potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 07:13:02 +04:00
Code Packages Releases Wiki Activity

Remove Shift deep learning layer

Browse Source
This commit is contained in:
Dmitry Kurtaev
2018-05-28 18:13:32 +03:00
parent 29421d7def
commit 2c3c59d018
4 changed files with 95 additions and 173 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/src/layers/scale_layer.cpp
+67 -20
View File
@@ -28,6 +28,7 @@ public:
setParamsFrom(params);
hasBias = params.get<bool>("bias_term", false);
axis = params.get<int>("axis", 1);
hasWeights = false;
}
bool getMemoryShapes(const std::vector<MatShape> &inputs,
@@ -35,11 +36,16 @@ public:
std::vector<MatShape> &outputs,
std::vector<MatShape> &internals) const CV_OVERRIDE
{
CV_Assert(inputs.size() == 2 && blobs.empty() || blobs.size() == 1 + hasBias);
outputs.assign(1, inputs[0]);
return true;
}
virtual void finalize(const std::vector<Mat*> &inputs, std::vector<Mat> &outputs) CV_OVERRIDE
{
hasWeights = blobs.size() == 2 || (blobs.size() == 1 && !hasBias);
CV_Assert(inputs.size() == 2 && blobs.empty() || blobs.size() == (int)hasWeights + (int)hasBias);
}
virtual bool supportBackend(int backendId) CV_OVERRIDE
{
return backendId == DNN_BACKEND_DEFAULT ||
@@ -63,10 +69,15 @@ public:
Mat &inpBlob = *inputs[0];
Mat &outBlob = outputs[0];
Mat &weights = blobs.empty() ? *inputs[1] : blobs[0];
Mat bias = hasBias ? blobs.back() : Mat();
// There is a mode when we multiply a first blob by a second one
// instead of trainable weights.
Mat weights = blobs.empty() ? *inputs[1] : (hasWeights ? blobs[0] : Mat());
Mat bias = hasBias ? blobs.back().reshape(1, 1) : Mat();
if (!weights.empty())
weights = weights.reshape(1, 1);
MatShape inpShape = shape(inpBlob);
const int numWeights = weights.total();
const int numWeights = !weights.empty() ? weights.total() : bias.total();
CV_Assert(numWeights != 0, !hasWeights || !hasBias || weights.total() == bias.total());
int endAxis;
for (endAxis = axis + 1; endAxis <= inpBlob.dims; ++endAxis)
@@ -84,15 +95,15 @@ public:
if (endAxis != inpBlob.dims)
{
float* weightsData = (float*)weights.data;
float* weightsData = !weights.empty() ? (float*)weights.data : 0;
float* biasesData = hasBias ? (float*)bias.data : 0;
int spatialSize = total(inpShape, endAxis); // spatialSize != 1
for (int i = 0; i < numSlices; ++i)
{
for (int j = 0; j < numWeights; ++j)
{
float w = weightsData[j];
float b = hasBias ? biasesData[j] : 0;
float w = weightsData ? weightsData[j] : 1;
float b = biasesData ? biasesData[j] : 0;
Mat inpSlice(1, spatialSize, CV_32F, inpData);
Mat outSlice(1, spatialSize, CV_32F, outData);
inpSlice.convertTo(outSlice, CV_32F, w, b);
@@ -105,12 +116,16 @@ public:
{
for (int i = 0; i < numSlices; ++i)
{
Mat inpSlice(weights.dims, weights.size, CV_32F, inpData);
Mat outSlice(weights.dims, weights.size, CV_32F, outData);
multiply(inpSlice, weights, outSlice);
if (hasBias)
add(outSlice, bias, outSlice);
Mat inpSlice(1, numWeights, CV_32F, inpData);
Mat outSlice(1, numWeights, CV_32F, outData);
if (!weights.empty())
{
multiply(inpSlice, weights, outSlice);
if (hasBias)
add(outSlice, bias, outSlice);
}
else if (hasBias)
add(inpSlice, bias, outSlice);
inpData += numWeights;
outData += numWeights;
}
@@ -157,11 +172,15 @@ public:
const int numChannels = blobs[0].total();
auto weights = wrapToHalideBuffer(blobs[0], {numChannels});
Halide::Expr topExpr = input * weights(c);
Halide::Expr topExpr = input;
if (hasWeights)
{
auto weights = wrapToHalideBuffer(blobs[0], {numChannels});
topExpr *= weights(c);
}
if (hasBias)
{
auto bias = wrapToHalideBuffer(blobs[1], {numChannels});
auto bias = wrapToHalideBuffer(blobs.back(), {numChannels});
topExpr += bias(c);
}
top(x, y, c, n) = topExpr;
@@ -178,10 +197,24 @@ public:
lp.precision = InferenceEngine::Precision::FP32;
std::shared_ptr<InferenceEngine::ScaleShiftLayer> ieLayer(new InferenceEngine::ScaleShiftLayer(lp));
CV_Assert(!blobs.empty());
const size_t numChannels = blobs[0].total();
ieLayer->_weights = wrapToInfEngineBlob(blobs[0], {numChannels}, InferenceEngine::Layout::C);
if (hasWeights)
{
ieLayer->_weights = wrapToInfEngineBlob(blobs[0], {numChannels}, InferenceEngine::Layout::C);
}
else
{
auto weights = InferenceEngine::make_shared_blob<float>(InferenceEngine::Precision::FP32,
{numChannels});
weights->allocate();
std::vector<float> ones(numChannels, 1);
weights->set(ones);
ieLayer->_weights = weights;
}
if (hasBias)
ieLayer->_biases = wrapToInfEngineBlob(blobs[1], {numChannels}, InferenceEngine::Layout::C);
ieLayer->_biases = wrapToInfEngineBlob(blobs.back(), {numChannels}, InferenceEngine::Layout::C);
return Ptr<BackendNode>(new InfEngineBackendNode(ieLayer));
#endif // HAVE_INF_ENGINE
@@ -190,8 +223,8 @@ public:
void getScaleShift(Mat& scale, Mat& shift) const CV_OVERRIDE
{
scale = !blobs.empty() ? blobs[0] : Mat();
shift = hasBias ? blobs[1] : Mat();
scale = hasWeights ? blobs[0] : Mat();
shift = hasBias ? blobs.back() : Mat();
}
virtual int64 getFLOPS(const std::vector<MatShape> &inputs,
@@ -205,6 +238,9 @@ public:
}
return flops;
}
private:
bool hasWeights;
};
@@ -213,5 +249,16 @@ Ptr<ScaleLayer> ScaleLayer::create(const LayerParams& params)
return Ptr<ScaleLayer>(new ScaleLayerImpl(params));
}
Ptr<Layer> ShiftLayer::create(const LayerParams& params)
{
LayerParams scaleParams;
scaleParams.name = params.name;
scaleParams.type = "Scale";
scaleParams.blobs = params.blobs;
scaleParams.set("bias_term", true);
scaleParams.set("axis", 0);
return Ptr<ScaleLayer>(new ScaleLayerImpl(scaleParams));
}
} // namespace dnn
} // namespace cv