Merge pull request #17384 from dkurt:efficientdet

modules/dnn/perf/perf_net.cpp

@@ -235,6 +235,17 @@ PERF_TEST_P_(DNNTestNetwork, Inception_v2_Faster_RCNN)
                Mat(cv::Size(800, 600), CV_32FC3));
 }
 
+PERF_TEST_P_(DNNTestNetwork, EfficientDet)
+{
+    if (backend == DNN_BACKEND_HALIDE || target != DNN_TARGET_CPU)
+        throw SkipTestException("");
+    Mat sample = imread(findDataFile("dnn/dog416.png"));
+    resize(sample, sample, Size(512, 512));
+    Mat inp;
+    sample.convertTo(inp, CV_32FC3, 1.0/255);
+    processNet("dnn/efficientdet-d0.pb", "dnn/efficientdet-d0.pbtxt", "", inp);
+}
+
 INSTANTIATE_TEST_CASE_P(/*nothing*/, DNNTestNetwork, dnnBackendsAndTargets());
 
 } // namespace

modules/dnn/src/tensorflow/tf_importer.cpp

@@ -1542,22 +1542,32 @@ void TFImporter::populateNet(Net dstNet)
 
             connect(layer_id, dstNet, parsePin(layer.input(0)), id, 0);
         }
-        else if (type == "Mul")
+        else if (type == "Mul" || type == "RealDiv")
         {
-            bool haveConst = false;
-            for(int ii = 0; !haveConst && ii < layer.input_size(); ++ii)
+            int constId = -1;
+            for(int ii = 0; ii < layer.input_size(); ++ii)
             {
                 Pin input = parsePin(layer.input(ii));
-                haveConst = value_id.find(input.name) != value_id.end();
+                if (value_id.find(input.name) != value_id.end())
+                {
+                    constId = ii;
+                    break;
+                }
             }
-            CV_Assert(!haveConst || layer.input_size() == 2);
+            CV_Assert((constId != -1) || (layer.input_size() == 2));
 
-            if (haveConst)
+            if (constId != -1)
             {
                 // Multiplication by constant.
                 CV_Assert(layer.input_size() == 2);
                 Mat scaleMat = getTensorContent(getConstBlob(layer, value_id));
                 CV_Assert(scaleMat.type() == CV_32FC1);
+                if (type == "RealDiv")
+                {
+                    if (constId == 0)
+                        CV_Error(Error::StsNotImplemented, "Division of constant over variable");
+                    scaleMat = 1.0f / scaleMat;
+                }
 
                 int id;
                 if (scaleMat.total() == 1)  // is a scalar.
@@ -1659,11 +1669,15 @@ void TFImporter::populateNet(Net dstNet)
                 int id;
                 if (equalInpShapes || netInputShapes.empty())
                 {
-                    layerParams.set("operation", "prod");
+                    layerParams.set("operation", type == "RealDiv" ? "div" : "prod");
                     id = dstNet.addLayer(name, "Eltwise", layerParams);
                 }
                 else
+                {
+                    if (type == "RealDiv")
+                        CV_Error(Error::StsNotImplemented, "Division of non equal tensors");
                     id = dstNet.addLayer(name, "Scale", layerParams);
+                }
 
                 layer_id[name] = id;
 

modules/dnn/test/test_tf_importer.cpp

@@ -1128,4 +1128,37 @@ TEST_P(Test_TensorFlow_nets, Mask_RCNN)
         expectNoFallbacks(net);
 }
 
+TEST_P(Test_TensorFlow_nets, EfficientDet)
+{
+    if (target != DNN_TARGET_CPU)
+    {
+        if (target == DNN_TARGET_OPENCL_FP16) applyTestTag(CV_TEST_TAG_DNN_SKIP_OPENCL_FP16);
+        if (target == DNN_TARGET_OPENCL)      applyTestTag(CV_TEST_TAG_DNN_SKIP_OPENCL);
+        if (target == DNN_TARGET_MYRIAD)      applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD);
+    }
+    checkBackend();
+    std::string proto = findDataFile("dnn/efficientdet-d0.pbtxt");
+    std::string model = findDataFile("dnn/efficientdet-d0.pb");
+
+    Net net = readNetFromTensorflow(model, proto);
+    Mat img = imread(findDataFile("dnn/dog416.png"));
+    Mat blob = blobFromImage(img, 1.0/255, Size(512, 512), Scalar(123.675, 116.28, 103.53));
+
+    net.setPreferableBackend(backend);
+    net.setPreferableTarget(target);
+    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 TensorFlow model.
+    Mat ref = (Mat_<float>(3, 7) << 0, 1, 0.8437444, 0.153996080160141, 0.20534580945968628, 0.7463544607162476, 0.7414066195487976,
+                                    0, 17, 0.8245924, 0.16657517850399017, 0.3996818959712982, 0.4111558794975281, 0.9306337833404541,
+                                    0, 7, 0.8039304, 0.6118435263633728, 0.13175517320632935, 0.9065558314323425, 0.2943994700908661);
+    double scoreDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 4e-3 : 1e-5;
+    double iouDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 2e-3 : 1e-4;
+    normAssertDetections(ref, out, "", 0.5, scoreDiff, iouDiff);
+    expectNoFallbacksFromIE(net);
+}
+
 }