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);
}
////////////////////////////////////////////////////////////////////////////////
// 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);
}
}
//////////////////////////////////////////////////////////////////////////////
// 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);
}
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);
}
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();
}
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];
}
}
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;
}
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);
}
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);
}