mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2024-11-28 21:20:18 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #12128 from dkurt:dnn_fix_12066

Browse Source
This commit is contained in:
Alexander Alekhin 2018-08-10 14:14:16 +00:00
commit 615883977f
5 changed files with 79 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
modules/dnn/src/layers/reshape_layer.cpp
View File

@ -186,15 +186,20 @@ public:
std::vector<MatShape> &outputs,
std::vector<MatShape> &internals) const CV_OVERRIDE
{
outputs.clear();
for (size_t i = 0; i < inputs.size(); i++)
if (inputs.size() == 1 || inputs.size() == requiredOutputs)
{
outputs.push_back(MatShape());
computeShapeByReshapeMask(inputs[i], newShapeDesc, newShapeRange, outputs.back());
outputs.clear();
for (size_t i = 0; i < inputs.size(); i++)
{
outputs.push_back(MatShape());
computeShapeByReshapeMask(inputs[i], newShapeDesc, newShapeRange, outputs.back());
}
}
else
{
CV_Assert(inputs.size() == 2, total(inputs[0]) == total(inputs[1]));
outputs.assign(1, inputs[1]);
}
internals = outputs;
return true;
}
@ -206,7 +211,7 @@ public:
inps.getUMatVector(inputs);
outs.getUMatVector(outputs);
for (size_t i = 0; i < inputs.size(); i++)
for (size_t i = 0; i < outputs.size(); i++)
{
UMat srcBlob = inputs[i];
void *src_handle = inputs[i].handle(ACCESS_READ);
@ -240,7 +245,7 @@ public:
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
for (size_t i = 0; i < inputs.size(); i++)
for (size_t i = 0; i < outputs.size(); i++)
{
Mat srcBlob = *inputs[i];
if (outputs[i].data != srcBlob.data)
@ -248,7 +253,7 @@ public:
}
}
virtual Ptr<BackendNode> initInfEngine(const std::vector<Ptr<BackendWrapper> >&) CV_OVERRIDE
virtual Ptr<BackendNode> initInfEngine(const std::vector<Ptr<BackendWrapper> >& inputs) CV_OVERRIDE
{
#ifdef HAVE_INF_ENGINE
InferenceEngine::LayerParams lp;
@ -256,7 +261,15 @@ public:
lp.type = "Reshape";
lp.precision = InferenceEngine::Precision::FP32;
std::shared_ptr<InferenceEngine::ReshapeLayer> ieLayer(new InferenceEngine::ReshapeLayer(lp));
ieLayer->shape = newShapeDesc;
if (!newShapeDesc.empty())
ieLayer->shape = newShapeDesc;
else
{
CV_Assert(inputs.size() == 2);
InferenceEngine::DataPtr shapeSrc = infEngineDataNode(inputs[1]);
// NOTE: shapeSrc->dims are reversed
ieLayer->shape = std::vector<int>(shapeSrc->dims.rbegin(), shapeSrc->dims.rend());
}
return Ptr<BackendNode>(new InfEngineBackendNode(ieLayer));
#endif // HAVE_INF_ENGINE
return Ptr<BackendNode>();

6
modules/dnn/src/op_inf_engine.cpp
View File

@ -524,8 +524,7 @@ Mat infEngineBlobToMat(const InferenceEngine::Blob::Ptr& blob)
{
// NOTE: Inference Engine sizes are reversed.
std::vector<size_t> dims = blob->dims();
std::vector<int> size(dims.begin(), dims.end());
std::reverse(size.begin(), size.end());
std::vector<int> size(dims.rbegin(), dims.rend());
return Mat(size, CV_32F, (void*)blob->buffer());
}
@ -540,8 +539,7 @@ bool InfEngineBackendLayer::getMemoryShapes(const std::vector<MatShape> &inputs,
std::vector<MatShape> &internals) const
{
std::vector<size_t> dims = output->dims;
std::vector<int> shape(dims.begin(), dims.end());
std::reverse(shape.begin(), shape.end());
std::vector<int> shape(dims.rbegin(), dims.rend());
outputs.assign(1, shape);
return false;
}

14
modules/dnn/src/tensorflow/tf_graph_simplifier.cpp
View File

@ -615,6 +615,19 @@ public:
}
};
class ReshapeAsShapeSubgraph : public Subgraph
{
public:
ReshapeAsShapeSubgraph()
{
int input = addNodeToMatch("");
int shapeSrc = addNodeToMatch("");
int shape = addNodeToMatch("Shape", shapeSrc);
addNodeToMatch("Reshape", input, shape);
setFusedNode("Reshape", input, shapeSrc);
}
};
void simplifySubgraphs(tensorflow::GraphDef& net)
{
std::vector<Ptr<Subgraph> > subgraphs;
@ -630,6 +643,7 @@ void simplifySubgraphs(tensorflow::GraphDef& net)
subgraphs.push_back(Ptr<Subgraph>(new DeconvolutionSameKerasSubgraph()));
subgraphs.push_back(Ptr<Subgraph>(new ResizeBilinearSubgraph()));
subgraphs.push_back(Ptr<Subgraph>(new UpsamplingKerasSubgraph()));
subgraphs.push_back(Ptr<Subgraph>(new ReshapeAsShapeSubgraph()));
int numNodes = net.node_size();
std::vector<int> matchedNodesIds;

63
modules/dnn/src/tensorflow/tf_importer.cpp
View File

@ -1038,37 +1038,50 @@ void TFImporter::populateNet(Net dstNet)
else if (type == "Reshape")
{
Pin inpId = parsePin(layer.input(0));
Mat newShape = getTensorContent(getConstBlob(layer, value_id, 1));
int inpLayout = getDataLayout(layer.input(0), data_layouts);
if (newShape.total() != 4 && inpLayout == DATA_LAYOUT_NHWC)
// There are two possible implementations: reshape an input using
// predefined sizes or use a second input blob as a source of new shape.
if (value_id.find(layer.input(1)) != value_id.end())
{
LayerParams permLP;
int order[] = {0, 2, 3, 1}; // From OpenCV's NCHW to NHWC.
permLP.set("order", DictValue::arrayInt<int*>(order, 4));
Mat newShape = getTensorContent(getConstBlob(layer, value_id, 1));
std::string permName = name + "/nchw";
CV_Assert(layer_id.find(permName) == layer_id.end());
int permId = dstNet.addLayer(permName, "Permute", permLP);
layer_id[permName] = permId;
connect(layer_id, dstNet, inpId, permId, 0);
inpId = Pin(permName);
inpLayout = DATA_LAYOUT_NCHW;
if (newShape.total() != 4 && inpLayout == DATA_LAYOUT_NHWC)
{
LayerParams permLP;
int order[] = {0, 2, 3, 1}; // From OpenCV's NCHW to NHWC.
permLP.set("order", DictValue::arrayInt<int*>(order, 4));
std::string permName = name + "/nchw";
CV_Assert(layer_id.find(permName) == layer_id.end());
int permId = dstNet.addLayer(permName, "Permute", permLP);
layer_id[permName] = permId;
connect(layer_id, dstNet, inpId, permId, 0);
inpId = Pin(permName);
inpLayout = DATA_LAYOUT_NCHW;
}
else if (newShape.total() == 4 && inpLayout == DATA_LAYOUT_NHWC)
{
// NHWC->NCHW
std::swap(*newShape.ptr<int32_t>(0, 2), *newShape.ptr<int32_t>(0, 3));
std::swap(*newShape.ptr<int32_t>(0, 1), *newShape.ptr<int32_t>(0, 2));
}
layerParams.set("dim", DictValue::arrayInt<int*>(newShape.ptr<int>(), newShape.total()));
int id = dstNet.addLayer(name, "Reshape", layerParams);
layer_id[name] = id;
// one input only
connect(layer_id, dstNet, inpId, id, 0);
data_layouts[name] = newShape.total() == 2 ? DATA_LAYOUT_PLANAR : inpLayout;
}
else if (newShape.total() == 4 && inpLayout == DATA_LAYOUT_NHWC)
else
{
// NHWC->NCHW
std::swap(*newShape.ptr<int32_t>(0, 2), *newShape.ptr<int32_t>(0, 3));
std::swap(*newShape.ptr<int32_t>(0, 1), *newShape.ptr<int32_t>(0, 2));
int id = dstNet.addLayer(name, "Reshape", layerParams);
layer_id[name] = id;
connect(layer_id, dstNet, inpId, id, 0);
connect(layer_id, dstNet, parsePin(layer.input(1)), id, 1);
data_layouts[name] = inpLayout;
}
layerParams.set("dim", DictValue::arrayInt<int*>(newShape.ptr<int>(), newShape.total()));
int id = dstNet.addLayer(name, "Reshape", layerParams);
layer_id[name] = id;
// one input only
connect(layer_id, dstNet, inpId, id, 0);
data_layouts[name] = newShape.total() == 2 ? DATA_LAYOUT_PLANAR : inpLayout;
}
else if (type == "Flatten" || type == "Squeeze")
{

1
modules/dnn/test/test_tf_importer.cpp
View File

@ -212,6 +212,7 @@ TEST_P(Test_TensorFlow_layers, reshape)
runTensorFlowNet("shift_reshape_no_reorder");
runTensorFlowNet("reshape_no_reorder");
runTensorFlowNet("reshape_reduce");
runTensorFlowNet("reshape_as_shape");
}
TEST_P(Test_TensorFlow_layers, flatten)