C++ MatShape::size方法代码示例

    void blobFromProto(const caffe::BlobProto &pbBlob, cv::Mat &dstBlob)
    {
        MatShape shape;
        blobShapeFromProto(pbBlob, shape);

        dstBlob.create((int)shape.size(), &shape[0], CV_32F);
        if (pbBlob.data_size())
        {
            // Single precision floats.
            CV_Assert(pbBlob.data_size() == (int)dstBlob.total());

            CV_DbgAssert(pbBlob.GetDescriptor()->FindFieldByLowercaseName("data")->cpp_type() == FieldDescriptor::CPPTYPE_FLOAT);
            Mat(dstBlob.dims, &dstBlob.size[0], CV_32F, (void*)pbBlob.data().data()).copyTo(dstBlob);
        }
        else
        {
            CV_Assert(pbBlob.has_raw_data());
            const std::string& raw_data = pbBlob.raw_data();
            if (pbBlob.raw_data_type() == caffe::FLOAT16)
            {
                // Half precision floats.
                CV_Assert(raw_data.size() / 2 == (int)dstBlob.total());

                Mat halfs((int)shape.size(), &shape[0], CV_16SC1, (void*)raw_data.c_str());
                convertFp16(halfs, dstBlob);
            }
            else if (pbBlob.raw_data_type() == caffe::FLOAT)
            {
                CV_Assert(raw_data.size() / 4 == (int)dstBlob.total());
                Mat((int)shape.size(), &shape[0], CV_32FC1, (void*)raw_data.c_str()).copyTo(dstBlob);
            }
            else
                CV_Error(Error::StsNotImplemented, "Unexpected blob data type");
        }
    }

    void blobFromProto(const caffe::BlobProto &pbBlob, cv::Mat &dstBlob)
    {
        MatShape shape;
        blobShapeFromProto(pbBlob, shape);

        dstBlob.create((int)shape.size(), &shape[0], CV_32F);
        float *dstData = dstBlob.ptr<float>();
        if (pbBlob.data_size())
        {
            // Single precision floats.
            CV_Assert(pbBlob.data_size() == (int)dstBlob.total());

            CV_DbgAssert(pbBlob.GetDescriptor()->FindFieldByLowercaseName("data")->cpp_type() == FieldDescriptor::CPPTYPE_FLOAT);

            for (int i = 0; i < pbBlob.data_size(); i++)
                dstData[i] = pbBlob.data(i);
        }
        else
        {
            // Half precision floats.
            CV_Assert(pbBlob.raw_data_type() == caffe::FLOAT16);
            std::string raw_data = pbBlob.raw_data();

            CV_Assert(raw_data.size() / 2 == (int)dstBlob.total());

            Mat halfs((int)shape.size(), &shape[0], CV_16SC1, (void*)raw_data.c_str());
            convertFp16(halfs, dstBlob);
        }
    }

static MatShape getBufferShape(const MatShape& shape)
{
    if (shape.size() == 2 || shape.size() == 4)
    {
        int w, h, c, n;
        getCanonicalSize(shape, &w, &h, &c, &n);
        return {w, h, c, n};
    }
    else
    {
        MatShape bufferShape(shape);
        std::reverse(bufferShape.begin(), bufferShape.end());
        return bufferShape;
    }
}

inline void print(const MatShape& shape, const String& name = "")
{
    printf("%s: [", name.c_str());
    size_t i, n = shape.size();
    for( i = 0; i < n; i++ )
        printf(" %d", shape[i]);
    printf(" ]\n");
}

static inline int total(const MatShape& shape, int start = -1, int end = -1)
{
    if (start == -1) start = 0;
    if (end == -1) end = (int)shape.size();

    if (shape.empty())
        return 0;

    int elems = 1;
    CV_Assert(start <= (int)shape.size() && end <= (int)shape.size() &&
              start <= end);
    for(int i = start; i < end; i++)
    {
        elems *= shape[i];
    }
    return elems;
}

static inline std::string toString(const MatShape& shape, const String& name = "")
{
    std::ostringstream ss;
    if (!name.empty())
        ss << name << ' ';
    ss << '[';
    for(size_t i = 0, n = shape.size(); i < n; ++i)
        ss << ' ' << shape[i];
    ss << " ]";
    return ss.str();
}

 bool getMemoryShapes(const std::vector<MatShape> &inputs,
                      const int requiredOutputs,
                      std::vector<MatShape> &outputs,
                      std::vector<MatShape> &internals) const
 {
     bool inplace = Layer::getMemoryShapes(inputs, requiredOutputs, outputs, internals);
     MatShape shape = inputs[0];
     int cAxis = clamp(axisRaw, shape.size());
     shape[cAxis] = 1;
     internals.assign(1, shape);
     return inplace;
 }

    bool getMemoryShapes(const std::vector<MatShape> &inputs,
                         const int requiredOutputs,
                         std::vector<MatShape> &outputs,
                         std::vector<MatShape> &internals) const
    {
        CV_Assert(inputs.size() == 2);

        MatShape dstShape = inputs[0];
        int start = clamp(startAxis, dstShape);
        for (int i = start; i < dstShape.size(); i++)
        {
            dstShape[i] = inputs[1][i];
        }

        outputs.resize(1, dstShape);

        return false;
    }

void getCanonicalSize(const MatShape& shape, int* width, int* height,
                      int* channels, int* batch)
{
    const int dims = shape.size();
    CV_Assert(dims == 2 || dims == 4);
    *batch = shape[0];
    *channels = shape[1];
    if (dims == 4)
    {
        *width = shape[3];
        *height = shape[2];
    }
    else
    {
        *width = 1;
        *height = 1;
    }
}

    bool forward_ocl(InputArrayOfArrays inps, OutputArrayOfArrays outs, OutputArrayOfArrays internals)
    {
        std::vector<UMat> inputs;
        std::vector<UMat> outputs;

        inps.getUMatVector(inputs);
        outs.getUMatVector(outputs);

        for (size_t i = 0; i < inputs.size(); i++)
        {
            UMat srcBlob = inputs[i];
            void *src_handle = inputs[i].handle(ACCESS_READ);
            void *dst_handle = outputs[i].handle(ACCESS_WRITE);
            if (src_handle != dst_handle)
            {
                MatShape outShape = shape(outputs[i]);
                UMat umat = srcBlob.reshape(1, (int)outShape.size(), &outShape[0]);
                umat.copyTo(outputs[i]);
            }
        }
        outs.assign(outputs);

        return true;
    }

inline int clamp(int ax, const MatShape& shape)
{
    return clamp(ax, (int)shape.size());
}

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";
            }
//.........这里部分代码省略.........

static void computeShapeByReshapeMask(const MatShape &srcShape,
                                      const MatShape &maskShape,
                                      Range srcRange /*= Range::all()*/,
                                      MatShape& dstShape)
{
    int srcShapeSize = (int)srcShape.size();
    int maskShapeSize = (int)maskShape.size();

    if (srcRange == Range::all())
        srcRange = Range(0, srcShapeSize);
    else
    {
        int sz = srcRange.size();
        srcRange.start = clamp(srcRange.start, srcShapeSize);
        srcRange.end = srcRange.end == INT_MAX ? srcShapeSize : srcRange.start + sz;
    }

    bool explicitMask = !maskShape.empty();  // All mask values are positive.
    for (int i = 0, n = maskShape.size(); i < n && explicitMask; ++i)
    {
        explicitMask = maskShape[i] > 0;
    }
    // Working range of source shape is a range where area(src) == area(mask).
    if (explicitMask)
    {
        int maskTotal = total(maskShape);
        // Go from the end of mask until we collect required total.
        bool matched = false;
        for (int i = srcRange.end - 1; i >= srcRange.start; --i)
        {
            if (matched)
            {
                if (i == 0 || total(srcShape, i, srcRange.end) != maskTotal)
                {
                    srcRange.start = i + 1;
                    break;
                }
            }
            else
            {
                matched = total(srcShape, i, srcRange.end) == maskTotal;
            }
        }
        CV_Assert(total(srcShape, srcRange.start, srcRange.end) == maskTotal);
    }

    CV_Assert(0 <= srcRange.start && srcRange.start <= srcRange.end && srcRange.end <= srcShapeSize);
    int dstShapeSize = srcShapeSize - srcRange.size() + maskShapeSize;
    dstShape.resize(dstShapeSize);

    std::copy(srcShape.begin(), srcShape.begin() + srcRange.start, dstShape.begin());
    std::copy(srcShape.begin() + srcRange.end, srcShape.begin() + srcShapeSize, dstShape.begin() + srcRange.start + maskShapeSize);

    int inferDim = -1;
    for (int i = 0; i < maskShapeSize; i++)
    {
        if (maskShape[i] > 0)
        {
            dstShape[srcRange.start + i] = maskShape[i];
        }
        else if (maskShape[i] == 0)
        {
            if (srcRange.start + i >= srcShapeSize)
                CV_Error(Error::StsBadArg, format("Copy dim[%d] (which has zero size) is out of the source shape bounds", srcRange.start + i));
            dstShape[srcRange.start + i] = srcShape[srcRange.start + i];
        }
        else if (maskShape[i] == -1)
        {
            if (inferDim != -1)
                CV_Error(Error::StsAssert, "Duplicate of inferred dim (which is denoted by -1)");
            inferDim = srcRange.start + i;
            dstShape[inferDim] = 1;
        }
        else
            CV_Error(Error::StsBadArg, "maskShape[i] >= -1");
    }

    size_t srcTotal = total(srcShape);
    size_t dstTotal = total(dstShape);

    if (inferDim != -1)
    {
        if (srcTotal % dstTotal != 0)
            CV_Error(Error::StsBackTrace, "Can't infer a dim denoted by -1");

        dstShape[inferDim] = (int)(srcTotal / dstTotal);
    }
    else
    {
        CV_Assert(srcTotal == dstTotal);
    }
}

static void computeShapeByReshapeMask(const MatShape &srcShape,
                                      const MatShape &maskShape,
                                      Range srcRange /*= Range::all()*/,
                                      MatShape& dstShape)
{
    int srcShapeSize = (int)srcShape.size();
    int maskShapeSize = (int)maskShape.size();

    if (srcRange == Range::all())
        srcRange = Range(0, srcShapeSize);
    else
    {
        int sz = srcRange.size();
        srcRange.start = clamp(srcRange.start, srcShapeSize);
        srcRange.end = srcRange.end == INT_MAX ? srcShapeSize : srcRange.start + sz;
    }

    CV_Assert(0 <= srcRange.start && srcRange.start <= srcRange.end && srcRange.end <= srcShapeSize);
    int dstShapeSize = srcShapeSize - srcRange.size() + maskShapeSize;
    dstShape.resize(dstShapeSize);

    std::copy(srcShape.begin(), srcShape.begin() + srcRange.start, dstShape.begin());
    std::copy(srcShape.begin() + srcRange.end, srcShape.begin() + srcShapeSize, dstShape.begin() + srcRange.start + maskShapeSize);

    int inferDim = -1;
    for (int i = 0; i < maskShapeSize; i++)
    {
        if (maskShape[i] > 0)
        {
            dstShape[srcRange.start + i] = maskShape[i];
        }
        else if (maskShape[i] == 0)
        {
            if (srcRange.start + i >= srcShapeSize)
                CV_Error(Error::StsBadArg, format("Copy dim[%d] (which has zero size) is out of the source shape bounds", srcRange.start + i));
            dstShape[srcRange.start + i] = srcShape[srcRange.start + i];
        }
        else if (maskShape[i] == -1)
        {
            if (inferDim != -1)
                CV_Error(Error::StsAssert, "Duplicate of inferred dim (which is denoted by -1)");
            inferDim = srcRange.start + i;
            dstShape[inferDim] = 1;
        }
        else
            CV_Error(Error::StsBadArg, "maskShape[i] >= -1");
    }

    size_t srcTotal = total(srcShape);
    size_t dstTotal = total(dstShape);

    if (inferDim != -1)
    {
        if (srcTotal % dstTotal != 0)
            CV_Error(Error::StsBackTrace, "Can't infer a dim denoted by -1");

        dstShape[inferDim] = (int)(srcTotal / dstTotal);
    }
    else
    {
        CV_Assert(srcTotal == dstTotal);
    }
}

    bool forward_ocl(InputArrayOfArrays inputs_, OutputArrayOfArrays outputs_, OutputArrayOfArrays internals_)
    {
        std::vector<UMat> inputs;
        std::vector<UMat> outputs;
        std::vector<UMat> internals;

        inputs_.getUMatVector(inputs);
        outputs_.getUMatVector(outputs);
        internals_.getUMatVector(internals);

        CV_Assert(inputs.size() == 1 && outputs.size() == 1);
        CV_Assert(inputs[0].total() == outputs[0].total());

        const UMat& inp0 = inputs[0];
        UMat& buffer = internals[0];
        size_t num = inp0.size[0];
        size_t channels = inp0.size[1];
        size_t channelSize = inp0.total() / (num * channels);
        for (size_t i = 0; i < num; ++i)
        {
            MatShape s = shape(channels, channelSize);
            UMat src = inputs[i].reshape(1, s.size(), &s[0]);
            UMat dst = outputs[i].reshape(1, s.size(), &s[0]);

            UMat abs_mat;
            absdiff(src, cv::Scalar::all(0), abs_mat);
            pow(abs_mat, pnorm, buffer);

            if (acrossSpatial)
            {
                // add eps to avoid overflow
                float absSum = sum(buffer)[0] + epsilon;
                float norm = pow(absSum, 1.0f / pnorm);
                multiply(src, 1.0f / norm, dst);
            }
            else
            {
                Mat norm;
                reduce(buffer, norm, 0, REDUCE_SUM);
                norm += epsilon;

                // compute inverted norm to call multiply instead divide
                cv::pow(norm, -1.0f / pnorm, norm);

                repeat(norm, channels, 1, buffer);
                multiply(src, buffer, dst);
            }

            if (!blobs.empty())
            {
                // scale the output
                Mat scale = blobs[0];
                if (scale.total() == 1)
                {
                    // _scale: 1 x 1
                    multiply(dst, scale.at<float>(0, 0), dst);
                }
                else
                {
                    // _scale: _channels x 1
                    CV_Assert(scale.total() == channels);
                    repeat(scale, 1, dst.cols, buffer);
                    multiply(dst, buffer, dst);
                }
            }
        }
        return true;
    }