release();
pd = tmp;
}
type = r.type;
return *this;
}
inline DictValue::DictValue(const DictValue &r)
{
type = r.type;
if (r.type == Param::INT)
pi = new AutoBuffer<int64, 1>(*r.pi);
else if (r.type == Param::STRING)
ps = new AutoBuffer<String, 1>(*r.ps);
else if (r.type == Param::REAL)
pd = new AutoBuffer<double, 1>(*r.pd);
}
inline bool DictValue::isString() const
{
return (type == Param::STRING);
}
inline bool DictValue::isInt() const
{
return (type == Param::INT);
}
inline bool DictValue::isReal() const
{
return (type == Param::REAL || type == Param::INT);
}
inline int DictValue::size() const
{
switch (type)
{
case Param::INT:
return (int)pi->size();
break;
case Param::STRING:
return (int)ps->size();
break;
case Param::REAL:
return (int)pd->size();
break;
default:
CV_Error(Error::StsInternal, "");
return -1;
}
}
inline std::ostream &operator<<(std::ostream &stream, const DictValue &dictv)
{
int i;
if (dictv.isInt())
{
for (i = 0; i < dictv.size() - 1; i++)
stream << dictv.get<int64>(i) << ", ";
stream << dictv.get<int64>(i);
}
else if (dictv.isReal())
{
for (i = 0; i < dictv.size() - 1; i++)
stream << dictv.get<double>(i) << ", ";
stream << dictv.get<double>(i);
}
else if (dictv.isString())
{
for (i = 0; i < dictv.size() - 1; i++)
stream << "\"" << dictv.get<String>(i) << "\", ";
stream << dictv.get<String>(i);
}
return stream;
}
/////////////////////////////////////////////////////////////////
inline bool Dict::has(const String &key) const
{
return dict.count(key) != 0;
}
inline DictValue *Dict::ptr(const String &key)
{
_Dict::iterator i = dict.find(key);
return (i == dict.end()) ? NULL : &i->second;
}
inline const DictValue *Dict::ptr(const String &key) const
{
_Dict::const_iterator i = dict.find(key);
return (i == dict.end()) ? NULL : &i->second;
}
inline const DictValue &Dict::get(const String &key) const
{
_Dict::const_iterator i = dict.find(key);
if (i == dict.end())
CV_Error(Error::StsObjectNotFound, "Required argument \"" + key + "\" not found into dictionary");
return i->second;
}
template <typename T>
inline T Dict::get(const String &key) const
{
return this->get(key).get<T>();
}
template <typename T>
inline T Dict::get(const String &key, const T &defaultValue) const
{
_Dict::const_iterator i = dict.find(key);
if (i != dict.end())
return i->second.get<T>();
else
return defaultValue;
}
template<typename T>
inline const T &Dict::set(const String &key, const T &value)
{
_Dict::iterator i = dict.find(key);
if (i != dict.end())
i->second = DictValue(value);
else
dict.insert(std::make_pair(key, DictValue(value)));
return value;
}
inline std::ostream &operator<<(std::ostream &stream, const Dict &dict)
{
Dict::_Dict::const_iterator it;
for (it = dict.dict.begin(); it != dict.dict.end(); it++)
stream << it->first << " : " << it->second << "\n";
return stream;
}
CV__DNN_EXPERIMENTAL_NS_END
}
}
#endif

78
3rdparty/libopencv/include/opencv2/dnn/layer.details.hpp vendored Normal file
View File

@ -0,0 +1,78 @@
// This file is part of OpenCV project.
// It is subject to the license terms in the LICENSE file found in the top-level directory
// of this distribution and at http://opencv.org/license.html.
//
#ifndef OPENCV_DNN_LAYER_DETAILS_HPP
#define OPENCV_DNN_LAYER_DETAILS_HPP
#include <opencv2/dnn/layer.hpp>
namespace cv {
namespace dnn {
CV__DNN_EXPERIMENTAL_NS_BEGIN
/** @brief Registers layer constructor in runtime.
* @param type string, containing type name of the layer.
* @param constuctorFunc pointer to the function of type LayerRegister::Constuctor, which creates the layer.
* @details This macros must be placed inside the function code.
*/
#define CV_DNN_REGISTER_LAYER_FUNC(type, constuctorFunc) \
cv::dnn::LayerFactory::registerLayer(#type, constuctorFunc);
/** @brief Registers layer class in runtime.
* @param type string, containing type name of the layer.
* @param class C++ class, derived from Layer.
* @details This macros must be placed inside the function code.
*/
#define CV_DNN_REGISTER_LAYER_CLASS(type, class) \
cv::dnn::LayerFactory::registerLayer(#type, cv::dnn::details::_layerDynamicRegisterer<class>);
/** @brief Registers layer constructor on module load time.
* @param type string, containing type name of the layer.
* @param constuctorFunc pointer to the function of type LayerRegister::Constuctor, which creates the layer.
* @details This macros must be placed outside the function code.
*/
#define CV_DNN_REGISTER_LAYER_FUNC_STATIC(type, constuctorFunc) \
static cv::dnn::details::_LayerStaticRegisterer __LayerStaticRegisterer_##type(#type, constuctorFunc);
/** @brief Registers layer class on module load time.
* @param type string, containing type name of the layer.
* @param class C++ class, derived from Layer.
* @details This macros must be placed outside the function code.
*/
#define CV_DNN_REGISTER_LAYER_CLASS_STATIC(type, class) \
Ptr<Layer> __LayerStaticRegisterer_func_##type(LayerParams &params) \
{ return Ptr<Layer>(new class(params)); } \
static cv::dnn::details::_LayerStaticRegisterer __LayerStaticRegisterer_##type(#type, __LayerStaticRegisterer_func_##type);
namespace details {
template<typename LayerClass>
Ptr<Layer> _layerDynamicRegisterer(LayerParams &params)
{
return Ptr<Layer>(LayerClass::create(params));
}
//allows automatically register created layer on module load time
class _LayerStaticRegisterer
{
String type;
public:
_LayerStaticRegisterer(const String &layerType, LayerFactory::Constuctor layerConstuctor)
{
this->type = layerType;
LayerFactory::registerLayer(layerType, layerConstuctor);
}
~_LayerStaticRegisterer()
{
LayerFactory::unregisterLayer(type);
}
};
} // namespace
CV__DNN_EXPERIMENTAL_NS_END
}} // namespace
#endif

85
3rdparty/libopencv/include/opencv2/dnn/layer.hpp vendored Normal file
View File

@ -0,0 +1,85 @@
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of the copyright holders may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#ifndef OPENCV_DNN_LAYER_HPP
#define OPENCV_DNN_LAYER_HPP
#include <opencv2/dnn.hpp>
namespace cv {
namespace dnn {
CV__DNN_EXPERIMENTAL_NS_BEGIN
//! @addtogroup dnn
//! @{
//!
//! @defgroup dnnLayerFactory Utilities for New Layers Registration
//! @{
/** @brief %Layer factory allows to create instances of registered layers. */
class CV_EXPORTS LayerFactory
{
public:
//! Each Layer class must provide this function to the factory
typedef Ptr<Layer>(*Constuctor)(LayerParams &params);
//! Registers the layer class with typename @p type and specified @p constructor. Thread-safe.
static void registerLayer(const String &type, Constuctor constructor);
//! Unregisters registered layer with specified type name. Thread-safe.
static void unregisterLayer(const String &type);
/** @brief Creates instance of registered layer.
* @param type type name of creating layer.
* @param params parameters which will be used for layer initialization.
* @note Thread-safe.
*/
static Ptr<Layer> createLayerInstance(const String &type, LayerParams& params);
private:
LayerFactory();
};
//! @}
//! @}
CV__DNN_EXPERIMENTAL_NS_END
}
}
#endif

206
3rdparty/libopencv/include/opencv2/dnn/shape_utils.hpp vendored Normal file
View File

@ -0,0 +1,206 @@
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of the copyright holders may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#ifndef OPENCV_DNN_DNN_SHAPE_UTILS_HPP
#define OPENCV_DNN_DNN_SHAPE_UTILS_HPP
#include <opencv2/core.hpp>
#include <opencv2/core/types_c.h>
#include <ostream>
namespace cv {
namespace dnn {
CV__DNN_EXPERIMENTAL_NS_BEGIN
//Useful shortcut
inline std::ostream &operator<< (std::ostream &s, cv::Range &r)
{
return s << "[" << r.start << ", " << r.end << ")";
}
//Slicing
struct _Range : public cv::Range
{
_Range(const Range &r) : cv::Range(r) {}
_Range(int start_, int size_ = 1) : cv::Range(start_, start_ + size_) {}
};
static inline Mat slice(const Mat &m, const _Range &r0)
{
Range ranges[CV_MAX_DIM];
for (int i = 1; i < m.dims; i++)
ranges[i] = Range::all();
ranges[0] = r0;
return m(&ranges[0]);
}
static inline Mat slice(const Mat &m, const _Range &r0, const _Range &r1)
{
CV_Assert(m.dims >= 2);
Range ranges[CV_MAX_DIM];
for (int i = 2; i < m.dims; i++)
ranges[i] = Range::all();
ranges[0] = r0;
ranges[1] = r1;
return m(&ranges[0]);
}
static inline Mat slice(const Mat &m, const _Range &r0, const _Range &r1, const _Range &r2)
{
CV_Assert(m.dims >= 3);
Range ranges[CV_MAX_DIM];
for (int i = 3; i < m.dims; i++)
ranges[i] = Range::all();
ranges[0] = r0;
ranges[1] = r1;
ranges[2] = r2;
return m(&ranges[0]);
}
static inline Mat slice(const Mat &m, const _Range &r0, const _Range &r1, const _Range &r2, const _Range &r3)
{
CV_Assert(m.dims >= 4);
Range ranges[CV_MAX_DIM];
for (int i = 4; i < m.dims; i++)
ranges[i] = Range::all();
ranges[0] = r0;
ranges[1] = r1;
ranges[2] = r2;
ranges[3] = r3;
return m(&ranges[0]);
}
static inline Mat getPlane(const Mat &m, int n, int cn)
{
CV_Assert(m.dims > 2);
int sz[CV_MAX_DIM];
for(int i = 2; i < m.dims; i++)
{
sz[i-2] = m.size.p[i];
}
return Mat(m.dims - 2, sz, m.type(), (void*)m.ptr<float>(n, cn));
}
static inline MatShape shape(const int* dims, const int n = 4)
{
MatShape shape;
shape.assign(dims, dims + n);
return shape;
}
static inline MatShape shape(const Mat& mat)
{
return shape(mat.size.p, mat.dims);
}
static inline MatShape shape(const UMat& mat)
{
return shape(mat.size.p, mat.dims);
}
namespace {inline bool is_neg(int i) { return i < 0; }}
static inline MatShape shape(int a0, int a1=-1, int a2=-1, int a3=-1)
{
int dims[] = {a0, a1, a2, a3};
MatShape s = shape(dims);
s.erase(std::remove_if(s.begin(), s.end(), is_neg), s.end());
return s;
}
static inline int total(const MatShape& shape, int start = -1, int end = -1)
{
if (start == -1) start = 0;
if (end == -1) end = (int)shape.size();
if (shape.empty())
return 0;
int elems = 1;
CV_Assert(start <= (int)shape.size() && end <= (int)shape.size() &&
start <= end);
for(int i = start; i < end; i++)
{
elems *= shape[i];
}
return elems;
}
static inline MatShape concat(const MatShape& a, const MatShape& b)
{
MatShape c = a;
c.insert(c.end(), b.begin(), b.end());
return c;
}
inline void print(const MatShape& shape, const String& name = "")
{
printf("%s: [", name.c_str());
size_t i, n = shape.size();
for( i = 0; i < n; i++ )
printf(" %d", shape[i]);
printf(" ]\n");
}
inline int clamp(int ax, int dims)
{
return ax < 0 ? ax + dims : ax;
}
inline int clamp(int ax, const MatShape& shape)
{
return clamp(ax, (int)shape.size());
}
inline Range clamp(const Range& r, int axisSize)
{
Range clamped(std::max(r.start, 0),
r.end > 0 ? std::min(r.end, axisSize) : axisSize + r.end + 1);
CV_Assert(clamped.start < clamped.end, clamped.end <= axisSize);
return clamped;
}
CV__DNN_EXPERIMENTAL_NS_END
}
}
#endif