potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-30 07:43:03 +04:00
Code Packages Releases Wiki Activity

JavaScript bindings for dnn module

Browse Source
This commit is contained in:
Dmitry Kurtaev
2017-12-02 23:52:35 +03:00
parent 6185f7209e
commit f503515082
14 changed files with 326 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/CMakeLists.txt
+1 -1
View File
@@ -15,7 +15,7 @@ set(the_description "Deep neural network module. It allows to load models from d
ocv_add_dispatched_file("layers/layers_common" AVX AVX2)
ocv_add_module(dnn opencv_core opencv_imgproc WRAP python matlab java)
ocv_add_module(dnn opencv_core opencv_imgproc WRAP python matlab java js)
ocv_warnings_disable(CMAKE_CXX_FLAGS -Wno-shadow -Wno-parentheses -Wmaybe-uninitialized -Wsign-promo
-Wmissing-declarations -Wmissing-prototypes
)
modules/dnn/include/opencv2/dnn/all_layers.hpp
-20
View File
@@ -221,11 +221,6 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
class CV_EXPORTS LRNLayer : public Layer
{
public:
enum Type
{
CHANNEL_NRM,
SPATIAL_NRM
};
int type;
int size;
@@ -238,14 +233,6 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
class CV_EXPORTS PoolingLayer : public Layer
{
public:
enum Type
{
MAX,
AVE,
STOCHASTIC,
ROI
};
int type;
Size kernel, stride, pad;
bool globalPooling;
@@ -474,13 +461,6 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
class CV_EXPORTS EltwiseLayer : public Layer
{
public:
enum EltwiseOp
{
PROD = 0,
SUM = 1,
MAX = 2,
};
static Ptr<EltwiseLayer> create(const LayerParams &params);
};
modules/dnn/include/opencv2/dnn/dnn.hpp
+4 -4
View File
@@ -423,8 +423,8 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
* @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 void forward(std::vector<std::vector<Mat> >& outputBlobs,
const std::vector<String>& outBlobNames);
void forward(std::vector<std::vector<Mat> >& outputBlobs,
const std::vector<String>& outBlobNames);
//TODO:
/** @brief Optimized forward.
@@ -467,7 +467,7 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
* @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(const Mat &blob, const String& name = "");
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.
@@ -733,7 +733,7 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
* 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(const Mat& image, double scalefactor=1.0, const Size& size = Size(),
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 series of images. Optionally resizes and
* crops @p images from center, subtract @p mean values, scales values by @p scalefactor,
modules/dnn/src/dnn.cpp
+4 -3
View File
@@ -84,11 +84,11 @@ static String toString(const T &v)
return ss.str();
}
Mat blobFromImage(const Mat& image, double scalefactor, const Size& size,
Mat blobFromImage(InputArray image, double scalefactor, const Size& size,
const Scalar& mean, bool swapRB, bool crop)
{
CV_TRACE_FUNCTION();
std::vector<Mat> images(1, image);
std::vector<Mat> images(1, image.getMat());
return blobFromImages(images, scalefactor, size, mean, swapRB, crop);
}
@@ -1910,7 +1910,7 @@ void Net::setInputsNames(const std::vector<String> &inputBlobNames)
impl->netInputLayer->setNames(inputBlobNames);
}
void Net::setInput(const Mat &blob_, const String& name)
void Net::setInput(InputArray blob, const String& name)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
@@ -1930,6 +1930,7 @@ void Net::setInput(const Mat &blob_, const String& name)
ld.umat_outputBlobs.resize( std::max(pin.oid+1, (int)ld.requiredOutputs.size()) );
ld.outputBlobsWrappers.resize(ld.outputBlobs.size());
MatShape prevShape = shape(ld.outputBlobs[pin.oid]);
Mat blob_ = blob.getMat();
bool oldShape = prevShape == shape(blob_);
if (oldShape)
{
modules/dnn/src/layers/eltwise_layer.cpp
+14 -9
View File
@@ -52,22 +52,27 @@ namespace dnn
class EltwiseLayerImpl : public EltwiseLayer
{
public:
EltwiseOp op;
enum EltwiseOp
{
PROD = 0,
SUM = 1,
MAX = 2,
} op;
std::vector<float> coeffs;
EltwiseLayerImpl(const LayerParams& params)
{
setParamsFrom(params);
op = EltwiseLayer::SUM;
op = SUM;
if (params.has("operation"))
{
String operation = params.get<String>("operation").toLowerCase();
if (operation == "prod")
op = EltwiseLayer::PROD;
op = PROD;
else if (operation == "sum")
op = EltwiseLayer::SUM;
op = SUM;
else if (operation == "max")
op = EltwiseLayer::MAX;
op = MAX;
else
CV_Error(cv::Error::StsBadArg, "Unknown operaticon type \"" + operation + "\"");
}
@@ -122,7 +127,7 @@ public:
int channels;
size_t planeSize;
EltwiseInvoker() : srcs(0), nsrcs(0), dst(0), coeffs(0), op(EltwiseLayer::PROD), nstripes(0), activ(0), channels(0), planeSize(0) {}
EltwiseInvoker() : srcs(0), nsrcs(0), dst(0), coeffs(0), op(PROD), nstripes(0), activ(0), channels(0), planeSize(0) {}
static void run(const Mat** srcs, int nsrcs, Mat& dst,
const std::vector<float>& coeffs, EltwiseOp op,
@@ -150,7 +155,7 @@ public:
CV_Assert(dst.total() == dst.size[0] * p.channels * p.planeSize);
bool simpleCoeffs = true;
if( op == EltwiseLayer::SUM && !coeffs.empty() )
if( op == SUM && !coeffs.empty() )
{
CV_Assert( coeffs.size() == (size_t)nsrcs );
@@ -192,7 +197,7 @@ public:
const float* srcptr0 = srcs[0]->ptr<float>() + globalDelta;
float* dstptr = dstptr0 + globalDelta;
if( op == EltwiseLayer::PROD )
if( op == PROD )
{
for( k = 1; k < n; k++ )
{
@@ -204,7 +209,7 @@ public:
srcptr0 = (const float*)dstptr;
}
}
else if( op == EltwiseLayer::MAX )
else if( op == MAX )
{
for( k = 1; k < n; k++ )
{
modules/dnn/src/layers/lrn_layer.cpp
+9 -2
View File
@@ -67,9 +67,9 @@ public:
type = -1;
String nrmType = params.get<String>("norm_region", "ACROSS_CHANNELS");
if (nrmType == "ACROSS_CHANNELS")
type = LRNLayer::CHANNEL_NRM;
type = CHANNEL_NRM;
else if (nrmType == "WITHIN_CHANNEL")
type = LRNLayer::SPATIAL_NRM;
type = SPATIAL_NRM;
else
CV_Error(Error::StsBadArg, "Unknown region type \"" + nrmType + "\"");
@@ -397,6 +397,13 @@ public:
}
return flops;
}
private:
enum Type
{
CHANNEL_NRM,
SPATIAL_NRM
};
};
Ptr<LRNLayer> LRNLayer::create(const LayerParams& params)
modules/dnn/src/layers/pooling_layer.cpp
+18 -11
View File
@@ -63,7 +63,7 @@ class PoolingLayerImpl : public PoolingLayer
public:
PoolingLayerImpl(const LayerParams& params)
{
type = PoolingLayer::MAX;
type = MAX;
computeMaxIdx = true;
globalPooling = false;
@@ -71,11 +71,11 @@ public:
{
String pool = params.get<String>("pool").toLowerCase();
if (pool == "max")
type = PoolingLayer::MAX;
type = MAX;
else if (pool == "ave")
type = PoolingLayer::AVE;
type = AVE;
else if (pool == "stochastic")
type = PoolingLayer::STOCHASTIC;
type = STOCHASTIC;
else
CV_Error(Error::StsBadArg, "Unknown pooling type \"" + pool + "\"");
getPoolingKernelParams(params, kernel.height, kernel.width, globalPooling,
@@ -83,7 +83,7 @@ public:
}
else if (params.has("pooled_w") || params.has("pooled_h") || params.has("spatial_scale"))
{
type = PoolingLayer::ROI;
type = ROI;
}
setParamsFrom(params);
ceilMode = params.get<bool>("ceil_mode", true);
@@ -115,8 +115,7 @@ public:
{
return backendId == DNN_BACKEND_DEFAULT ||
backendId == DNN_BACKEND_HALIDE && haveHalide() &&
(type == PoolingLayer::MAX ||
type == PoolingLayer::AVE && !pad.width && !pad.height);
(type == MAX || type == AVE && !pad.width && !pad.height);
}
#ifdef HAVE_OPENCL
@@ -200,9 +199,9 @@ public:
virtual Ptr<BackendNode> initHalide(const std::vector<Ptr<BackendWrapper> > &inputs)
{
if (type == PoolingLayer::MAX)
if (type == MAX)
return initMaxPoolingHalide(inputs);
else if (type == PoolingLayer::AVE)
else if (type == AVE)
return initAvePoolingHalide(inputs);
else
return Ptr<BackendNode>();
@@ -221,7 +220,7 @@ public:
float spatialScale;
PoolingInvoker() : src(0), rois(0), dst(0), mask(0), nstripes(0),
computeMaxIdx(0), poolingType(PoolingLayer::MAX), spatialScale(0) {}
computeMaxIdx(0), poolingType(MAX), spatialScale(0) {}
static void run(const Mat& src, const Mat& rois, Mat& dst, Mat& mask, Size kernel,
Size stride, Size pad, int poolingType, float spatialScale,
@@ -698,7 +697,7 @@ public:
out.height = 1;
out.width = 1;
}
else if (type == PoolingLayer::ROI)
else if (type == ROI)
{
out.height = pooledSize.height;
out.width = pooledSize.width;
@@ -757,6 +756,14 @@ public:
}
return flops;
}
private:
enum Type
{
MAX,
AVE,
STOCHASTIC,
ROI
};
};
Ptr<PoolingLayer> PoolingLayer::create(const LayerParams& params)
modules/js/src/core_bindings.cpp
+5 -3
View File
@@ -73,11 +73,13 @@
#include "opencv2/video/tracking.hpp"
#include "opencv2/video/background_segm.hpp"
#include "opencv2/objdetect.hpp"
#include "opencv2/dnn.hpp"
#include <emscripten/bind.h>
using namespace emscripten;
using namespace cv;
using namespace dnn;
namespace binding_utils
{
@@ -339,12 +341,12 @@ EMSCRIPTEN_BINDINGS(binding_utils)
.constructor<int, int, int, const Scalar&>()
.constructor(&binding_utils::createMat, allow_raw_pointers())
.class_function("eye", select_overload<Mat(int, int, int)>(&binding_utils::matEye))
.class_function("eye", select_overload<Mat(Size, int)>(&binding_utils::matEye))
.class_function("ones", select_overload<Mat(int, int, int)>(&binding_utils::matOnes))
.class_function("eye", select_overload<Mat(int, int, int)>(&binding_utils::matEye))
.class_function("ones", select_overload<Mat(Size, int)>(&binding_utils::matOnes))
.class_function("zeros", select_overload<Mat(int, int, int)>(&binding_utils::matZeros))
.class_function("ones", select_overload<Mat(int, int, int)>(&binding_utils::matOnes))
.class_function("zeros", select_overload<Mat(Size, int)>(&binding_utils::matZeros))
.class_function("zeros", select_overload<Mat(int, int, int)>(&binding_utils::matZeros))
.property("rows", &cv::Mat::rows)
.property("cols", &cv::Mat::cols)
modules/js/src/embindgen.py
+4 -1
View File
@@ -125,6 +125,9 @@ video = {'': ['CamShift', 'calcOpticalFlowFarneback', 'calcOpticalFlowPyrLK', 'c
'BackgroundSubtractorMOG2': ['BackgroundSubtractorMOG2', 'apply'],
'BackgroundSubtractor': ['apply', 'getBackgroundImage']}
dnn = {'dnn_Net': ['setInput', 'forward'],
'': ['readNetFromCaffe', 'readNetFromTensorflow', 'readNetFromTorch', 'readNetFromDarknet', 'blobFromImage']}
def makeWhiteList(module_list):
wl = {}
for m in module_list:
@@ -135,7 +138,7 @@ def makeWhiteList(module_list):
wl[k] = m[k]
return wl
white_list = makeWhiteList([core, imgproc, objdetect, video])
white_list = makeWhiteList([core, imgproc, objdetect, video, dnn])
# Features to be exported
export_enums = False