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); } }
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); } }
OCL_TEST(Torch_Importer, ENet_accuracy) { Net net; { const string model = findDataFile("dnn/Enet-model-best.net", false); Ptr<Importer> importer = createTorchImporter(model, true); ASSERT_TRUE(importer != NULL); importer->populateNet(net); } net.setPreferableBackend(DNN_BACKEND_DEFAULT); net.setPreferableTarget(DNN_TARGET_OPENCL); 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); } }
TEST_P(Reproducibility_SqueezeNet_v1_1, Accuracy) { Net net = readNetFromCaffe(findDataFile("dnn/squeezenet_v1.1.prototxt", false), findDataFile("dnn/squeezenet_v1.1.caffemodel", false)); 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. // 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); }
TEST_P(Reproducibility_ResNet50, Accuracy) { Net net = readNetFromCaffe(findDataFile("dnn/ResNet-50-deploy.prototxt", false), findDataFile("dnn/ResNet-50-model.caffemodel", false)); int targetId = GetParam(); net.setPreferableTarget(targetId); float l1 = (targetId == DNN_TARGET_OPENCL_FP16) ? 3e-5 : 1e-5; float lInf = (targetId == DNN_TARGET_OPENCL_FP16) ? 6e-3 : 1e-4; 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, "", l1, lInf); if (targetId == DNN_TARGET_OPENCL || targetId == DNN_TARGET_OPENCL_FP16) { UMat out_umat; net.forward(out_umat); normAssert(ref, out_umat, "out_umat", l1, lInf); std::vector<UMat> out_umats; net.forward(out_umats); normAssert(ref, out_umats[0], "out_umat_vector", l1, lInf); } }
void testInPlaceActivation(LayerParams& lp) { EXPECT_FALSE(lp.name.empty()); LayerParams pool; pool.set("pool", "ave"); pool.set("kernel_w", 2); pool.set("kernel_h", 2); pool.set("stride_w", 2); pool.set("stride_h", 2); pool.type = "Pooling"; Net net; int poolId = net.addLayer(pool.name, pool.type, pool); net.connect(0, 0, poolId, 0); net.addLayerToPrev(lp.name, lp.type, lp); Mat input({1, kNumChannels, 10, 10}, CV_32F); randu(input, -1.0f, 1.0f); net.setInput(input); Mat outputDefault = net.forward(lp.name).clone(); net.setInput(input); net.setPreferableBackend(DNN_BACKEND_HALIDE); Mat outputHalide = net.forward(lp.name).clone(); normAssert(outputDefault, outputHalide); }
TEST(Test_Darknet, read_yolo_voc_stream) { Mat ref; Mat sample = imread(_tf("dog416.png")); Mat inp = blobFromImage(sample, 1.0/255, Size(416, 416), Scalar(), true, false); const std::string cfgFile = findDataFile("dnn/yolo-voc.cfg", false); const std::string weightsFile = findDataFile("dnn/yolo-voc.weights", false); // Import by paths. { Net net = readNetFromDarknet(cfgFile, weightsFile); net.setInput(inp); net.setPreferableBackend(DNN_BACKEND_OPENCV); ref = net.forward(); } // Import from bytes array. { std::string cfg, weights; readFileInMemory(cfgFile, cfg); readFileInMemory(weightsFile, weights); Net net = readNetFromDarknet(&cfg[0], cfg.size(), &weights[0], weights.size()); net.setInput(inp); net.setPreferableBackend(DNN_BACKEND_OPENCV); Mat out = net.forward(); normAssert(ref, out); } }
TEST_P(Concat, Accuracy) { Vec3i inSize = get<0>(GetParam()); Vec3i numChannels = get<1>(GetParam()); Net net; std::vector<int> convLayerIds; convLayerIds.reserve(numChannels.channels); for (int i = 0, n = numChannels.channels; i < n; ++i) { if (!numChannels[i]) break; Mat weights({numChannels[i], inSize[0], 1, 1}, CV_32F); randu(weights, -1.0f, 1.0f); LayerParams convParam; convParam.set("kernel_w", 1); convParam.set("kernel_h", 1); convParam.set("num_output", numChannels[i]); convParam.set("bias_term", false); convParam.type = "Convolution"; std::ostringstream ss; ss << "convLayer" << i; convParam.name = ss.str(); convParam.blobs.push_back(weights); int layerId = net.addLayer(convParam.name, convParam.type, convParam); convLayerIds.push_back(layerId); net.connect(0, 0, layerId, 0); } LayerParams concatParam; concatParam.type = "Concat"; concatParam.name = "testLayer"; int concatId = net.addLayer(concatParam.name, concatParam.type, concatParam); net.connect(0, 0, concatId, 0); for (int i = 0; i < convLayerIds.size(); ++i) { net.connect(convLayerIds[i], 0, concatId, i + 1); } Mat input({1, inSize[0], inSize[1], inSize[2]}, CV_32F); randu(input, -1.0f, 1.0f); net.setInput(input); Mat outputDefault = net.forward(concatParam.name).clone(); net.setPreferableBackend(DNN_BACKEND_HALIDE); Mat outputHalide = net.forward(concatParam.name).clone(); normAssert(outputDefault, outputHalide); }
static void test(LayerParams& params, Mat& input) { randu(input, -1.0f, 1.0f); Net net; int lid = net.addLayer(params.name, params.type, params); net.connect(0, 0, lid, 0); net.setInput(input); Mat outputDefault = net.forward(params.name).clone(); net.setPreferableBackend(DNN_BACKEND_HALIDE); Mat outputHalide = net.forward(params.name).clone(); normAssert(outputDefault, outputHalide); }
void runTorchNet(const String& prefix, String outLayerName = "", bool check2ndBlob = false, bool isBinary = false, double l1 = 0.0, double lInf = 0.0) { String suffix = (isBinary) ? ".dat" : ".txt"; Mat inp, outRef; ASSERT_NO_THROW( inp = readTorchBlob(_tf(prefix + "_input" + suffix), isBinary) ); ASSERT_NO_THROW( outRef = readTorchBlob(_tf(prefix + "_output" + suffix), isBinary) ); checkBackend(backend, target, &inp, &outRef); Net net = readNetFromTorch(_tf(prefix + "_net" + suffix), isBinary); ASSERT_FALSE(net.empty()); net.setPreferableBackend(backend); net.setPreferableTarget(target); if (outLayerName.empty()) outLayerName = net.getLayerNames().back(); net.setInput(inp); std::vector<Mat> outBlobs; net.forward(outBlobs, outLayerName); l1 = l1 ? l1 : default_l1; lInf = lInf ? lInf : default_lInf; normAssert(outRef, outBlobs[0], "", l1, lInf); if (check2ndBlob && backend != DNN_BACKEND_INFERENCE_ENGINE) { Mat out2 = outBlobs[1]; Mat ref2 = readTorchBlob(_tf(prefix + "_output_2" + suffix), isBinary); normAssert(out2, ref2, "", l1, lInf); } }
TEST_P(Test_Torch_nets, OpenFace_accuracy) { #if defined(INF_ENGINE_RELEASE) && INF_ENGINE_RELEASE < 2018030000 if (backend == DNN_BACKEND_INFERENCE_ENGINE && target == DNN_TARGET_MYRIAD) throw SkipTestException("Test is enabled starts from OpenVINO 2018R3"); #endif checkBackend(); if (backend == DNN_BACKEND_INFERENCE_ENGINE && target == DNN_TARGET_OPENCL_FP16) throw SkipTestException(""); const string model = findDataFile("dnn/openface_nn4.small2.v1.t7", false); Net net = readNetFromTorch(model); net.setPreferableBackend(backend); net.setPreferableTarget(target); 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, 1.0, Size(), Scalar(), /*swapRB*/true); net.setInput(inputBlob); Mat out = net.forward(); Mat outRef = readTorchBlob(_tf("net_openface_output.dat"), true); normAssert(out, outRef, "", default_l1, default_lInf); }
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(Test_Caffe, multiple_inputs) { const string proto = findDataFile("dnn/layers/net_input.prototxt", false); Net net = readNetFromCaffe(proto); Mat first_image(10, 11, CV_32FC3); Mat second_image(10, 11, CV_32FC3); randu(first_image, -1, 1); randu(second_image, -1, 1); first_image = blobFromImage(first_image); second_image = blobFromImage(second_image); Mat first_image_blue_green = slice(first_image, Range::all(), Range(0, 2), Range::all(), Range::all()); Mat first_image_red = slice(first_image, Range::all(), Range(2, 3), Range::all(), Range::all()); Mat second_image_blue_green = slice(second_image, Range::all(), Range(0, 2), Range::all(), Range::all()); Mat second_image_red = slice(second_image, Range::all(), Range(2, 3), Range::all(), Range::all()); net.setInput(first_image_blue_green, "old_style_input_blue_green"); net.setInput(first_image_red, "different_name_for_red"); net.setInput(second_image_blue_green, "input_layer_blue_green"); net.setInput(second_image_red, "old_style_input_red"); Mat out = net.forward(); normAssert(out, first_image + second_image); }
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); }
TEST(Reproducibility_FCN, Accuracy) { Net net; { const string proto = findDataFile("dnn/fcn8s-heavy-pascal.prototxt", false); const string model = findDataFile("dnn/fcn8s-heavy-pascal.caffemodel", false); net = readNetFromCaffe(proto, model); ASSERT_FALSE(net.empty()); } Mat sample = imread(_tf("street.png")); ASSERT_TRUE(!sample.empty()); std::vector<int> layerIds; std::vector<size_t> weights, blobs; net.getMemoryConsumption(shape(1,3,227,227), layerIds, weights, blobs); net.setInput(blobFromImage(sample, 1.0f, Size(500, 500), Scalar(), false), "data"); Mat out = net.forward("score"); Mat refData = imread(_tf("caffe_fcn8s_prob.png"), IMREAD_ANYDEPTH); int shape[] = {1, 21, 500, 500}; Mat ref(4, shape, CV_32FC1, refData.data); normAssert(ref, out); }
TEST_P(opencv_face_detector, Accuracy) { std::string proto = findDataFile("dnn/opencv_face_detector.prototxt", false); std::string model = findDataFile(get<0>(GetParam()), false); dnn::Target targetId = (dnn::Target)(int)get<1>(GetParam()); Net net = readNetFromCaffe(proto, model); 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(targetId); 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>(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); normAssertDetections(ref, out, "", 0.5, 1e-5, 2e-4); }
void test( Net& model, torch::Device device, DataLoader& data_loader, size_t dataset_size) { torch::NoGradGuard no_grad; model.eval(); double test_loss = 0; int32_t correct = 0; for (const auto& batch : data_loader) { auto data = batch.data.to(device), targets = batch.target.to(device); auto output = model.forward(data); test_loss += torch::nll_loss( output, targets, /*weight=*/{}, Reduction::Sum) .template item<float>(); auto pred = output.argmax(1); correct += pred.eq(targets).sum().template item<int64_t>(); } test_loss /= dataset_size; std::printf( "\nTest set: Average loss: %.4f | Accuracy: %.3f\n", test_loss, static_cast<double>(correct) / dataset_size); }
void train( int32_t epoch, Net& model, torch::Device device, DataLoader& data_loader, torch::optim::Optimizer& optimizer, size_t dataset_size) { model.train(); size_t batch_idx = 0; for (auto& batch : data_loader) { auto data = batch.data.to(device), targets = batch.target.to(device); optimizer.zero_grad(); auto output = model.forward(data); auto loss = torch::nll_loss(output, targets); AT_ASSERT(!std::isnan(loss.template item<float>())); loss.backward(); optimizer.step(); if (batch_idx++ % kLogInterval == 0) { std::printf( "\rTrain Epoch: %ld [%5ld/%5ld] Loss: %.4f", epoch, batch_idx * batch.data.size(0), dataset_size, loss.template item<float>()); } } }
TEST(Test_Caffe, FasterRCNN_and_RFCN) { std::string models[] = {"VGG16_faster_rcnn_final.caffemodel", "ZF_faster_rcnn_final.caffemodel", "resnet50_rfcn_final.caffemodel"}; std::string protos[] = {"faster_rcnn_vgg16.prototxt", "faster_rcnn_zf.prototxt", "rfcn_pascal_voc_resnet50.prototxt"}; Mat refs[] = {(Mat_<float>(3, 7) << 0, 2, 0.949398, 99.2454, 210.141, 601.205, 462.849, 0, 7, 0.997022, 481.841, 92.3218, 722.685, 175.953, 0, 12, 0.993028, 133.221, 189.377, 350.994, 563.166), (Mat_<float>(3, 7) << 0, 2, 0.90121, 120.407, 115.83, 570.586, 528.395, 0, 7, 0.988779, 469.849, 75.1756, 718.64, 186.762, 0, 12, 0.967198, 138.588, 206.843, 329.766, 553.176), (Mat_<float>(2, 7) << 0, 7, 0.991359, 491.822, 81.1668, 702.573, 178.234, 0, 12, 0.94786, 132.093, 223.903, 338.077, 566.16)}; for (int i = 0; i < 3; ++i) { std::string proto = findDataFile("dnn/" + protos[i], false); std::string model = findDataFile("dnn/" + models[i], false); Net net = readNetFromCaffe(proto, model); Mat img = imread(findDataFile("dnn/dog416.png", false)); resize(img, img, Size(800, 600)); Mat blob = blobFromImage(img, 1.0, Size(), Scalar(102.9801, 115.9465, 122.7717), false, false); Mat imInfo = (Mat_<float>(1, 3) << img.rows, img.cols, 1.6f); net.setInput(blob, "data"); net.setInput(imInfo, "im_info"); // 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(); normAssertDetections(refs[i], out, ("model name: " + models[i]).c_str(), 0.8); } }
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); } }
static void runTorchNet(String prefix, String outLayerName = "", bool check2ndBlob = false, bool isBinary = false) { String suffix = (isBinary) ? ".dat" : ".txt"; Net net; Ptr<Importer> importer = createTorchImporter(_tf(prefix + "_net" + suffix), isBinary); ASSERT_TRUE(importer != NULL); importer->populateNet(net); Blob inp, outRef; ASSERT_NO_THROW( inp = readTorchBlob(_tf(prefix + "_input" + suffix), isBinary) ); ASSERT_NO_THROW( outRef = readTorchBlob(_tf(prefix + "_output" + suffix), isBinary) ); net.setBlob(".0", inp); net.forward(); if (outLayerName.empty()) outLayerName = net.getLayerNames().back(); Blob out = net.getBlob(outLayerName); normAssert(outRef, out); if (check2ndBlob) { Blob out2 = net.getBlob(outLayerName + ".1"); Blob ref2 = readTorchBlob(_tf(prefix + "_output_2" + suffix), isBinary); normAssert(out2, ref2); } }
TEST(Reproducibility_FCN, Accuracy) { Net net; { const string proto = findDataFile("dnn/fcn8s-heavy-pascal.prototxt", false); const string model = findDataFile("dnn/fcn8s-heavy-pascal.caffemodel", false); Ptr<Importer> importer = createCaffeImporter(proto, model); ASSERT_TRUE(importer != NULL); importer->populateNet(net); } Mat sample = imread(_tf("street.png")); ASSERT_TRUE(!sample.empty()); Size inputSize(500, 500); if (sample.size() != inputSize) resize(sample, sample, inputSize); net.setBlob(".data", blobFromImage(sample, 1.)); net.forward(); Mat out = net.getBlob("score"); Mat ref = blobFromNPY(_tf("caffe_fcn8s_prob.npy")); normAssert(ref, out); }
TEST(Reproducibility_AlexNet, Accuracy) { Net net; { const string proto = findDataFile("dnn/bvlc_alexnet.prototxt", false); const string model = findDataFile("dnn/bvlc_alexnet.caffemodel", false); Ptr<Importer> importer = createCaffeImporter(proto, model); ASSERT_TRUE(importer != NULL); importer->populateNet(net); } Mat sample = imread(_tf("grace_hopper_227.png")); ASSERT_TRUE(!sample.empty()); Size inputSize(227, 227); if (sample.size() != inputSize) resize(sample, sample, inputSize); net.setBlob(".data", blobFromImage(sample, 1.)); net.forward(); Mat out = net.getBlob("prob"); Mat ref = blobFromNPY(_tf("caffe_alexnet_prob.npy")); normAssert(ref, out); }
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) { 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, 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); }
static void runTorchNet(String prefix, int targetId = DNN_TARGET_CPU, String outLayerName = "", bool check2ndBlob = false, bool isBinary = false) { String suffix = (isBinary) ? ".dat" : ".txt"; Net net = readNetFromTorch(_tf(prefix + "_net" + suffix), isBinary); ASSERT_FALSE(net.empty()); net.setPreferableBackend(DNN_BACKEND_DEFAULT); net.setPreferableTarget(targetId); Mat inp, outRef; ASSERT_NO_THROW( inp = readTorchBlob(_tf(prefix + "_input" + suffix), isBinary) ); ASSERT_NO_THROW( outRef = readTorchBlob(_tf(prefix + "_output" + suffix), isBinary) ); if (outLayerName.empty()) outLayerName = net.getLayerNames().back(); net.setInput(inp, "0"); std::vector<Mat> outBlobs; net.forward(outBlobs, outLayerName); normAssert(outRef, outBlobs[0]); if (check2ndBlob) { Mat out2 = outBlobs[1]; Mat ref2 = readTorchBlob(_tf(prefix + "_output_2" + suffix), isBinary); normAssert(out2, ref2); } }
// Check accuracy of style transfer models from https://github.com/jcjohnson/fast-neural-style // th fast_neural_style.lua \ // -input_image ~/opencv_extra/testdata/dnn/googlenet_1.png \ // -output_image lena.png \ // -median_filter 0 \ // -image_size 0 \ // -model models/eccv16/starry_night.t7 // th fast_neural_style.lua \ // -input_image ~/opencv_extra/testdata/dnn/googlenet_1.png \ // -output_image lena.png \ // -median_filter 0 \ // -image_size 0 \ // -model models/instance_norm/feathers.t7 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"}; for (int i = 0; i < 2; ++i) { const string model = findDataFile(models[i], false); Net net = readNetFromTorch(model); 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); normAssert(out, refBlob, "", 0.5, 1.1); } }
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); int targetId = GetParam(); const float l1 = (targetId == DNN_TARGET_OPENCL_FP16) ? 1.5e-4 : 1e-5; const float lInf = (targetId == DNN_TARGET_OPENCL_FP16) ? 4e-4 : 1e-4; net.setPreferableTarget(targetId); 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(); const float scores_diff = (targetId == DNN_TARGET_OPENCL_FP16) ? 4e-4 : 1e-5; const float boxes_iou_diff = (targetId == DNN_TARGET_OPENCL_FP16) ? 5e-3 : 1e-4; Mat ref = blobFromNPY(_tf("mobilenet_ssd_caffe_out.npy")); normAssertDetections(ref, out, "", 0.0, scores_diff, boxes_iou_diff); // Check that detections aren't preserved. inp.setTo(0.0f); net.setInput(inp); out = net.forward(); out = out.reshape(1, out.total() / 7); const int numDetections = out.rows; ASSERT_NE(numDetections, 0); for (int i = 0; i < numDetections; ++i) { float confidence = out.ptr<float>(i)[2]; ASSERT_EQ(confidence, 0); } // 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, "", l1, lInf); normAssert(outBatch.rowRange(numDetections, 2 * numDetections).colRange(1, 7), ref.colRange(1, 7), "", l1, lInf); }
TEST_P(Test_ONNX_nets, Googlenet) { if (backend == DNN_BACKEND_INFERENCE_ENGINE) throw SkipTestException(""); const String model = _tf("models/googlenet.onnx"); Net net = readNetFromONNX(model); ASSERT_FALSE(net.empty()); net.setPreferableBackend(backend); net.setPreferableTarget(target); std::vector<Mat> images; images.push_back( imread(_tf("../googlenet_0.png")) ); images.push_back( imread(_tf("../googlenet_1.png")) ); Mat inp = blobFromImages(images, 1.0f, Size(), Scalar(), false); Mat ref = blobFromNPY(_tf("../googlenet_prob.npy")); checkBackend(&inp, &ref); net.setInput(inp); ASSERT_FALSE(net.empty()); Mat out = net.forward(); normAssert(ref, out, "", default_l1, default_lInf); expectNoFallbacksFromIE(net); }