dnn(ocl4dnn): fuseLayer() use umat_input/outputBlobs for OpenCL target

wzw-intel · pli2-intel · commit 1f465a0ef9f2 · 2017-11-27T22:25:53.000+08:00
Also, fix bug when use OPENCL target but no OpenCL runtime

Signed-off-by: Wu Zhiwen &lt;zhiwen.wu@intel.com&gt;
diff --git a/modules/dnn/src/dnn.cpp b/modules/dnn/src/dnn.cpp
@@ -1196,7 +1196,8 @@ struct Net::Impl
             // some other layers.
 
             // TODO: OpenCL target support more fusion styles.
-            if ( preferableTarget == DNN_TARGET_OPENCL && ld.layerInstance->type.compare("Convolution") )
+            if ( preferableTarget == DNN_TARGET_OPENCL &&
+                 (!cv::ocl::useOpenCL() || ld.layerInstance->type.compare("Convolution")) )
                 continue;
 
             Ptr<Layer>& currLayer = ld.layerInstance;
@@ -1214,7 +1215,10 @@ struct Net::Impl
                     {
                         printf_(("\tfused with %s\n", nextBNormLayer->name.c_str()));
                         bnormData->skipFlags[DNN_BACKEND_DEFAULT] = true;
-                        ld.outputBlobs = layers[lpNext.lid].outputBlobs;
+                        if ( preferableTarget == DNN_TARGET_OPENCL )
+                            ld.umat_outputBlobs = layers[lpNext.lid].umat_outputBlobs;
+                        else
+                            ld.outputBlobs = layers[lpNext.lid].outputBlobs;
                         if( bnormData->consumers.size() == 1 )
                         {
                             nextData = &layers[bnormData->consumers[0].lid];
@@ -1234,7 +1238,10 @@ struct Net::Impl
                     {
                         printf_(("\tfused with %s\n", nextScaleLayer->name.c_str()));
                         scaleData->skipFlags[DNN_BACKEND_DEFAULT] = true;
-                        ld.outputBlobs = layers[lpNext.lid].outputBlobs;
+                        if ( preferableTarget == DNN_TARGET_OPENCL )
+                            ld.umat_outputBlobs = layers[lpNext.lid].umat_outputBlobs;
+                        else
+                            ld.outputBlobs = layers[lpNext.lid].outputBlobs;
                         if( scaleData->consumers.size() == 1 )
                         {
                             nextData = &layers[scaleData->consumers[0].lid];
@@ -1263,7 +1270,10 @@ struct Net::Impl
                         LayerData *activData = nextData;
                         printf_(("\tfused with %s\n", nextActivLayer->name.c_str()));
                         activData->skipFlags[DNN_BACKEND_DEFAULT] = true;
-                        ld.outputBlobs = layers[lpNext.lid].outputBlobs;
+                        if ( preferableTarget == DNN_TARGET_OPENCL )
+                            ld.umat_outputBlobs = layers[lpNext.lid].umat_outputBlobs;
+                        else
+                            ld.outputBlobs = layers[lpNext.lid].outputBlobs;
 
                         if ( preferableTarget == DNN_TARGET_OPENCL )
                         {
@@ -1325,13 +1335,13 @@ struct Net::Impl
                                              !nextData->type.compare("Power")) &&
                                             currLayer->setActivation(nextActivLayer) )
                                     {
-                                        CV_Assert(firstConvLayerData->outputBlobs.size() == 1 && ld.inputBlobs.size() == 1);
-                                        ld.inputBlobs.push_back(&firstConvLayerData->outputBlobs[0]);
+                                        CV_Assert(firstConvLayerData->umat_outputBlobs.size() == 1 && ld.umat_inputBlobs.size() == 1);
+                                        ld.umat_inputBlobs.push_back(firstConvLayerData->umat_outputBlobs[0]);
                                         printf_(("\tfused with %s\n", nextEltwiseLayer->name.c_str()));
                                         printf_(("\tfused with %s\n", nextActivLayer->name.c_str()));
                                         eltwiseData->skipFlags[DNN_BACKEND_DEFAULT] = true;
                                         nextData->skipFlags[DNN_BACKEND_DEFAULT] = true;
-                                        ld.outputBlobs = layers[lpNext.lid].outputBlobs;
+                                        ld.umat_outputBlobs = layers[lpNext.lid].umat_outputBlobs;
                                     }
                                 }
                             }
