TEST_P(Test_TensorFlow_nets, 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.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(); // 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); }
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); 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); 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)); } 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); }
TEST_P(Test_TensorFlow_nets, opencv_face_detector_uint8) { checkBackend(); 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.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 Caffe model. Mat ref = (Mat_<float>(6, 7) << 0, 1, 0.99520785, 0.80997437, 0.16379407, 0.87996572, 0.26685631, 0, 1, 0.9934696, 0.2831718, 0.50738752, 0.345781, 0.5985168, 0, 1, 0.99096733, 0.13629119, 0.24892329, 0.19756334, 0.3310290, 0, 1, 0.98977017, 0.23901358, 0.09084064, 0.29902688, 0.1769477, 0, 1, 0.97203469, 0.67965847, 0.06876482, 0.73999709, 0.1513494, 0, 1, 0.95097077, 0.51901293, 0.45863652, 0.5777427, 0.5347801); double scoreDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 4e-3 : 3.4e-3; double iouDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.024 : 1e-2; normAssertDetections(ref, out, "", 0.9, scoreDiff, iouDiff); }
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); 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.setPreferableTarget(GetParam()); 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); }
TEST_P(Test_TensorFlow_nets, Faster_RCNN) { static std::string names[] = {"faster_rcnn_inception_v2_coco_2018_01_28", "faster_rcnn_resnet50_coco_2018_01_28"}; checkBackend(); if ((backend == DNN_BACKEND_INFERENCE_ENGINE && target != DNN_TARGET_CPU) || (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16)) throw SkipTestException(""); for (int i = 1; i < 2; ++i) { std::string proto = findDataFile("dnn/" + names[i] + ".pbtxt", false); std::string model = findDataFile("dnn/" + names[i] + ".pb", false); Net net = readNetFromTensorflow(model, proto); net.setPreferableBackend(backend); net.setPreferableTarget(target); Mat img = imread(findDataFile("dnn/dog416.png", false)); Mat blob = blobFromImage(img, 1.0f, Size(800, 600), Scalar(), true, false); net.setInput(blob); Mat out = net.forward(); Mat ref = blobFromNPY(findDataFile("dnn/tensorflow/" + names[i] + ".detection_out.npy")); normAssertDetections(ref, out, names[i].c_str(), 0.3); } }
TEST_P(Test_TensorFlow_nets, Inception_v2_SSD) { checkBackend(); 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); Net net = readNetFromTensorflow(model, proto); Mat img = imread(findDataFile("dnn/street.png", false)); Mat blob = blobFromImage(img, 1.0f, Size(300, 300), Scalar(), true, false); 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(); Mat ref = (Mat_<float>(5, 7) << 0, 1, 0.90176028, 0.19872092, 0.36311883, 0.26461923, 0.63498729, 0, 3, 0.93569964, 0.64865261, 0.45906419, 0.80675775, 0.65708131, 0, 3, 0.75838411, 0.44668293, 0.45907149, 0.49459291, 0.52197015, 0, 10, 0.95932811, 0.38349164, 0.32528657, 0.40387636, 0.39165527, 0, 10, 0.93973452, 0.66561931, 0.37841269, 0.68074018, 0.42907384); double scoreDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.0097 : default_l1; double iouDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.09 : default_lInf; normAssertDetections(ref, out, "", 0.5, scoreDiff, iouDiff); }
void runTensorFlowNet(const std::string& prefix, bool hasText = false, double l1 = 0.0, double lInf = 0.0, bool memoryLoad = false) { std::string netPath = path(prefix + "_net.pb"); std::string netConfig = (hasText ? path(prefix + "_net.pbtxt") : ""); std::string inpPath = path(prefix + "_in.npy"); std::string outPath = path(prefix + "_out.npy"); cv::Mat input = blobFromNPY(inpPath); cv::Mat ref = blobFromNPY(outPath); checkBackend(&input, &ref); Net net; if (memoryLoad) { // Load files into a memory buffers string dataModel; ASSERT_TRUE(readFileInMemory(netPath, dataModel)); string dataConfig; if (hasText) { ASSERT_TRUE(readFileInMemory(netConfig, dataConfig)); } net = readNetFromTensorflow(dataModel.c_str(), dataModel.size(), dataConfig.c_str(), dataConfig.size()); } else net = readNetFromTensorflow(netPath, netConfig); ASSERT_FALSE(net.empty()); net.setPreferableBackend(backend); net.setPreferableTarget(target); net.setInput(input); cv::Mat output = net.forward(); normAssert(ref, output, "", l1 ? l1 : default_l1, lInf ? lInf : default_lInf); }
TEST(Test_TensorFlow, Mask_RCNN) { std::string proto = findDataFile("dnn/mask_rcnn_inception_v2_coco_2018_01_28.pbtxt", false); std::string model = findDataFile("dnn/mask_rcnn_inception_v2_coco_2018_01_28.pb", false); Net net = readNetFromTensorflow(model, proto); Mat img = imread(findDataFile("dnn/street.png", false)); Mat refDetections = blobFromNPY(path("mask_rcnn_inception_v2_coco_2018_01_28.detection_out.npy")); Mat refMasks = blobFromNPY(path("mask_rcnn_inception_v2_coco_2018_01_28.detection_masks.npy")); Mat blob = blobFromImage(img, 1.0f, Size(800, 800), Scalar(), true, false); net.setPreferableBackend(DNN_BACKEND_OPENCV); net.setInput(blob); // Mask-RCNN predicts bounding boxes and segmentation masks. std::vector<String> outNames(2); outNames[0] = "detection_out_final"; outNames[1] = "detection_masks"; std::vector<Mat> outs; net.forward(outs, outNames); Mat outDetections = outs[0]; Mat outMasks = outs[1]; normAssertDetections(refDetections, outDetections, "", /*threshold for zero confidence*/1e-5); // Output size of masks is NxCxHxW where // N - number of detected boxes // C - number of classes (excluding background) // HxW - segmentation shape const int numDetections = outDetections.size[2]; int masksSize[] = {1, numDetections, outMasks.size[2], outMasks.size[3]}; Mat masks(4, &masksSize[0], CV_32F); std::vector<cv::Range> srcRanges(4, cv::Range::all()); std::vector<cv::Range> dstRanges(4, cv::Range::all()); outDetections = outDetections.reshape(1, outDetections.total() / 7); for (int i = 0; i < numDetections; ++i) { // Get a class id for this bounding box and copy mask only for that class. int classId = static_cast<int>(outDetections.at<float>(i, 1)); srcRanges[0] = dstRanges[1] = cv::Range(i, i + 1); srcRanges[1] = cv::Range(classId, classId + 1); outMasks(srcRanges).copyTo(masks(dstRanges)); } cv::Range topRefMasks[] = {Range::all(), Range(0, numDetections), Range::all(), Range::all()}; normAssert(masks, refMasks(&topRefMasks[0])); }
static void runTensorFlowNet(const std::string& prefix, int targetId = DNN_TARGET_CPU, bool hasText = false, double l1 = 1e-5, double lInf = 1e-4, bool memoryLoad = false) { std::string netPath = path(prefix + "_net.pb"); std::string netConfig = (hasText ? path(prefix + "_net.pbtxt") : ""); std::string inpPath = path(prefix + "_in.npy"); std::string outPath = path(prefix + "_out.npy"); Net net; if (memoryLoad) { // Load files into a memory buffers string dataModel; ASSERT_TRUE(readFileInMemory(netPath, dataModel)); string dataConfig; if (hasText) ASSERT_TRUE(readFileInMemory(netConfig, dataConfig)); net = readNetFromTensorflow(dataModel.c_str(), dataModel.size(), dataConfig.c_str(), dataConfig.size()); } else net = readNetFromTensorflow(netPath, netConfig); ASSERT_FALSE(net.empty()); net.setPreferableBackend(DNN_BACKEND_DEFAULT); net.setPreferableTarget(targetId); cv::Mat input = blobFromNPY(inpPath); cv::Mat target = blobFromNPY(outPath); net.setInput(input); cv::Mat output = net.forward(); normAssert(target, output, "", l1, lInf); }
TEST(Test_TensorFlow, inception_accuracy) { Net net; { const string model = findDataFile("dnn/tensorflow_inception_graph.pb", false); net = readNetFromTensorflow(model); ASSERT_FALSE(net.empty()); } Mat sample = imread(_tf("grace_hopper_227.png")); ASSERT_TRUE(!sample.empty()); resize(sample, sample, Size(224, 224)); Mat inputBlob = blobFromImage(sample); net.setInput(inputBlob, "input"); Mat out = net.forward("softmax2"); Mat ref = blobFromNPY(_tf("tf_inception_prob.npy")); normAssert(ref, out); }
TEST(Test_TensorFlow, inception_accuracy) { Net net; { const string model = findDataFile("dnn/tensorflow_inception_graph.pb", false); net = readNetFromTensorflow(model); ASSERT_FALSE(net.empty()); } net.setPreferableBackend(DNN_BACKEND_OPENCV); Mat sample = imread(_tf("grace_hopper_227.png")); ASSERT_TRUE(!sample.empty()); Mat inputBlob = blobFromImage(sample, 1.0, Size(224, 224), Scalar(), /*swapRB*/true); net.setInput(inputBlob, "input"); Mat out = net.forward("softmax2"); Mat ref = blobFromNPY(_tf("tf_inception_prob.npy")); normAssert(ref, out); }
TEST_P(Test_TensorFlow_nets, MobileNet_v1_SSD_PPN) { checkBackend(); std::string proto = findDataFile("dnn/ssd_mobilenet_v1_ppn_coco.pbtxt", false); std::string model = findDataFile("dnn/ssd_mobilenet_v1_ppn_coco.pb", false); Net net = readNetFromTensorflow(model, proto); Mat img = imread(findDataFile("dnn/dog416.png", false)); Mat ref = blobFromNPY(findDataFile("dnn/tensorflow/ssd_mobilenet_v1_ppn_coco.detection_out.npy", false)); Mat blob = blobFromImage(img, 1.0f, Size(300, 300), Scalar(), true, false); net.setPreferableBackend(backend); net.setPreferableTarget(target); net.setInput(blob); Mat out = net.forward(); double scoreDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.011 : default_l1; double iouDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.021 : default_lInf; normAssertDetections(ref, out, "", 0.4, scoreDiff, iouDiff); }
TEST_P(Test_TensorFlow_nets, MobileNet_SSD) { checkBackend(); if ((backend == DNN_BACKEND_INFERENCE_ENGINE && target != DNN_TARGET_CPU) || (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16)) throw SkipTestException(""); 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> refs(outNames.size()); for (int i = 0; i < outNames.size(); ++i) { std::string path = findDataFile("dnn/tensorflow/ssd_mobilenet_v1_coco." + outNames[i] + ".npy", false); refs[i] = blobFromNPY(path); } Net net = readNetFromTensorflow(netPath, netConfig); net.setPreferableBackend(backend); net.setPreferableTarget(target); net.setInput(inp); std::vector<Mat> output; net.forward(output, outNames); normAssert(refs[0].reshape(1, 1), output[0].reshape(1, 1), "", 1e-5, 1.5e-4); normAssert(refs[1].reshape(1, 1), output[1].reshape(1, 1), "", 1e-5, 3e-4); normAssertDetections(refs[2], output[2], "", 0.2); }
TEST(Test_TensorFlow, read_inception) { Net net; { const string model = findDataFile("dnn/tensorflow_inception_graph.pb", false); net = readNetFromTensorflow(model); ASSERT_FALSE(net.empty()); } Mat sample = imread(_tf("grace_hopper_227.png")); ASSERT_TRUE(!sample.empty()); Mat input; resize(sample, input, Size(224, 224)); input -= 128; // mean sub Mat inputBlob = blobFromImage(input); net.setInput(inputBlob, "input"); Mat out = net.forward("softmax2"); std::cout << out.dims << std::endl; }