Merge pull request #10992 from dkurt:dnn_opencl_tests

modules/dnn/src/layers/convolution_layer.cpp

@@ -273,6 +273,9 @@ public:
             for(int i = 0; i < outCn; i++ )
                 biasvec[i] = biasMat.at<float>(i);
         }
+#ifdef HAVE_OPENCL
+        convolutionOp.release();
+#endif
     }
 
     bool setActivation(const Ptr<ActivationLayer>& layer)

modules/dnn/src/layers/fully_connected_layer.cpp

@@ -267,6 +267,11 @@ public:
     };
 
 #ifdef HAVE_OPENCL
+    void finalize(const std::vector<Mat*> &inputs, std::vector<Mat> &outputs)
+    {
+        innerProductOp.release();
+    }
+
     bool forward_ocl(InputArrayOfArrays inps, OutputArrayOfArrays outs, InputArrayOfArrays internals)
     {
         std::vector<UMat> inputs;

modules/dnn/src/layers/lrn_layer.cpp

@@ -96,6 +96,11 @@ public:
     }
 
 #ifdef HAVE_OPENCL
+    void finalize(const std::vector<Mat*> &inputs, std::vector<Mat> &outputs)
+    {
+        lrnOp.release();
+    }
+
     bool forward_ocl(InputArrayOfArrays inps, OutputArrayOfArrays outs, OutputArrayOfArrays internals)
     {
         std::vector<UMat> inputs;

modules/dnn/src/layers/pooling_layer.cpp

@@ -127,6 +127,10 @@ public:
         }
 
         getConvPoolPaddings(inp, out, kernel, stride, padMode, Size(1, 1), pad);
+
+#ifdef HAVE_OPENCL
+        poolOp.release();
+#endif
     }
 
     virtual bool supportBackend(int backendId)

modules/dnn/src/layers/softmax_layer.cpp

@@ -94,6 +94,11 @@ public:
     }
 
 #ifdef HAVE_OPENCL
+    virtual void finalize(const std::vector<Mat*> &inputs, std::vector<Mat> &outputs)
+    {
+        softmaxOp.release();
+    }
+
     bool forward_ocl(InputArrayOfArrays inps, OutputArrayOfArrays outs, OutputArrayOfArrays itns)
     {
         std::vector<UMat> inputs;

modules/dnn/test/test_backends.cpp

@@ -10,9 +10,6 @@
 
 namespace opencv_test { namespace {
 
-CV_ENUM(DNNBackend, DNN_BACKEND_DEFAULT, DNN_BACKEND_HALIDE, DNN_BACKEND_INFERENCE_ENGINE)
-CV_ENUM(DNNTarget, DNN_TARGET_CPU, DNN_TARGET_OPENCL)
-
 static void loadNet(const std::string& weights, const std::string& proto,
                     const std::string& framework, Net* net)
 {

modules/dnn/test/test_caffe_importer.cpp

@@ -42,8 +42,6 @@
 #include "test_precomp.hpp"
 #include "npy_blob.hpp"
 #include <opencv2/dnn/shape_utils.hpp>
-#include <opencv2/core/ocl.hpp>
-#include <opencv2/ts/ocl_test.hpp>
 
 namespace opencv_test { namespace {
 
@@ -83,10 +81,10 @@ TEST(Test_Caffe, read_googlenet)
     ASSERT_FALSE(net.empty());
 }
 
-typedef testing::TestWithParam<bool> Reproducibility_AlexNet;
+typedef testing::TestWithParam<tuple<bool, DNNTarget> > Reproducibility_AlexNet;
 TEST_P(Reproducibility_AlexNet, Accuracy)
 {
-    bool readFromMemory = GetParam();
+    bool readFromMemory = get<0>(GetParam());
     Net net;
     {
         const string proto = findDataFile("dnn/bvlc_alexnet.prototxt", false);
@@ -106,42 +104,7 @@ TEST_P(Reproducibility_AlexNet, Accuracy)
         ASSERT_FALSE(net.empty());
     }
 
-    Mat sample = imread(_tf("grace_hopper_227.png"));
-    ASSERT_TRUE(!sample.empty());
-
-    net.setInput(blobFromImage(sample, 1.0f, Size(227, 227), Scalar(), false), "data");
-    Mat out = net.forward("prob");
-    Mat ref = blobFromNPY(_tf("caffe_alexnet_prob.npy"));
-    normAssert(ref, out);
-}
-
-INSTANTIATE_TEST_CASE_P(Test_Caffe, Reproducibility_AlexNet, testing::Bool());
-
-typedef testing::TestWithParam<bool> Reproducibility_OCL_AlexNet;
-OCL_TEST_P(Reproducibility_OCL_AlexNet, Accuracy)
-{
-    bool readFromMemory = GetParam();
-    Net net;
-    {
-        const string proto = findDataFile("dnn/bvlc_alexnet.prototxt", false);
-        const string model = findDataFile("dnn/bvlc_alexnet.caffemodel", false);
-        if (readFromMemory)
-        {
-            string dataProto;
-            ASSERT_TRUE(readFileInMemory(proto, dataProto));
-            string dataModel;
-            ASSERT_TRUE(readFileInMemory(model, dataModel));
-
-            net = readNetFromCaffe(dataProto.c_str(), dataProto.size(),
-                                   dataModel.c_str(), dataModel.size());
-        }
-        else
-            net = readNetFromCaffe(proto, model);
-        ASSERT_FALSE(net.empty());
-    }
-
-    net.setPreferableBackend(DNN_BACKEND_DEFAULT);
-    net.setPreferableTarget(DNN_TARGET_OPENCL);
+    net.setPreferableTarget(get<1>(GetParam()));
 
     Mat sample = imread(_tf("grace_hopper_227.png"));
     ASSERT_TRUE(!sample.empty());
@@ -152,7 +115,7 @@ OCL_TEST_P(Reproducibility_OCL_AlexNet, Accuracy)
     normAssert(ref, out);
 }
 
-OCL_INSTANTIATE_TEST_CASE_P(Test_Caffe, Reproducibility_OCL_AlexNet, testing::Bool());
+INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_AlexNet, Combine(testing::Bool(), availableDnnTargets()));
 
 #if !defined(_WIN32) || defined(_WIN64)
 TEST(Reproducibility_FCN, Accuracy)
@@ -207,43 +170,14 @@ TEST(Reproducibility_SSD, Accuracy)
     normAssert(ref, out);
 }
 
-TEST(Reproducibility_MobileNet_SSD, Accuracy)
-{
-    const string proto = findDataFile("dnn/MobileNetSSD_deploy.prototxt", false);
-    const string model = findDataFile("dnn/MobileNetSSD_deploy.caffemodel", false);
-    Net net = readNetFromCaffe(proto, model);
-
-    Mat sample = imread(_tf("street.png"));
-
-    Mat inp = blobFromImage(sample, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);
-    net.setInput(inp);
-    Mat out = net.forward();
-
-    Mat ref = blobFromNPY(_tf("mobilenet_ssd_caffe_out.npy"));
-    normAssert(ref, out);
-
-    // Check that detections aren't preserved.
-    inp.setTo(0.0f);
-    net.setInput(inp);
-    out = net.forward();
-
-    const int numDetections = out.size[2];
-    ASSERT_NE(numDetections, 0);
-    for (int i = 0; i < numDetections; ++i)
-    {
-        float confidence = out.ptr<float>(0, 0, i)[2];
-        ASSERT_EQ(confidence, 0);
-    }
-}
-
-OCL_TEST(Reproducibility_MobileNet_SSD, Accuracy)
+typedef testing::TestWithParam<DNNTarget> Reproducibility_MobileNet_SSD;
+TEST_P(Reproducibility_MobileNet_SSD, Accuracy)
 {
     const string proto = findDataFile("dnn/MobileNetSSD_deploy.prototxt", false);
     const string model = findDataFile("dnn/MobileNetSSD_deploy.caffemodel", false);
     Net net = readNetFromCaffe(proto, model);
 
-    net.setPreferableBackend(DNN_BACKEND_DEFAULT);
-    net.setPreferableTarget(DNN_TARGET_OPENCL);
+    net.setPreferableTarget(GetParam());
 
     Mat sample = imread(_tf("street.png"));
 
@@ -258,38 +192,39 @@ OCL_TEST(Reproducibility_MobileNet_SSD, Accuracy)
     inp.setTo(0.0f);
     net.setInput(inp);
     out = net.forward();
+    out = out.reshape(1, out.total() / 7);
 
-    const int numDetections = out.size[2];
+    const int numDetections = out.rows;
     ASSERT_NE(numDetections, 0);
     for (int i = 0; i < numDetections; ++i)
     {
-        float confidence = out.ptr<float>(0, 0, i)[2];
+        float confidence = out.ptr<float>(i)[2];
         ASSERT_EQ(confidence, 0);
     }
-}
 
-TEST(Reproducibility_ResNet50, Accuracy)
-{
-    Net net = readNetFromCaffe(findDataFile("dnn/ResNet-50-deploy.prototxt", false),
-                               findDataFile("dnn/ResNet-50-model.caffemodel", false));
-
-    Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(224,224), Scalar(), false);
-    ASSERT_TRUE(!input.empty());
-
-    net.setInput(input);
-    Mat out = net.forward();
-
-    Mat ref = blobFromNPY(_tf("resnet50_prob.npy"));
-    normAssert(ref, out);
+    // Check batching mode.
+    ref = ref.reshape(1, numDetections);
+    inp = blobFromImages(std::vector<Mat>(2, sample), 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);
+    net.setInput(inp);
+    Mat outBatch = net.forward();
+
+    // Output blob has a shape 1x1x2Nx7 where N is a number of detection for
+    // a single sample in batch. The first numbers of detection vectors are batch id.
+    outBatch = outBatch.reshape(1, outBatch.total() / 7);
+    EXPECT_EQ(outBatch.rows, 2 * numDetections);
+    normAssert(outBatch.rowRange(0, numDetections), ref);
+    normAssert(outBatch.rowRange(numDetections, 2 * numDetections).colRange(1, 7), ref.colRange(1, 7));
 }
+INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_MobileNet_SSD, availableDnnTargets());
 
-OCL_TEST(Reproducibility_ResNet50, Accuracy)
+typedef testing::TestWithParam<DNNTarget> Reproducibility_ResNet50;
+TEST_P(Reproducibility_ResNet50, Accuracy)
 {
     Net net = readNetFromCaffe(findDataFile("dnn/ResNet-50-deploy.prototxt", false),
                                findDataFile("dnn/ResNet-50-model.caffemodel", false));
 
-    net.setPreferableBackend(DNN_BACKEND_DEFAULT);
-    net.setPreferableTarget(DNN_TARGET_OPENCL);
+    int targetId = GetParam();
+    net.setPreferableTarget(targetId);
 
     Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(224,224), Scalar(), false);
     ASSERT_TRUE(!input.empty());
@@ -300,6 +235,8 @@ OCL_TEST(Reproducibility_ResNet50, Accuracy)
     Mat ref = blobFromNPY(_tf("resnet50_prob.npy"));
     normAssert(ref, out);
 
+    if (targetId == DNN_TARGET_OPENCL)
+    {
         UMat out_umat;
         net.forward(out_umat);
         normAssert(ref, out_umat, "out_umat");
@@ -307,45 +244,37 @@ OCL_TEST(Reproducibility_ResNet50, Accuracy)
         std::vector<UMat> out_umats;
         net.forward(out_umats);
         normAssert(ref, out_umats[0], "out_umat_vector");
+    }
 }
+INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_ResNet50, availableDnnTargets());
 
-TEST(Reproducibility_SqueezeNet_v1_1, Accuracy)
-{
-    Net net = readNetFromCaffe(findDataFile("dnn/squeezenet_v1.1.prototxt", false),
-                               findDataFile("dnn/squeezenet_v1.1.caffemodel", false));
-
-    Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(227,227), Scalar(), false);
-    ASSERT_TRUE(!input.empty());
-
-    net.setInput(input);
-    Mat out = net.forward();
-
-    Mat ref = blobFromNPY(_tf("squeezenet_v1.1_prob.npy"));
-    normAssert(ref, out);
-}
-
-OCL_TEST(Reproducibility_SqueezeNet_v1_1, Accuracy)
+typedef testing::TestWithParam<DNNTarget> Reproducibility_SqueezeNet_v1_1;
+TEST_P(Reproducibility_SqueezeNet_v1_1, Accuracy)
 {
     Net net = readNetFromCaffe(findDataFile("dnn/squeezenet_v1.1.prototxt", false),
                                findDataFile("dnn/squeezenet_v1.1.caffemodel", false));
 
-    net.setPreferableBackend(DNN_BACKEND_DEFAULT);
-    net.setPreferableTarget(DNN_TARGET_OPENCL);
+    int targetId = GetParam();
+    net.setPreferableTarget(targetId);
 
     Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(227,227), Scalar(), false);
     ASSERT_TRUE(!input.empty());
 
+    Mat out;
+    if (targetId == DNN_TARGET_OPENCL)
+    {
         // Firstly set a wrong input blob and run the model to receive a wrong output.
-    net.setInput(input * 2.0f);
-    Mat out = net.forward();
-
         // Then set a correct input blob to check CPU->GPU synchronization is working well.
+        net.setInput(input * 2.0f);
+        out = net.forward();
+    }
     net.setInput(input);
     out = net.forward();
 
     Mat ref = blobFromNPY(_tf("squeezenet_v1.1_prob.npy"));
     normAssert(ref, out);
 }
+INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_SqueezeNet_v1_1, availableDnnTargets());
 
 TEST(Reproducibility_AlexNet_fp16, Accuracy)
 {
@@ -456,7 +385,6 @@ TEST(Test_Caffe, multiple_inputs)
     normAssert(out, first_image + second_image);
 }
 
-CV_ENUM(DNNTarget, DNN_TARGET_CPU, DNN_TARGET_OPENCL)
 typedef testing::TestWithParam<tuple<std::string, DNNTarget> > opencv_face_detector;
 TEST_P(opencv_face_detector, Accuracy)
 {

modules/dnn/test/test_googlenet.cpp

@@ -77,6 +77,10 @@ OCL_TEST(Reproducibility_GoogLeNet, Accuracy)
     net.setPreferableBackend(DNN_BACKEND_DEFAULT);
     net.setPreferableTarget(DNN_TARGET_OPENCL);
 
+    // Initialize network for a single image in the batch but test with batch size=2.
+    net.setInput(blobFromImage(Mat(224, 224, CV_8UC3)));
+    net.forward();
+
     std::vector<Mat> inpMats;
     inpMats.push_back( imread(_tf("googlenet_0.png")) );
     inpMats.push_back( imread(_tf("googlenet_1.png")) );

modules/dnn/test/test_precomp.hpp

@@ -44,12 +44,31 @@
 #include "opencv2/ts.hpp"
 #include "opencv2/ts/ts_perf.hpp"
 #include "opencv2/core/utility.hpp"
+#include "opencv2/core/ocl.hpp"
 
 #include "opencv2/dnn.hpp"
 #include "test_common.hpp"
 
 namespace opencv_test {
 using namespace cv::dnn;
+
+CV_ENUM(DNNBackend, DNN_BACKEND_DEFAULT, DNN_BACKEND_HALIDE, DNN_BACKEND_INFERENCE_ENGINE)
+CV_ENUM(DNNTarget, DNN_TARGET_CPU, DNN_TARGET_OPENCL)
+
+static testing::internal::ParamGenerator<DNNTarget> availableDnnTargets()
+{
+    static std::vector<DNNTarget> targets;
+    if (targets.empty())
+    {
+        targets.push_back(DNN_TARGET_CPU);
+#ifdef HAVE_OPENCL
+        if (cv::ocl::useOpenCL())
+            targets.push_back(DNN_TARGET_OPENCL);
+#endif
+    }
+    return testing::ValuesIn(targets);
+}
+
 }
 
 #endif

modules/dnn/test/test_tf_importer.cpp

@@ -11,8 +11,6 @@ Test for Tensorflow models loading
 
 #include "test_precomp.hpp"
 #include "npy_blob.hpp"
-#include <opencv2/core/ocl.hpp>
-#include <opencv2/ts/ocl_test.hpp>
 
 namespace opencv_test
 {
@@ -115,118 +113,85 @@ static void runTensorFlowNet(const std::string& prefix, int targetId = DNN_TARGE
     normAssert(target, output, "", l1, lInf);
 }
 
-TEST(Test_TensorFlow, conv)
-{
-    runTensorFlowNet("single_conv");
-    runTensorFlowNet("atrous_conv2d_valid");
-    runTensorFlowNet("atrous_conv2d_same");
-    runTensorFlowNet("depthwise_conv2d");
-}
+typedef testing::TestWithParam<DNNTarget> Test_TensorFlow_layers;
 
-TEST(Test_TensorFlow, padding)
+TEST_P(Test_TensorFlow_layers, conv)
 {
-    runTensorFlowNet("padding_same");
-    runTensorFlowNet("padding_valid");
-    runTensorFlowNet("spatial_padding");
+    int targetId = GetParam();
+    runTensorFlowNet("single_conv", targetId);
+    runTensorFlowNet("atrous_conv2d_valid", targetId);
+    runTensorFlowNet("atrous_conv2d_same", targetId);
+    runTensorFlowNet("depthwise_conv2d", targetId);
 }
 
-TEST(Test_TensorFlow, eltwise_add_mul)
+TEST_P(Test_TensorFlow_layers, padding)
 {
-    runTensorFlowNet("eltwise_add_mul");
+    int targetId = GetParam();
+    runTensorFlowNet("padding_same", targetId);
+    runTensorFlowNet("padding_valid", targetId);
+    runTensorFlowNet("spatial_padding", targetId);
 }
 
-OCL_TEST(Test_TensorFlow, eltwise_add_mul)
+TEST_P(Test_TensorFlow_layers, eltwise_add_mul)
 {
-    runTensorFlowNet("eltwise_add_mul", DNN_TARGET_OPENCL);
+    runTensorFlowNet("eltwise_add_mul", GetParam());
 }
 
-TEST(Test_TensorFlow, pad_and_concat)
+TEST_P(Test_TensorFlow_layers, pad_and_concat)
 {
-    runTensorFlowNet("pad_and_concat");
+    runTensorFlowNet("pad_and_concat", GetParam());
 }
 
-TEST(Test_TensorFlow, batch_norm)
+TEST_P(Test_TensorFlow_layers, batch_norm)
 {
-    runTensorFlowNet("batch_norm");
-    runTensorFlowNet("fused_batch_norm");
-    runTensorFlowNet("batch_norm_text", DNN_TARGET_CPU, true);
-    runTensorFlowNet("mvn_batch_norm");
-    runTensorFlowNet("mvn_batch_norm_1x1");
+    int targetId = GetParam();
+    runTensorFlowNet("batch_norm", targetId);
+    runTensorFlowNet("fused_batch_norm", targetId);
+    runTensorFlowNet("batch_norm_text", targetId, true);
+    runTensorFlowNet("mvn_batch_norm", targetId);
+    runTensorFlowNet("mvn_batch_norm_1x1", targetId);
 }
 
-OCL_TEST(Test_TensorFlow, batch_norm)
+TEST_P(Test_TensorFlow_layers, pooling)
 {
-    runTensorFlowNet("batch_norm", DNN_TARGET_OPENCL);
-    runTensorFlowNet("fused_batch_norm", DNN_TARGET_OPENCL);
-    runTensorFlowNet("batch_norm_text", DNN_TARGET_OPENCL, true);
+    int targetId = GetParam();
+    runTensorFlowNet("max_pool_even", targetId);
+    runTensorFlowNet("max_pool_odd_valid", targetId);
+    runTensorFlowNet("ave_pool_same", targetId);
+    runTensorFlowNet("max_pool_odd_same", targetId);
 }
 
-TEST(Test_TensorFlow, pooling)
+TEST_P(Test_TensorFlow_layers, deconvolution)
 {
-    runTensorFlowNet("max_pool_even");
-    runTensorFlowNet("max_pool_odd_valid");
-    runTensorFlowNet("max_pool_odd_same");
-    runTensorFlowNet("ave_pool_same");
+    int targetId = GetParam();
+    runTensorFlowNet("deconvolution", targetId);
+    runTensorFlowNet("deconvolution_same", targetId);
+    runTensorFlowNet("deconvolution_stride_2_same", targetId);
+    runTensorFlowNet("deconvolution_adj_pad_valid", targetId);
+    runTensorFlowNet("deconvolution_adj_pad_same", targetId);
 }
 
-TEST(Test_TensorFlow, deconvolution)
+TEST_P(Test_TensorFlow_layers, matmul)
 {
-    runTensorFlowNet("deconvolution");
-    runTensorFlowNet("deconvolution_same");
-    runTensorFlowNet("deconvolution_stride_2_same");
-    runTensorFlowNet("deconvolution_adj_pad_valid");
-    runTensorFlowNet("deconvolution_adj_pad_same");
+    int targetId = GetParam();
+    runTensorFlowNet("matmul", targetId);
+    runTensorFlowNet("nhwc_reshape_matmul", targetId);
+    runTensorFlowNet("nhwc_transpose_reshape_matmul", targetId);
 }
 
-OCL_TEST(Test_TensorFlow, deconvolution)
+TEST_P(Test_TensorFlow_layers, reshape)
 {
-    runTensorFlowNet("deconvolution", DNN_TARGET_OPENCL);
-    runTensorFlowNet("deconvolution_same", DNN_TARGET_OPENCL);
-    runTensorFlowNet("deconvolution_stride_2_same", DNN_TARGET_OPENCL);
-    runTensorFlowNet("deconvolution_adj_pad_valid", DNN_TARGET_OPENCL);
-    runTensorFlowNet("deconvolution_adj_pad_same", DNN_TARGET_OPENCL);
+    int targetId = GetParam();
+    runTensorFlowNet("shift_reshape_no_reorder", targetId);
+    runTensorFlowNet("reshape_reduce", targetId);
+    runTensorFlowNet("flatten", targetId, true);
 }
 
-TEST(Test_TensorFlow, matmul)
-{
-    runTensorFlowNet("matmul");
-    runTensorFlowNet("nhwc_reshape_matmul");
-    runTensorFlowNet("nhwc_transpose_reshape_matmul");
-}
+INSTANTIATE_TEST_CASE_P(/**/, Test_TensorFlow_layers, availableDnnTargets());
 
-TEST(Test_TensorFlow, defun)
-{
-    runTensorFlowNet("defun_dropout");
-}
+typedef testing::TestWithParam<DNNTarget> Test_TensorFlow_nets;
 
-TEST(Test_TensorFlow, reshape)
-{
-    runTensorFlowNet("shift_reshape_no_reorder");
-    runTensorFlowNet("reshape_reduce");
-    runTensorFlowNet("flatten", DNN_TARGET_CPU, true);
-}
-
-TEST(Test_TensorFlow, fp16)
-{
-    const float l1 = 1e-3;
-    const float lInf = 1e-2;
-    runTensorFlowNet("fp16_single_conv", DNN_TARGET_CPU, false, l1, lInf);
-    runTensorFlowNet("fp16_deconvolution", DNN_TARGET_CPU, false, l1, lInf);
-    runTensorFlowNet("fp16_max_pool_odd_same", DNN_TARGET_CPU, false, l1, lInf);
-    runTensorFlowNet("fp16_padding_valid", DNN_TARGET_CPU, false, l1, lInf);
-    runTensorFlowNet("fp16_eltwise_add_mul", DNN_TARGET_CPU, false, l1, lInf);
-    runTensorFlowNet("fp16_max_pool_odd_valid", DNN_TARGET_CPU, false, l1, lInf);
-    runTensorFlowNet("fp16_pad_and_concat", DNN_TARGET_CPU, false, l1, lInf);
-    runTensorFlowNet("fp16_max_pool_even", DNN_TARGET_CPU, false, l1, lInf);
-    runTensorFlowNet("fp16_padding_same", DNN_TARGET_CPU, false, l1, lInf);
-}
-
-TEST(Test_TensorFlow, quantized)
-{
-    runTensorFlowNet("uint8_single_conv");
-}
-
-TEST(Test_TensorFlow, MobileNet_SSD)
+TEST_P(Test_TensorFlow_nets, MobileNet_SSD)
 {
     std::string netPath = findDataFile("dnn/ssd_mobilenet_v1_coco.pb", false);
     std::string netConfig = findDataFile("dnn/ssd_mobilenet_v1_coco.pbtxt", false);
@@ -249,17 +214,20 @@ TEST(Test_TensorFlow, MobileNet_SSD)
     }
 
     Net net = readNetFromTensorflow(netPath, netConfig);
+
+    net.setPreferableTarget(GetParam());
+
     net.setInput(inp);
 
     std::vector<Mat> output;
     net.forward(output, outNames);
 
-    normAssert(target[0].reshape(1, 1), output[0].reshape(1, 1));
+    normAssert(target[0].reshape(1, 1), output[0].reshape(1, 1), "", 1e-5, 1.5e-4);
     normAssert(target[1].reshape(1, 1), output[1].reshape(1, 1), "", 1e-5, 3e-4);
     normAssert(target[2].reshape(1, 1), output[2].reshape(1, 1), "", 4e-5, 1e-2);
 }
 
-TEST(Test_TensorFlow, Inception_v2_SSD)
+TEST_P(Test_TensorFlow_nets, Inception_v2_SSD)
 {
     std::string proto = findDataFile("dnn/ssd_inception_v2_coco_2017_11_17.pbtxt", false);
     std::string model = findDataFile("dnn/ssd_inception_v2_coco_2017_11_17.pb", false);
@@ -268,6 +236,8 @@ TEST(Test_TensorFlow, Inception_v2_SSD)
     Mat img = imread(findDataFile("dnn/street.png", false));
     Mat blob = blobFromImage(img, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), true, false);
 
+    net.setPreferableTarget(GetParam());
+
     net.setInput(blob);
     // Output has shape 1x1xNx7 where N - number of detections.
     // An every detection is a vector of values [id, classId, confidence, left, top, right, bottom]
@@ -289,74 +259,57 @@ TEST(Test_TensorFlow, Inception_v2_SSD)
     normAssert(detections, ref);
 }
 
-OCL_TEST(Test_TensorFlow, MobileNet_SSD)
-{
-    std::string netPath = findDataFile("dnn/ssd_mobilenet_v1_coco.pb", false);
-    std::string netConfig = findDataFile("dnn/ssd_mobilenet_v1_coco.pbtxt", false);
-    std::string imgPath = findDataFile("dnn/street.png", false);
-
-    Mat inp;
-    resize(imread(imgPath), inp, Size(300, 300));
-    inp = blobFromImage(inp, 1.0f / 127.5, Size(), Scalar(127.5, 127.5, 127.5), true);
-
-    std::vector<String> outNames(3);
-    outNames[0] = "concat";
-    outNames[1] = "concat_1";
-    outNames[2] = "detection_out";
-
-    std::vector<Mat> target(outNames.size());
-    for (int i = 0; i < outNames.size(); ++i)
-    {
-        std::string path = findDataFile("dnn/tensorflow/ssd_mobilenet_v1_coco." + outNames[i] + ".npy", false);
-        target[i] = blobFromNPY(path);
-    }
-
-    Net net = readNetFromTensorflow(netPath, netConfig);
-
-    net.setPreferableBackend(DNN_BACKEND_DEFAULT);
-    net.setPreferableTarget(DNN_TARGET_OPENCL);
-
-    net.setInput(inp);
-
-    std::vector<Mat> output;
-    net.forward(output, outNames);
-
-    normAssert(target[0].reshape(1, 1), output[0].reshape(1, 1), "", 1e-5, 1.5e-4);
-    normAssert(target[1].reshape(1, 1), output[1].reshape(1, 1), "", 1e-5, 3e-4);
-    normAssert(target[2].reshape(1, 1), output[2].reshape(1, 1), "", 4e-5, 1e-2);
-}
-
-OCL_TEST(Test_TensorFlow, Inception_v2_SSD)
+TEST_P(Test_TensorFlow_nets, opencv_face_detector_uint8)
 {
-    std::string proto = findDataFile("dnn/ssd_inception_v2_coco_2017_11_17.pbtxt", false);
-    std::string model = findDataFile("dnn/ssd_inception_v2_coco_2017_11_17.pb", false);
+    std::string proto = findDataFile("dnn/opencv_face_detector.pbtxt", false);
+    std::string model = findDataFile("dnn/opencv_face_detector_uint8.pb", false);
 
     Net net = readNetFromTensorflow(model, proto);
-    Mat img = imread(findDataFile("dnn/street.png", false));
-    Mat blob = blobFromImage(img, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), true, false);
+    Mat img = imread(findDataFile("gpu/lbpcascade/er.png", false));
+    Mat blob = blobFromImage(img, 1.0, Size(), Scalar(104.0, 177.0, 123.0), false, false);
 
-    net.setPreferableBackend(DNN_BACKEND_DEFAULT);
-    net.setPreferableTarget(DNN_TARGET_OPENCL);
+    net.setPreferableTarget(GetParam());
 
     net.setInput(blob);
     // Output has shape 1x1xNx7 where N - number of detections.
     // An every detection is a vector of values [id, classId, confidence, left, top, right, bottom]
     Mat out = net.forward();
-    out = out.reshape(1, out.total() / 7);
 
-    Mat detections;
-    for (int i = 0; i < out.rows; ++i)
-    {
-        if (out.at<float>(i, 2) > 0.5)
-          detections.push_back(out.row(i).colRange(1, 7));
-    }
+    // References are from test for Caffe model.
+    Mat ref = (Mat_<float>(6, 5) << 0.99520785, 0.80997437, 0.16379407, 0.87996572, 0.26685631,
+                                    0.9934696, 0.2831718, 0.50738752, 0.345781, 0.5985168,
+                                    0.99096733, 0.13629119, 0.24892329, 0.19756334, 0.3310290,
+                                    0.98977017, 0.23901358, 0.09084064, 0.29902688, 0.1769477,
+                                    0.97203469, 0.67965847, 0.06876482, 0.73999709, 0.1513494,
+                                    0.95097077, 0.51901293, 0.45863652, 0.5777427, 0.5347801);
+    normAssert(out.reshape(1, out.total() / 7).rowRange(0, 6).colRange(2, 7), ref, "", 2.8e-4, 3.4e-3);
+}
 
-    Mat ref = (Mat_<float>(5, 6) << 1, 0.90176028, 0.19872092, 0.36311883, 0.26461923, 0.63498729,
-                                    3, 0.93569964, 0.64865261, 0.45906419, 0.80675775, 0.65708131,
-                                    3, 0.75838411, 0.44668293, 0.45907149, 0.49459291, 0.52197015,
-                                    10, 0.95932811, 0.38349164, 0.32528657, 0.40387636, 0.39165527,
-                                    10, 0.93973452, 0.66561931, 0.37841269, 0.68074018, 0.42907384);
-    normAssert(detections, ref);
+INSTANTIATE_TEST_CASE_P(/**/, Test_TensorFlow_nets, availableDnnTargets());
+
+TEST(Test_TensorFlow, defun)
+{
+    runTensorFlowNet("defun_dropout");
+}
+
+TEST(Test_TensorFlow, fp16)
+{
+    const float l1 = 1e-3;
+    const float lInf = 1e-2;
+    runTensorFlowNet("fp16_single_conv", DNN_TARGET_CPU, false, l1, lInf);
+    runTensorFlowNet("fp16_deconvolution", DNN_TARGET_CPU, false, l1, lInf);
+    runTensorFlowNet("fp16_max_pool_odd_same", DNN_TARGET_CPU, false, l1, lInf);
+    runTensorFlowNet("fp16_padding_valid", DNN_TARGET_CPU, false, l1, lInf);
+    runTensorFlowNet("fp16_eltwise_add_mul", DNN_TARGET_CPU, false, l1, lInf);
+    runTensorFlowNet("fp16_max_pool_odd_valid", DNN_TARGET_CPU, false, l1, lInf);
+    runTensorFlowNet("fp16_pad_and_concat", DNN_TARGET_CPU, false, l1, lInf);
+    runTensorFlowNet("fp16_max_pool_even", DNN_TARGET_CPU, false, l1, lInf);
+    runTensorFlowNet("fp16_padding_same", DNN_TARGET_CPU, false, l1, lInf);
+}
+
+TEST(Test_TensorFlow, quantized)
+{
+    runTensorFlowNet("uint8_single_conv");
 }
 
 TEST(Test_TensorFlow, lstm)
@@ -390,28 +343,4 @@ TEST(Test_TensorFlow, memory_read)
     runTensorFlowNet("batch_norm_text", DNN_TARGET_CPU, true, l1, lInf, true);
 }
 
-TEST(Test_TensorFlow, opencv_face_detector_uint8)
-{
-    std::string proto = findDataFile("dnn/opencv_face_detector.pbtxt", false);
-    std::string model = findDataFile("dnn/opencv_face_detector_uint8.pb", false);
-
-    Net net = readNetFromTensorflow(model, proto);
-    Mat img = imread(findDataFile("gpu/lbpcascade/er.png", false));
-    Mat blob = blobFromImage(img, 1.0, Size(), Scalar(104.0, 177.0, 123.0), false, false);
-
-    net.setInput(blob);
-    // Output has shape 1x1xNx7 where N - number of detections.
-    // An every detection is a vector of values [id, classId, confidence, left, top, right, bottom]
-    Mat out = net.forward();
-
-    // References are from test for Caffe model.
-    Mat ref = (Mat_<float>(6, 5) << 0.99520785, 0.80997437, 0.16379407, 0.87996572, 0.26685631,
-                                    0.9934696, 0.2831718, 0.50738752, 0.345781, 0.5985168,
-                                    0.99096733, 0.13629119, 0.24892329, 0.19756334, 0.3310290,
-                                    0.98977017, 0.23901358, 0.09084064, 0.29902688, 0.1769477,
-                                    0.97203469, 0.67965847, 0.06876482, 0.73999709, 0.1513494,
-                                    0.95097077, 0.51901293, 0.45863652, 0.5777427, 0.5347801);
-    normAssert(out.reshape(1, out.total() / 7).rowRange(0, 6).colRange(2, 7), ref, "", 2.8e-4, 3.4e-3);
-}
-
 }

modules/dnn/test/test_torch_importer.cpp

@@ -42,7 +42,6 @@
 #include "test_precomp.hpp"
 #include "npy_blob.hpp"
 #include <opencv2/dnn/shape_utils.hpp>
-#include <opencv2/ts/ocl_test.hpp>
 
 namespace opencv_test
 {
@@ -100,219 +99,122 @@ static void runTorchNet(String prefix, int targetId = DNN_TARGET_CPU, String out
     }
 }
 
-TEST(Torch_Importer, run_convolution)
-{
-    runTorchNet("net_conv");
-}
-
-OCL_TEST(Torch_Importer, run_convolution)
-{
-    runTorchNet("net_conv", DNN_TARGET_OPENCL);
-}
+typedef testing::TestWithParam<DNNTarget> Test_Torch_layers;
 
-TEST(Torch_Importer, run_pool_max)
+TEST_P(Test_Torch_layers, run_convolution)
 {
-    runTorchNet("net_pool_max", DNN_TARGET_CPU, "", true);
+    runTorchNet("net_conv", GetParam());
 }
 
-OCL_TEST(Torch_Importer, run_pool_max)
+TEST_P(Test_Torch_layers, run_pool_max)
 {
-    runTorchNet("net_pool_max", DNN_TARGET_OPENCL, "", true);
+    runTorchNet("net_pool_max", GetParam(), "", true);
 }
 
-TEST(Torch_Importer, run_pool_ave)
+TEST_P(Test_Torch_layers, run_pool_ave)
 {
-    runTorchNet("net_pool_ave");
+    runTorchNet("net_pool_ave", GetParam());
 }
 
-OCL_TEST(Torch_Importer, run_pool_ave)
+TEST_P(Test_Torch_layers, run_reshape)
 {
-    runTorchNet("net_pool_ave", DNN_TARGET_OPENCL);
+    int targetId = GetParam();
+    runTorchNet("net_reshape", targetId);
+    runTorchNet("net_reshape_batch", targetId);
+    runTorchNet("net_reshape_single_sample", targetId);
+    runTorchNet("net_reshape_channels", targetId, "", false, true);
 }
 
-TEST(Torch_Importer, run_reshape)
+TEST_P(Test_Torch_layers, run_linear)
 {
-    runTorchNet("net_reshape");
-    runTorchNet("net_reshape_batch");
-    runTorchNet("net_reshape_single_sample");
-    runTorchNet("net_reshape_channels", DNN_TARGET_CPU, "", false, true);
+    runTorchNet("net_linear_2d", GetParam());
 }
 
-TEST(Torch_Importer, run_linear)
+TEST_P(Test_Torch_layers, run_concat)
 {
-    runTorchNet("net_linear_2d");
+    int targetId = GetParam();
+    runTorchNet("net_concat", targetId, "l5_torchMerge");
+    runTorchNet("net_depth_concat", targetId, "", false, true);
 }
 
-TEST(Torch_Importer, run_paralel)
+TEST_P(Test_Torch_layers, run_deconv)
 {
-    runTorchNet("net_parallel", DNN_TARGET_CPU, "l5_torchMerge");
+    runTorchNet("net_deconv", GetParam());
 }
 
-TEST(Torch_Importer, run_concat)
+TEST_P(Test_Torch_layers, run_batch_norm)
 {
-    runTorchNet("net_concat", DNN_TARGET_CPU, "l5_torchMerge");
-    runTorchNet("net_depth_concat", DNN_TARGET_CPU, "", false, true);
+    runTorchNet("net_batch_norm", GetParam(), "", false, true);
 }
 
-OCL_TEST(Torch_Importer, run_concat)
+TEST_P(Test_Torch_layers, net_prelu)
 {
-    runTorchNet("net_concat", DNN_TARGET_OPENCL, "l5_torchMerge");
-    runTorchNet("net_depth_concat", DNN_TARGET_OPENCL, "", false, true);
+    runTorchNet("net_prelu", GetParam());
 }
 
-TEST(Torch_Importer, run_deconv)
+TEST_P(Test_Torch_layers, net_cadd_table)
 {
-    runTorchNet("net_deconv");
+    runTorchNet("net_cadd_table", GetParam());
 }
 
-OCL_TEST(Torch_Importer, run_deconv)
+TEST_P(Test_Torch_layers, net_softmax)
 {
-    runTorchNet("net_deconv", DNN_TARGET_OPENCL);
+    int targetId = GetParam();
+    runTorchNet("net_softmax", targetId);
+    runTorchNet("net_softmax_spatial", targetId);
 }
 
-TEST(Torch_Importer, run_batch_norm)
-{
-    runTorchNet("net_batch_norm", DNN_TARGET_CPU, "", false, true);
-}
-
-OCL_TEST(Torch_Importer, run_batch_norm)
-{
-    runTorchNet("net_batch_norm", DNN_TARGET_OPENCL, "", false, true);
-}
-
-TEST(Torch_Importer, net_prelu)
-{
-    runTorchNet("net_prelu");
-}
-
-TEST(Torch_Importer, net_cadd_table)
-{
-    runTorchNet("net_cadd_table");
-}
-
-TEST(Torch_Importer, net_softmax)
-{
-    runTorchNet("net_softmax");
-    runTorchNet("net_softmax_spatial");
-}
-
-OCL_TEST(Torch_Importer, net_softmax)
-{
-    runTorchNet("net_softmax", DNN_TARGET_OPENCL);
-    runTorchNet("net_softmax_spatial", DNN_TARGET_OPENCL);
-}
-
-TEST(Torch_Importer, net_logsoftmax)
+TEST_P(Test_Torch_layers, net_logsoftmax)
 {
     runTorchNet("net_logsoftmax");
     runTorchNet("net_logsoftmax_spatial");
 }
 
-OCL_TEST(Torch_Importer, net_logsoftmax)
+TEST_P(Test_Torch_layers, net_lp_pooling)
 {
-    runTorchNet("net_logsoftmax", DNN_TARGET_OPENCL);
-    runTorchNet("net_logsoftmax_spatial", DNN_TARGET_OPENCL);
+    int targetId = GetParam();
+    runTorchNet("net_lp_pooling_square", targetId, "", false, true);
+    runTorchNet("net_lp_pooling_power", targetId, "", false, true);
 }
 
-TEST(Torch_Importer, net_lp_pooling)
+TEST_P(Test_Torch_layers, net_conv_gemm_lrn)
 {
-    runTorchNet("net_lp_pooling_square", DNN_TARGET_CPU, "", false, true);
-    runTorchNet("net_lp_pooling_power", DNN_TARGET_CPU, "", false, true);
+    runTorchNet("net_conv_gemm_lrn", GetParam(), "", false, true);
 }
 
-TEST(Torch_Importer, net_conv_gemm_lrn)
+TEST_P(Test_Torch_layers, net_inception_block)
 {
-    runTorchNet("net_conv_gemm_lrn", DNN_TARGET_CPU, "", false, true);
+    runTorchNet("net_inception_block", GetParam(), "", false, true);
 }
 
-TEST(Torch_Importer, net_inception_block)
+TEST_P(Test_Torch_layers, net_normalize)
 {
-    runTorchNet("net_inception_block", DNN_TARGET_CPU, "", false, true);
+    runTorchNet("net_normalize", GetParam(), "", false, true);
 }
 
-TEST(Torch_Importer, net_normalize)
+TEST_P(Test_Torch_layers, net_padding)
 {
-    runTorchNet("net_normalize", DNN_TARGET_CPU, "", false, true);
+    int targetId = GetParam();
+    runTorchNet("net_padding", targetId, "", false, true);
+    runTorchNet("net_spatial_zero_padding", targetId, "", false, true);
+    runTorchNet("net_spatial_reflection_padding", targetId, "", false, true);
 }
 
-OCL_TEST(Torch_Importer, net_normalize)
+TEST_P(Test_Torch_layers, net_non_spatial)
 {
-    runTorchNet("net_normalize", DNN_TARGET_OPENCL, "", false, true);
-}
-
-TEST(Torch_Importer, net_padding)
-{
-    runTorchNet("net_padding", DNN_TARGET_CPU, "", false, true);
-    runTorchNet("net_spatial_zero_padding", DNN_TARGET_CPU, "", false, true);
-    runTorchNet("net_spatial_reflection_padding", DNN_TARGET_CPU, "", false, true);
-}
-
-TEST(Torch_Importer, net_non_spatial)
-{
-    runTorchNet("net_non_spatial", DNN_TARGET_CPU, "", false, true);
-}
-
-OCL_TEST(Torch_Importer, net_non_spatial)
-{
-    runTorchNet("net_non_spatial", DNN_TARGET_OPENCL, "", false, true);
-}
-
-TEST(Torch_Importer, ENet_accuracy)
-{
-    Net net;
-    {
-        const string model = findDataFile("dnn/Enet-model-best.net", false);
-        net = readNetFromTorch(model, true);
-        ASSERT_FALSE(net.empty());
-    }
-
-    Mat sample = imread(_tf("street.png", false));
-    Mat inputBlob = blobFromImage(sample, 1./255);
-
-    net.setInput(inputBlob, "");
-    Mat out = net.forward();
-    Mat ref = blobFromNPY(_tf("torch_enet_prob.npy", false));
-    // Due to numerical instability in Pooling-Unpooling layers (indexes jittering)
-    // thresholds for ENet must be changed. Accuracy of resuults was checked on
-    // Cityscapes dataset and difference in mIOU with Torch is 10E-4%
-    normAssert(ref, out, "", 0.00044, 0.44);
-
-    const int N = 3;
-    for (int i = 0; i < N; i++)
-    {
-        net.setInput(inputBlob, "");
-        Mat out = net.forward();
-        normAssert(ref, out, "", 0.00044, 0.44);
-    }
+    runTorchNet("net_non_spatial", GetParam(), "", false, true);
 }
 
-TEST(Torch_Importer, OpenFace_accuracy)
-{
-    const string model = findDataFile("dnn/openface_nn4.small2.v1.t7", false);
-    Net net = readNetFromTorch(model);
+INSTANTIATE_TEST_CASE_P(/**/, Test_Torch_layers, availableDnnTargets());
 
-    Mat sample = imread(findDataFile("cv/shared/lena.png", false));
-    Mat sampleF32(sample.size(), CV_32FC3);
-    sample.convertTo(sampleF32, sampleF32.type());
-    sampleF32 /= 255;
-    resize(sampleF32, sampleF32, Size(96, 96), 0, 0, INTER_NEAREST);
-
-    Mat inputBlob = blobFromImage(sampleF32);
+typedef testing::TestWithParam<DNNTarget> Test_Torch_nets;
 
-    net.setInput(inputBlob);
-    Mat out = net.forward();
-
-    Mat outRef = readTorchBlob(_tf("net_openface_output.dat"), true);
-    normAssert(out, outRef);
-}
-
-OCL_TEST(Torch_Importer, OpenFace_accuracy)
+TEST_P(Test_Torch_nets, OpenFace_accuracy)
 {
     const string model = findDataFile("dnn/openface_nn4.small2.v1.t7", false);
     Net net = readNetFromTorch(model);
 
-    net.setPreferableBackend(DNN_BACKEND_DEFAULT);
-    net.setPreferableTarget(DNN_TARGET_OPENCL);
+    net.setPreferableTarget(GetParam());
 
     Mat sample = imread(findDataFile("cv/shared/lena.png", false));
     Mat sampleF32(sample.size(), CV_32FC3);
@@ -329,7 +231,7 @@ OCL_TEST(Torch_Importer, OpenFace_accuracy)
     normAssert(out, outRef);
 }
 
-OCL_TEST(Torch_Importer, ENet_accuracy)
+TEST_P(Test_Torch_nets, ENet_accuracy)
 {
     Net net;
     {
@@ -338,8 +240,7 @@ OCL_TEST(Torch_Importer, ENet_accuracy)
         ASSERT_TRUE(!net.empty());
     }
 
-    net.setPreferableBackend(DNN_BACKEND_DEFAULT);
-    net.setPreferableTarget(DNN_TARGET_OPENCL);
+    net.setPreferableTarget(GetParam());
 
     Mat sample = imread(_tf("street.png", false));
     Mat inputBlob = blobFromImage(sample, 1./255);
@@ -374,7 +275,7 @@ OCL_TEST(Torch_Importer, ENet_accuracy)
 //   -median_filter 0 \
 //   -image_size 0 \
 //   -model models/instance_norm/feathers.t7
-TEST(Torch_Importer, FastNeuralStyle_accuracy)
+TEST_P(Test_Torch_nets, FastNeuralStyle_accuracy)
 {
     std::string models[] = {"dnn/fast_neural_style_eccv16_starry_night.t7",
                             "dnn/fast_neural_style_instance_norm_feathers.t7"};
@@ -385,6 +286,8 @@ TEST(Torch_Importer, FastNeuralStyle_accuracy)
         const string model = findDataFile(models[i], false);
         Net net = readNetFromTorch(model);
 
+        net.setPreferableTarget(GetParam());
+
         Mat img = imread(findDataFile("dnn/googlenet_1.png", false));
         Mat inputBlob = blobFromImage(img, 1.0, Size(), Scalar(103.939, 116.779, 123.68), false);
 
@@ -404,37 +307,17 @@ TEST(Torch_Importer, FastNeuralStyle_accuracy)
     }
 }
 
-OCL_TEST(Torch_Importer, FastNeuralStyle_accuracy)
-{
-    std::string models[] = {"dnn/fast_neural_style_eccv16_starry_night.t7",
-                            "dnn/fast_neural_style_instance_norm_feathers.t7"};
-    std::string targets[] = {"dnn/lena_starry_night.png", "dnn/lena_feathers.png"};
+INSTANTIATE_TEST_CASE_P(/**/, Test_Torch_nets, availableDnnTargets());
 
-    for (int i = 0; i < 2; ++i)
-    {
-        const string model = findDataFile(models[i], false);
-        Net net = readNetFromTorch(model);
-
-        net.setPreferableBackend(DNN_BACKEND_DEFAULT);
-        net.setPreferableTarget(DNN_TARGET_OPENCL);
-
-        Mat img = imread(findDataFile("dnn/googlenet_1.png", false));
-        Mat inputBlob = blobFromImage(img, 1.0, Size(), Scalar(103.939, 116.779, 123.68), false);
-
-        net.setInput(inputBlob);
-        Mat out = net.forward();
-
-        // Deprocessing.
-        getPlane(out, 0, 0) += 103.939;
-        getPlane(out, 0, 1) += 116.779;
-        getPlane(out, 0, 2) += 123.68;
-        out = cv::min(cv::max(0, out), 255);
-
-        Mat ref = imread(findDataFile(targets[i]));
-        Mat refBlob = blobFromImage(ref, 1.0, Size(), Scalar(), false);
+// TODO: fix OpenCL and add to the rest of tests
+TEST(Torch_Importer, run_paralel)
+{
+    runTorchNet("net_parallel", DNN_TARGET_CPU, "l5_torchMerge");
+}
 
-        normAssert(out, refBlob, "", 0.5, 1.1);
-    }
+TEST(Torch_Importer, DISABLED_run_paralel)
+{
+    runTorchNet("net_parallel", DNN_TARGET_OPENCL, "l5_torchMerge");
 }
 
 }