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_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);
}
TEST_P(Power, Accuracy)
{
    float power = get<0>(GetParam())[0];
    float scale = get<0>(GetParam())[1];
    float shift = get<0>(GetParam())[2];

    LayerParams lp;
    lp.set("power", power);
    lp.set("scale", scale);
    lp.set("shift", shift);
    lp.type = "Power";
    lp.name = "testLayer";
    testInPlaceActivation(lp);
}
TEST_P(ReLU, Accuracy)
{
    float negativeSlope = get<0>(GetParam());

    LayerParams lp;
    lp.set("negative_slope", negativeSlope);
    lp.type = "ReLU";
    lp.name = "testLayer";
    testInPlaceActivation(lp);
}
TEST_P(AvePooling, Accuracy)
{
    int inChannels = get<0>(GetParam());
    Size outSize = get<1>(GetParam());;  // Input size will be computed from parameters.
    Size kernel = get<2>(GetParam());
    Size stride = get<3>(GetParam());

    const int inWidth = (outSize.width - 1) * stride.width + kernel.width;
    const int inHeight = (outSize.height - 1) * stride.height + kernel.height;

    LayerParams lp;
    lp.set("pool", "ave");
    lp.set("kernel_w", kernel.width);
    lp.set("kernel_h", kernel.height);
    lp.set("stride_w", stride.width);
    lp.set("stride_h", stride.height);
    lp.type = "Pooling";
    lp.name = "testLayer";

    Mat input({1, inChannels, inHeight, inWidth}, CV_32F);
    test(lp, input);
}
TEST_P(FullyConnected, Accuracy)
{
    int inChannels = get<0>(GetParam());
    Size inSize = get<1>(GetParam());
    int outChannels = get<2>(GetParam());
    bool hasBias = get<3>(GetParam());

    Mat weights(outChannels, inChannels * inSize.height * inSize.width, CV_32F);
    randu(weights, -1.0f, 1.0f);

    Mat bias(1, outChannels, CV_32F);
    randu(bias, -1.0f, 1.0f);

    LayerParams lp;
    lp.set("num_output", outChannels);
    lp.set("bias_term", hasBias);
    lp.blobs.push_back(weights);
    lp.blobs.push_back(bias);
    lp.type = "InnerProduct";
    lp.name = "testLayer";

    Mat input({1, inChannels, inSize.height, inSize.width}, CV_32F);
    test(lp, input);
}
TEST_P(BatchNorm, Accuracy)
{
    bool hasWeights = get<0>(GetParam());
    bool hasBias = get<1>(GetParam());
    float epsilon = get<2>(GetParam());

    LayerParams lp;
    lp.set("has_weight", hasWeights);
    lp.set("has_bias", hasBias);
    lp.set("eps", epsilon);
    lp.type = "BatchNorm";
    lp.name = "testLayer";

    lp.blobs.reserve(4);
    for (int i = 0; i < 3; ++i)
        lp.blobs.push_back(Mat({kNumChannels}, CV_32F));
    if (hasBias || hasWeights)
        lp.blobs.push_back(Mat({kNumChannels}, CV_32F));

    for (Mat& m : lp.blobs)
        randu(m, 0.0f, 1.0f);

    testInPlaceActivation(lp);
}
TEST_P(LRN, Accuracy)
{
    int inChannels = get<0>(GetParam())[0];
    Size inSize = Size(get<0>(GetParam())[1], get<0>(GetParam())[2]);
    int localSize = get<1>(GetParam());
    float alpha = get<2>(GetParam())[0];
    float beta = get<2>(GetParam())[1];
    float bias = get<2>(GetParam())[2];
    bool normBySize = get<3>(GetParam());
    std::string nrmType = get<4>(GetParam());

    LayerParams lp;
    lp.set("norm_region", nrmType);
    lp.set("local_size", localSize);
    lp.set("alpha", alpha);
    lp.set("beta", beta);
    lp.set("bias", bias);
    lp.set("norm_by_size", normBySize);
    lp.type = "LRN";
    lp.name = "testLayer";

    Mat input({1, inChannels, inSize.height, inSize.width}, CV_32F);
    test(lp, input);
}
TEST_P(Scale, Accuracy)
{
    bool hasBias = get<0>(GetParam());

    LayerParams lp;
    lp.set("bias_term", hasBias);
    lp.type = "Scale";
    lp.name = "testLayer";
    lp.blobs.push_back(Mat({kNumChannels}, CV_32F));
    randu(lp.blobs[0], -1.0f, 1.0f);
    if (hasBias)
    {
        lp.blobs.push_back(Mat({kNumChannels}, CV_32F));
        randu(lp.blobs[1], -1.0f, 1.0f);
    }
    testInPlaceActivation(lp);
}
示例#10
0
////////////////////////////////////////////////////////////////////////////////
// Padding
////////////////////////////////////////////////////////////////////////////////
TEST(Padding_Halide, Accuracy)
{
    static const int kNumRuns = 10;
    std::vector<int> paddings(8);
    for (int t = 0; t < kNumRuns; ++t)
    {
        for (int i = 0; i < paddings.size(); ++i)
            paddings[i] = rand() % 5;

        LayerParams lp;
        lp.set("paddings", DictValue::arrayInt<int*>(&paddings[0], paddings.size()));
        lp.type = "Padding";
        lp.name = "testLayer";

        Mat input({1 + rand() % 10, 1 + rand() % 10, 1 + rand() % 10, 1 + rand() % 10}, CV_32F);
        test(lp, input);
    }
}
示例#11
0
//////////////////////////////////////////////////////////////////////////////
// Max pooling - unpooling
//////////////////////////////////////////////////////////////////////////////
TEST(MaxPoolUnpool_Halide, Accuracy)
{
    LayerParams pool;
    pool.set("pool", "max");
    pool.set("kernel_w", 2);
    pool.set("kernel_h", 2);
    pool.set("stride_w", 2);
    pool.set("stride_h", 2);
    pool.set("pad_w", 0);
    pool.set("pad_h", 0);
    pool.type = "Pooling";
    pool.name = "testPool";

    LayerParams unpool;
    unpool.set("pool_k_w", 2);
    unpool.set("pool_k_h", 2);
    unpool.set("pool_stride_w", 2);
    unpool.set("pool_stride_h", 2);
    unpool.set("pool_pad_w", 0);
    unpool.set("pool_pad_h", 0);
    unpool.type = "MaxUnpool";
    unpool.name = "testUnpool";

    Net net;
    int poolId = net.addLayer(pool.name, pool.type, pool);
    net.connect(0, 0, poolId, 0);

    int unpoolId = net.addLayer(unpool.name, unpool.type, unpool);
    net.connect(poolId, 0, unpoolId, 0);
    net.connect(poolId, 1, unpoolId, 1);

    Mat input({1, 1, 4, 4}, CV_32F);
    randu(input, -1.0f, 1.0f);
    net.setInput(input);
    Mat outputDefault = net.forward("testUnpool").clone();

    net.setPreferableBackend(DNN_BACKEND_HALIDE);
    net.setInput(input);
    Mat outputHalide = net.forward("testUnpool").clone();
    normAssert(outputDefault, outputHalide);
}
示例#12
0
TEST_P(MaxPooling, Accuracy)
{
    int inChannels = get<0>(GetParam());
    Size inSize = get<1>(GetParam());
    Size kernel = get<2>(GetParam());
    Size stride = get<3>(GetParam());
    Size pad = get<4>(GetParam());

    LayerParams lp;
    lp.set("pool", "max");
    lp.set("kernel_w", kernel.width);
    lp.set("kernel_h", kernel.height);
    lp.set("stride_w", stride.width);
    lp.set("stride_h", stride.height);
    lp.set("pad_w", pad.width);
    lp.set("pad_h", pad.height);
    lp.type = "Pooling";
    lp.name = "testLayer";

    Mat input({1, inChannels, inSize.height, inSize.width}, CV_32F);
    test(lp, input);
}
示例#13
0
    void populateNet(Net dstNet)
    {
        CV_TRACE_FUNCTION();

        int layersSize = net.layer_size();
        layerCounter.clear();
        addedBlobs.clear();
        addedBlobs.reserve(layersSize + 1);

        //setup input layer names
        std::vector<String> netInputs(net.input_size());
        {
            for (int inNum = 0; inNum < net.input_size(); inNum++)
            {
                addedBlobs.push_back(BlobNote(net.input(inNum), 0, inNum));
                netInputs[inNum] = net.input(inNum);
            }
        }

        for (int li = 0; li < layersSize; li++)
        {
            const caffe::LayerParameter &layer = net.layer(li);
            String name = layer.name();
            String type = layer.type();
            LayerParams layerParams;

            extractLayerParams(layer, layerParams);
            extractBinaryLayerParams(layer, layerParams);

            int repetitions = layerCounter[name]++;
            if (repetitions)
                name += String("_") + toString(repetitions);

            if (type == "Input")
            {
                for (int outNum = 0; outNum < layer.top_size(); outNum++)
                {
                    addOutput(layer, 0, outNum);
                    addedBlobs.back().outNum = netInputs.size();
                    netInputs.push_back(addedBlobs.back().name);
                }
                continue;
            }
            else if (type == "BatchNorm")
            {
                if (!layerParams.get<bool>("use_global_stats", true))
                {
                    CV_Assert_N(layer.bottom_size() == 1, layer.top_size() == 1);

                    LayerParams mvnParams;
                    mvnParams.set("eps", layerParams.get<float>("eps", 1e-5));
                    std::string mvnName = name + "/mvn";

                    int repetitions = layerCounter[mvnName]++;
                    if (repetitions)
                        mvnName += String("_") + toString(repetitions);

                    int mvnId = dstNet.addLayer(mvnName, "MVN", mvnParams);
                    addInput(layer.bottom(0), mvnId, 0, dstNet);
                    addOutput(layer, mvnId, 0);
                    net.mutable_layer(li)->set_bottom(0, layer.top(0));
                    layerParams.blobs[0].setTo(0);  // mean
                    layerParams.blobs[1].setTo(1);  // std
                }
            }
            else if ("ConvolutionDepthwise" == type)
            {
                type = "Convolution";
            }

            int id = dstNet.addLayer(name, type, layerParams);

            for (int inNum = 0; inNum < layer.bottom_size(); inNum++)
                addInput(layer.bottom(inNum), id, inNum, dstNet);

            for (int outNum = 0; outNum < layer.top_size(); outNum++)
                addOutput(layer, id, outNum);
        }
        dstNet.setInputsNames(netInputs);

        addedBlobs.clear();
    }
示例#14
0
void ONNXImporter::populateNet(Net dstNet)
{
    CV_Assert(model_proto.has_graph());
    opencv_onnx::GraphProto graph_proto = model_proto.graph();
    std::map<std::string, Mat> constBlobs = getGraphTensors(graph_proto);
    // List of internal blobs shapes.
    std::map<std::string, MatShape> outShapes;
    // Add all the inputs shapes. It includes as constant blobs as network's inputs shapes.
    for (int i = 0; i < graph_proto.input_size(); ++i)
    {
        opencv_onnx::ValueInfoProto valueInfoProto = graph_proto.input(i);
        CV_Assert(valueInfoProto.has_type());
        opencv_onnx::TypeProto typeProto = valueInfoProto.type();
        CV_Assert(typeProto.has_tensor_type());
        opencv_onnx::TypeProto::Tensor tensor = typeProto.tensor_type();
        CV_Assert(tensor.has_shape());
        opencv_onnx::TensorShapeProto tensorShape = tensor.shape();

        MatShape inpShape(tensorShape.dim_size());
        for (int j = 0; j < inpShape.size(); ++j)
        {
            inpShape[j] = tensorShape.dim(j).dim_value();
        }
        outShapes[valueInfoProto.name()] = inpShape;
    }

    std::string framework_name;
    if (model_proto.has_producer_name()) {
        framework_name = model_proto.producer_name();
    }

    // create map with network inputs (without const blobs)
    std::map<std::string, LayerInfo> layer_id;
    std::map<std::string, LayerInfo>::iterator layerId;
    std::map<std::string, MatShape>::iterator shapeIt;
    // fill map: push layer name, layer id and output id
    std::vector<String> netInputs;
    for (int j = 0; j < graph_proto.input_size(); j++)
    {
        const std::string& name = graph_proto.input(j).name();
        if (constBlobs.find(name) == constBlobs.end()) {
            netInputs.push_back(name);
            layer_id.insert(std::make_pair(name, LayerInfo(0, netInputs.size() - 1)));
        }
    }
    dstNet.setInputsNames(netInputs);

    int layersSize = graph_proto.node_size();
    LayerParams layerParams;
    opencv_onnx::NodeProto node_proto;

    for(int li = 0; li < layersSize; li++)
    {
        node_proto = graph_proto.node(li);
        layerParams = getLayerParams(node_proto);
        CV_Assert(node_proto.output_size() >= 1);
        layerParams.name = node_proto.output(0);

        std::string layer_type = node_proto.op_type();
        layerParams.type = layer_type;


        if (layer_type == "MaxPool")
        {
            layerParams.type = "Pooling";
            layerParams.set("pool", "MAX");
            layerParams.set("ceil_mode", isCeilMode(layerParams));
        }
        else if (layer_type == "AveragePool")
        {
            layerParams.type = "Pooling";
            layerParams.set("pool", "AVE");
            layerParams.set("ceil_mode", isCeilMode(layerParams));
            layerParams.set("ave_pool_padded_area", framework_name == "pytorch");
        }
        else if (layer_type == "GlobalAveragePool")
        {
            layerParams.type = "Pooling";
            layerParams.set("pool", "AVE");
            layerParams.set("global_pooling", true);
        }
        else if (layer_type == "Add" || layer_type == "Sum")
        {
            if (layer_id.find(node_proto.input(1)) == layer_id.end())
            {
                Mat blob = getBlob(node_proto, constBlobs, 1);
                blob = blob.reshape(1, 1);
                if (blob.total() == 1) {
                    layerParams.type = "Power";
                    layerParams.set("shift", blob.at<float>(0));
                }
                else {
                    layerParams.type = "Scale";
                    layerParams.set("bias_term", true);
                    layerParams.blobs.push_back(blob);
                }
            }
            else {
                layerParams.type = "Eltwise";
            }
        }
        else if (layer_type == "Sub")
        {
            Mat blob = getBlob(node_proto, constBlobs, 1);
            if (blob.total() == 1) {
                layerParams.type = "Power";
                layerParams.set("shift", -blob.at<float>(0));
            }
            else {
                layerParams.type = "Scale";
                layerParams.set("has_bias", true);
                layerParams.blobs.push_back(-1.0f * blob.reshape(1, 1));
            }
        }
        else if (layer_type == "Div")
        {
            Mat blob = getBlob(node_proto, constBlobs, 1);
            CV_Assert_N(blob.type() == CV_32F, blob.total());
            if (blob.total() == 1)
            {
                layerParams.set("scale", 1.0f / blob.at<float>(0));
                layerParams.type = "Power";
            }
            else
            {
                layerParams.type = "Scale";
                divide(1.0, blob, blob);
                layerParams.blobs.push_back(blob);
                layerParams.set("bias_term", false);
            }
        }
        else if (layer_type == "Constant")
        {
            CV_Assert(node_proto.input_size() == 0);
            CV_Assert(layerParams.blobs.size() == 1);
            constBlobs.insert(std::make_pair(layerParams.name, layerParams.blobs[0]));
            continue;
        }
        else if (layer_type == "ImageScaler")
        {
            const float scale = layerParams.has("scale") ? layerParams.get<float>("scale") : 1.0f;
            layerParams.erase("scale");

            if (layerParams.has("bias"))
            {
                layerParams.type = "Scale";
                layerParams.blobs.push_back(
                    Mat(Size(1,  layerParams.get("bias").size()), CV_32FC1, scale));

                layerParams.set("bias_term", true);
                Mat bias(1, layerParams.get("bias").size(), CV_32FC1);
                for (int j = 0; j < bias.total(); j++) {
                    bias.at<float>(0, j) = layerParams.get("bias").getRealValue(j);
                }
                layerParams.blobs.push_back(bias);
                layerParams.erase("bias");
            }
            else {
                layerParams.set("scale", scale);
                layerParams.type = "Power";
            }
        }
        else if (layer_type == "LeakyRelu")
        {
            layerParams.type = "ReLU";
            replaceLayerParam(layerParams, "alpha", "negative_slope");
        }
        else if (layer_type == "LRN")
        {
            replaceLayerParam(layerParams, "size", "local_size");
        }
        else if (layer_type == "BatchNormalization")
        {
            if (node_proto.input_size() != 5)
                CV_Error(Error::StsNotImplemented,
                         "Expected input, scale, bias, mean and var");

            layerParams.type = "BatchNorm";
            replaceLayerParam(layerParams, "epsilon", "eps");
            replaceLayerParam(layerParams, "spatial", "use_global_stats");

            Mat meanData = getBlob(node_proto, constBlobs, 3);
            Mat stdData =  getBlob(node_proto, constBlobs, 4);

            layerParams.blobs.push_back(meanData);
            layerParams.blobs.push_back(stdData);

            if (!node_proto.input(1).empty()) {
                layerParams.set("has_weight", true);
                layerParams.blobs.push_back(getBlob(node_proto, constBlobs, 1));  // weightData
            } else {
                layerParams.set("has_weight", false);
            }

            if (!node_proto.input(2).empty()) {
                layerParams.set("has_bias", true);
                layerParams.blobs.push_back(getBlob(node_proto, constBlobs, 2)); // biasData
            } else {
                layerParams.set("has_bias", false);
            }
        }
        else if (layer_type == "Gemm")
        {
            CV_Assert(node_proto.input_size() >= 2);
            layerParams.type = "InnerProduct";
            Mat weights = getBlob(node_proto, constBlobs, 1);
            int ind_num_out = 0;
            if (layerParams.has("transB") && !layerParams.get<int>("transB")) {
                transpose(weights, weights);
                ind_num_out = 1;
            }
            layerParams.blobs.push_back(weights);

            if (node_proto.input_size() == 3) {
                Mat bias = getBlob(node_proto, constBlobs, 2);
                layerParams.blobs.push_back(bias);
            }

            layerParams.set("num_output", layerParams.blobs[0].size[ind_num_out]);
            layerParams.set("bias_term", node_proto.input_size() == 3);
        }
        else if (layer_type == "MatMul")
        {
            CV_Assert(node_proto.input_size() == 2);
            layerParams.type = "InnerProduct";
            Mat blob = getBlob(node_proto, constBlobs, 1);
            layerParams.blobs.push_back(blob.t());
            layerParams.set("bias_term", false);
            layerParams.set("num_output", layerParams.blobs[0].size[0]);
        }
        else if (layer_type == "Mul")
        {
            CV_Assert(node_proto.input_size() == 2);
            if (layer_id.find(node_proto.input(1)) == layer_id.end()) {
                Mat blob = getBlob(node_proto, constBlobs, 1);
                blob = blob.reshape(1, 1);
                if (blob.total() == 1) {
                    layerParams.set("scale", blob.at<float>(0));
                    layerParams.type = "Power";
                }
                else {
                    layerParams.blobs.push_back(blob);
                    layerParams.type = "Scale";
                }
            }
            else {
                layerParams.type = "Eltwise";
                layerParams.set("operation", "prod");
            }
        }
        else if (layer_type == "Conv")
        {
            CV_Assert(node_proto.input_size() >= 2);
            layerParams.type = "Convolution";
            for (int j = 1; j < node_proto.input_size(); j++) {
                layerParams.blobs.push_back(getBlob(node_proto, constBlobs, j));
            }
            layerParams.set("num_output", layerParams.blobs[0].size[0]);
            layerParams.set("bias_term", node_proto.input_size() == 3);
        }
        else if (layer_type == "ConvTranspose")
        {
            CV_Assert(node_proto.input_size() >= 2);
            layerParams.type = "Deconvolution";
            for (int j = 1; j < node_proto.input_size(); j++) {
                layerParams.blobs.push_back(getBlob(node_proto, constBlobs, j));
            }
            layerParams.set("num_output", layerParams.blobs[0].size[1]);
            layerParams.set("bias_term", node_proto.input_size() == 3);
        }
        else if (layer_type == "Transpose")
        {
            layerParams.type = "Permute";
            replaceLayerParam(layerParams, "perm", "order");
        }
        else if (layer_type == "Unsqueeze")
        {
            CV_Assert(node_proto.input_size() == 1);
            Mat input = getBlob(node_proto, constBlobs, 0);

            DictValue axes = layerParams.get("axes");
            std::vector<int> dims;
            for (int j = 0; j < input.dims; j++) {
                dims.push_back(input.size[j]);
            }
            CV_Assert(axes.getIntValue(axes.size()-1) <= dims.size());
            for (int j = 0; j < axes.size(); j++) {
                dims.insert(dims.begin() + axes.getIntValue(j), 1);
            }

            Mat out = input.reshape(0, dims);
            constBlobs.insert(std::make_pair(layerParams.name, out));
            continue;
        }
        else if (layer_type == "Reshape")
        {
            CV_Assert(node_proto.input_size() == 2 || layerParams.has("shape"));

            if (node_proto.input_size() == 2) {
                Mat blob = getBlob(node_proto, constBlobs, 1);
                CV_Assert(blob.type() == CV_32SC1);

                if (layer_id.find(node_proto.input(0)) == layer_id.end()) {
                    Mat input = getBlob(node_proto, constBlobs, 0);
                    Mat out = input.reshape(0, static_cast<std::vector<int> >(blob));
                    constBlobs.insert(std::make_pair(layerParams.name, out));
                    continue;
                }
                layerParams.set("dim", DictValue::arrayInt<int*>(
                            blob.ptr<int>(), blob.total() ));
            }
            else {
                DictValue shape = layerParams.get("shape");
                std::vector<int> dim;
                for (int j = 0; j < shape.size(); j++) {
                    dim.push_back(shape.getIntValue(j));
                }

                if (layer_id.find(node_proto.input(0)) == layer_id.end()) {
                    Mat input = getBlob(node_proto, constBlobs, 0);
                    Mat out = input.reshape(0, dim);
                    constBlobs.insert(std::make_pair(layerParams.name, out));
                    continue;
                }
                replaceLayerParam(layerParams, "shape", "dim");
            }
        }
        else if (layer_type == "Pad")
        {
            layerParams.type = "Padding";
        }
        else if (layer_type == "Shape")
        {
            CV_Assert(node_proto.input_size() == 1);
            shapeIt = outShapes.find(node_proto.input(0));
            CV_Assert(shapeIt != outShapes.end());
            MatShape inpShape = shapeIt->second;

            Mat shapeMat(inpShape.size(), 1, CV_32S);
            for (int j = 0; j < inpShape.size(); ++j)
                shapeMat.at<int>(j) = inpShape[j];
            shapeMat.dims = 1;

            constBlobs.insert(std::make_pair(layerParams.name, shapeMat));
            continue;
        }
        else if (layer_type == "Gather")
        {
            CV_Assert(node_proto.input_size() == 2);
            CV_Assert(layerParams.has("axis"));
            Mat input = getBlob(node_proto, constBlobs, 0);
            Mat indexMat = getBlob(node_proto, constBlobs, 1);
            CV_Assert_N(indexMat.type() == CV_32S, indexMat.total() == 1);
            int index = indexMat.at<int>(0);
            int axis = layerParams.get<int>("axis");

            std::vector<cv::Range> ranges(input.dims, Range::all());
            ranges[axis] = Range(index, index + 1);

            Mat out = input(ranges);
            constBlobs.insert(std::make_pair(layerParams.name, out));
            continue;
        }
        else if (layer_type == "Concat")
        {
            bool hasVariableInps = false;
            for (int i = 0; i < node_proto.input_size(); ++i)
            {
                if (layer_id.find(node_proto.input(i)) != layer_id.end())
                {
                    hasVariableInps = true;
                    break;
                }
            }

            if (!hasVariableInps)
            {
                std::vector<Mat> inputs(node_proto.input_size()), concatenated;
                for (size_t i = 0; i < inputs.size(); ++i)
                {
                    inputs[i] = getBlob(node_proto, constBlobs, i);
                }
                Ptr<Layer> concat = ConcatLayer::create(layerParams);
                runLayer(concat, inputs, concatenated);

                CV_Assert(concatenated.size() == 1);
                constBlobs.insert(std::make_pair(layerParams.name, concatenated[0]));
                continue;
            }
        }
        else
        {
            for (int j = 0; j < node_proto.input_size(); j++) {
                if (layer_id.find(node_proto.input(j)) == layer_id.end())
                    layerParams.blobs.push_back(getBlob(node_proto, constBlobs, j));
            }
         }

         int id = dstNet.addLayer(layerParams.name, layerParams.type, layerParams);
         layer_id.insert(std::make_pair(layerParams.name, LayerInfo(id, 0)));


         std::vector<MatShape> layerInpShapes, layerOutShapes, layerInternalShapes;
         for (int j = 0; j < node_proto.input_size(); j++) {
             layerId = layer_id.find(node_proto.input(j));
             if (layerId != layer_id.end()) {
                 dstNet.connect(layerId->second.layerId, layerId->second.outputId, id, j);
                 // Collect input shapes.
                 shapeIt = outShapes.find(node_proto.input(j));
                 CV_Assert(shapeIt != outShapes.end());
                 layerInpShapes.push_back(shapeIt->second);
             }
         }

         // Compute shape of output blob for this layer.
         Ptr<Layer> layer = dstNet.getLayer(id);
         layer->getMemoryShapes(layerInpShapes, 0, layerOutShapes, layerInternalShapes);
         CV_Assert(!layerOutShapes.empty());
         outShapes[layerParams.name] = layerOutShapes[0];
     }
 }
示例#15
0
LayerParams ONNXImporter::getLayerParams(const opencv_onnx::NodeProto& node_proto)
{
    LayerParams lp;
    for(int i = 0; i < node_proto.attribute_size(); i++)
    {
        opencv_onnx::AttributeProto attribute_proto = node_proto.attribute(i);
        std::string attribute_name = attribute_proto.name();

        if(attribute_name == "kernel_shape")
        {
            CV_Assert(attribute_proto.ints_size() == 2);
            lp.set("kernel_h", saturate_cast<int32_t>(attribute_proto.ints(0)));
            lp.set("kernel_w", saturate_cast<int32_t>(attribute_proto.ints(1)));
        }
        else if(attribute_name == "strides")
        {
            CV_Assert(attribute_proto.ints_size() == 2);
            lp.set("stride_h", saturate_cast<int32_t>(attribute_proto.ints(0)));
            lp.set("stride_w", saturate_cast<int32_t>(attribute_proto.ints(1)));
        }
        else if(attribute_name == "pads")
        {
            if (node_proto.op_type() == "Pad")
            {
                // Padding layer.
                // Paddings are in order begin0, begin1, .. beginN, end0, end1, ..., endN.
                // We need to shuffle it to begin0, end0, begin1, end1, ...
                CV_Assert(attribute_proto.ints_size() % 2 == 0);
                const int dims = attribute_proto.ints_size() / 2;
                std::vector<int32_t> paddings;
                paddings.reserve(attribute_proto.ints_size());
                for (int i = 0; i < dims; ++i)
                {
                    paddings.push_back(attribute_proto.ints(i));
                    paddings.push_back(attribute_proto.ints(dims + i));
                }
                lp.set("paddings", DictValue::arrayInt(&paddings[0], paddings.size()));
            }
            else
            {
                // Convolution or pooling.
                CV_Assert(attribute_proto.ints_size() == 4);
                lp.set("pad_t", saturate_cast<int32_t>(attribute_proto.ints(0)));
                lp.set("pad_l", saturate_cast<int32_t>(attribute_proto.ints(1)));
                lp.set("pad_b", saturate_cast<int32_t>(attribute_proto.ints(2)));
                lp.set("pad_r", saturate_cast<int32_t>(attribute_proto.ints(3)));
            }
        }
        else if(attribute_name == "auto_pad")
        {
            if (attribute_proto.s() == "SAME_UPPER" || attribute_proto.s() == "SAME_LOWER") {
                lp.set("pad_mode",  "SAME");
            }
            else if (attribute_proto.s() == "VALID") {
                lp.set("pad_mode", "VALID");
            }
        }
        else if(attribute_name == "dilations")
        {
            CV_Assert(attribute_proto.ints_size() == 2);
            lp.set("dilation_h",  saturate_cast<int32_t>(attribute_proto.ints(0)));
            lp.set("dilation_w",  saturate_cast<int32_t>(attribute_proto.ints(1)));
        }
        else if (attribute_proto.has_i())
        {
            ::google::protobuf::int64 src = attribute_proto.i();
            if (src < std::numeric_limits<int32_t>::min() || src > std::numeric_limits<int32_t>::max())
                CV_Error(Error::StsOutOfRange, "Input is out of OpenCV 32S range");
            else
                lp.set(attribute_name, saturate_cast<int32_t>(src));
        }
        else if (attribute_proto.has_f())
        {
            lp.set(attribute_name, attribute_proto.f());
        }
        else if (attribute_proto.has_s())
        {
            lp.set(attribute_name, attribute_proto.s());
        }
        else if (attribute_proto.floats_size() > 0)
        {
            lp.set(attribute_name, DictValue::arrayReal(
                attribute_proto.floats().data(), attribute_proto.floats_size()));
        }
        else if (attribute_proto.ints_size() > 0)
        {
            const ::google::protobuf::RepeatedField< ::google::protobuf::int64> src = attribute_proto.ints();
            std::vector<int32_t> dst(attribute_proto.ints_size());
            convertInt64ToInt32(src, dst, attribute_proto.ints_size());
            lp.set(attribute_proto.name(), DictValue::arrayInt(&dst[0], attribute_proto.ints_size()));
        }
        else if (attribute_proto.has_t())
        {
            opencv_onnx::TensorProto tensor = attribute_proto.t();
            Mat blob = getMatFromTensor(tensor);
            lp.blobs.push_back(blob);
        }
        else if (attribute_proto.has_g() || attribute_proto.strings_size() > 0 ||
                    attribute_proto.tensors_size() > 0 || attribute_proto.graphs_size() > 0)
        {
                CV_Error(Error::StsNotImplemented, "Unexpected attribute type");
        }
        else
            CV_Error(Error::StsNotImplemented, "Unsupported attribute type");
    }
    return lp;
}
示例#16
0
TEST_P(Convolution, Accuracy)
{
    int inChannels = get<0>(GetParam())[0];
    int outChannels = get<0>(GetParam())[1];
    int group = get<0>(GetParam())[2];
    Size inSize = get<1>(GetParam());
    Size kernel = get<2>(GetParam());
    Size stride = get<3>(GetParam());
    Size pad = get<4>(GetParam());
    Size dilation = get<5>(GetParam());
    bool hasBias = get<6>(GetParam());

    Mat weights({outChannels, inChannels / group, kernel.height, kernel.width}, CV_32F);
    randu(weights, -1.0f, 1.0f);

    LayerParams lp;
    lp.set("kernel_w", kernel.width);
    lp.set("kernel_h", kernel.height);
    lp.set("pad_w", pad.width);
    lp.set("pad_h", pad.height);
    lp.set("stride_w", stride.width);
    lp.set("stride_h", stride.height);
    lp.set("dilation_w", dilation.width);
    lp.set("dilation_h", dilation.height);
    lp.set("num_output", outChannels);
    lp.set("group", group);
    lp.set("bias_term", hasBias);
    lp.type = "Convolution";
    lp.name = "testLayer";
    lp.blobs.push_back(weights);
    if (hasBias)
    {
        Mat bias({outChannels}, CV_32F);
        randu(bias, -1.0f, 1.0f);
        lp.blobs.push_back(bias);
    }
    Mat input({1, inChannels, inSize.height, inSize.width}, CV_32F);
    test(lp, input);
}
示例#17
0
TEST_P(Eltwise, Accuracy)
{
    Vec3i inSize = get<0>(GetParam());
    std::string op = get<1>(GetParam());
    int numConv = get<2>(GetParam());
    bool weighted = get<3>(GetParam());

    Net net;

    std::vector<int> convLayerIds(numConv);
    for (int i = 0; i < numConv; ++i)
    {
        Mat weights({inSize[0], 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", inSize[0]);
        convParam.set("bias_term", false);
        convParam.type = "Convolution";
        std::ostringstream ss;
        ss << "convLayer" << i;
        convParam.name = ss.str();
        convParam.blobs.push_back(weights);

        convLayerIds[i] = net.addLayer(convParam.name, convParam.type, convParam);
        net.connect(0, 0, convLayerIds[i], 0);
    }

    LayerParams eltwiseParam;
    eltwiseParam.set("operation", op);
    if (op == "sum" && weighted)
    {
        RNG rng = cv::theRNG();
        std::vector<float> coeff(1 + numConv);
        for (int i = 0; i < coeff.size(); ++i)
        {
            coeff[i] = rng.uniform(-2.0f, 2.0f);
        }
        eltwiseParam.set("coeff", DictValue::arrayReal<float*>(&coeff[0], coeff.size()));
    }
    eltwiseParam.type = "Eltwise";
    eltwiseParam.name = "testLayer";
    int eltwiseId = net.addLayer(eltwiseParam.name, eltwiseParam.type, eltwiseParam);
    net.connect(0, 0, eltwiseId, 0);
    for (int i = 0; i < numConv; ++i)
    {
        net.connect(convLayerIds[i], 0, eltwiseId, 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(eltwiseParam.name).clone();

    net.setPreferableBackend(DNN_BACKEND_HALIDE);
    Mat outputHalide = net.forward(eltwiseParam.name).clone();
    normAssert(outputDefault, outputHalide);
}