potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 07:13:02 +04:00
Code Packages Releases Wiki Activity

Merge pull request #16724 from liqi-c:3.4-tengine

Browse Source 
* Add Tengine support .

* Modify printf to CV_LOG_WARNING

* a few minor fixes in the code

* Renew Tengine version

* Add header file for CV_LOG_WARNING

* Add #ifdef HAVE_TENGINE in tengine_graph_convolution.cpp

* remove trailing whitespace

* Remove trailing whitespace

* Modify for compile problem

* Modify some code style error

* remove whitespace

* Move some code style problem

* test

* add ios limit and build problem

* Modified as alalek suggested

* Add cmake 2.8 support

* modify cmake 3.5.1 problem

* test and set BUILD_ANDROID_PROJECTS OFF

* remove some compile error

* remove some extra code in tengine

* close test.

* Test again

* disable android.

* delete ndk version judgement

* Remove setenv() call . and add License information

* Set tengine default OFF. Close test .

Co-authored-by: Vadim Pisarevsky <vadim.pisarevsky@gmail.com>
This commit is contained in:
NesQl
2020-03-09 22:59:23 +08:00
committed by GitHub
parent 969cc3dd95
commit 0bcdf7d03e
7 changed files with 617 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/src/layers/convolution_layer.cpp
+39 -3
View File
@@ -55,6 +55,9 @@
#include "opencl_kernels_dnn.hpp"
using namespace cv::dnn::ocl4dnn;
#endif
#ifdef HAVE_TENGINE
#include "../tengine4dnn/include/tengine_graph_convolution.hpp"
#endif
namespace cv
{
@@ -1272,10 +1275,43 @@ public:
}
}
int nstripes = std::max(getNumThreads(), 1);
#ifdef HAVE_TENGINE
int inch = inputs[0].size[1]; // inch
int in_h = inputs[0].size[2]; // in_h
int in_w = inputs[0].size[3]; // in_w
ParallelConv::run(inputs[0], outputs[0], weightsMat, biasvec, reluslope,
kernel_size, strides, pads_begin, pads_end, dilations, activ.get(), ngroups, nstripes);
int out_b = outputs[0].size[0]; // out batch size
int outch = outputs[0].size[1]; // outch
int out_h = outputs[0].size[2]; // out_h
int out_w = outputs[0].size[3]; // out_w
float *input_ = inputs[0].ptr<float>();
float *output_ = outputs[0].ptr<float>();
float *kernel_ = weightsMat.ptr<float>();
float *teg_bias = &biasvec[0];
bool tengine_ret = tengine_forward(input_, inch, ngroups, in_h, in_w,
output_, out_b, outch, out_h, out_w,
kernel_, kernel_size.size(), kernel.height, kernel.width,
teg_bias, stride.height, stride.width,
pad.height, pad.width, dilation.height, dilation.width,
weightsMat.step1(), padMode);
/* activation */
if((true == tengine_ret) && activ )
{
int out_cstep = out_h * out_w; // out_cstep
ActivationLayer* activ_ = activ.get();
activ_->forwardSlice(output_, output_, out_cstep, out_cstep, 0, outch);
}
if(false == tengine_ret)
#endif
{
int nstripes = std::max(getNumThreads(), 1);
ParallelConv::run(inputs[0], outputs[0], weightsMat, biasvec, reluslope,
kernel_size, strides, pads_begin, pads_end, dilations, activ.get(), ngroups, nstripes);
}
}
virtual int64 getFLOPS(const std::vector<MatShape> &inputs,