potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 23:33:05 +04:00
Code Packages Releases Wiki Activity

Swap dimensions of deconvolution kernel

Browse Source
This commit is contained in:
Dmitry Kurtaev
2017-09-27 18:58:50 +03:00
parent 0f0f5652fb
commit 6e593cd1f0
5 changed files with 40 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/src/layers/convolution_layer.cpp
+35 -40
View File
@@ -252,24 +252,13 @@ public:
}
Halide::RDom r(0, kernel.width, 0, kernel.height, 0, inpGroupCn);
Halide::Expr kc = r.z;
if (group > 1)
{
int outCnBound = outGroupCn;
int inpChBound = inpGroupCn;
Halide::Expr shift = select(c < outCnBound, 0, inpChBound);
for (int i = 2; i < group; ++i)
{
outCnBound += outGroupCn;
inpChBound += inpGroupCn;
shift = select(c < outCnBound, shift, inpChBound);
}
kc += shift;
}
Halide::Expr kx = x * stride.width - pad.width + r.x * dilation.width;
Halide::Expr ky = y * stride.height - pad.height + r.y * dilation.height;
Halide::Expr kc = r.z;
for (int i = 1; i < group; ++i)
{
kc = select(c < outGroupCn * i, kc, inpGroupCn * i + r.z);
}
Halide::Expr topExpr = sum(padded_input(kx, ky, kc, n) *
weights(r.x, r.y, r.z, c));
if (hasBias())
@@ -278,7 +267,6 @@ public:
topExpr += bias(c);
}
top(x, y, c, n) = topExpr;
Ptr<BackendNode> pp(new HalideBackendNode({ padded_input, top }));
return Ptr<BackendNode>(new HalideBackendNode({ padded_input, top }));
#endif // HAVE_HALIDE
return Ptr<BackendNode>();
@@ -793,7 +781,7 @@ public:
int inpH = inpShape[2];
int inpW = inpShape[3];
int outCn = outShape[1];
int ngroups = inpCn / blobs[0].size[1];
int ngroups = inpCn / blobs[0].size[0];
int outGroupCn = outCn / ngroups;
int ksize = outGroupCn * kernel.height * kernel.width;
return shape(ksize, inpH * inpW);
@@ -804,7 +792,7 @@ public:
std::vector<MatShape> &outputs,
std::vector<MatShape> &internals) const
{
CV_Assert(!hasBias() || blobs[1].total() == (size_t)blobs[0].size[0]);
CV_Assert(!hasBias() || blobs[1].total() == (size_t)numOutput);
CV_Assert(inputs.size() != 0);
int inpCn = inputs[0][1];
@@ -813,12 +801,13 @@ public:
int outH = stride.height * (inpH - 1) + kernel.height - 2 * pad.height + adjustPad.height;
int outW = stride.width * (inpW - 1) + kernel.width - 2 * pad.width + adjustPad.width;
int outCn = blobs[0].size[0];
int outCn = numOutput;
int ngroups = inpCn / blobs[0].size[1];
CV_Assert(outCn % blobs[0].size[1] == 0);
int ngroups = outCn / blobs[0].size[1];
CV_Assert(inpCn % ngroups == 0 && outCn % ngroups == 0);
CV_Assert(blobs[0].size[0] == outCn && blobs[0].size[1] == inpCn / ngroups);
CV_Assert(blobs[0].size[0] == inpCn);
int dims[] = {inputs[0][0], outCn, outH, outW};
outputs.resize(inputs.size(), shape(dims));
@@ -1073,7 +1062,7 @@ public:
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
int outCn = blobs[0].size[0];
int outCn = numOutput;
int inpCn = inputs[0]->size[1];
bool is1x1flag = is1x1();
int nstripes = getNumThreads();
@@ -1086,9 +1075,9 @@ public:
for (size_t ii = 0; ii < outputs.size(); ii++)
{
int ngroups = inpCn / blobs[0].size[1];
int inpGroupCn = blobs[0].size[1];
int outGroupCn = outCn / ngroups;
int ngroups = outCn / blobs[0].size[1];
int inpGroupCn = inpCn / ngroups;
int outGroupCn = blobs[0].size[1];
const Mat& inp = *inputs[ii];
Mat& out = outputs[ii];
int numImg = inp.size[0];
@@ -1126,18 +1115,16 @@ public:
#ifdef HAVE_HALIDE
Halide::Buffer<float> inputBuffer = halideBuffer(inputs[0]);
int inW, inH, inC, inN, outC = blobs[0].size[0];
int inW, inH, inC, inN;
getCanonicalSize(inputBuffer, &inW, &inH, &inC, &inN);
if (inC / blobs[0].size[1] != 1)
CV_Error(cv::Error::StsNotImplemented,
"Halide backend for Deconvolution with group > 1 is not implemented");
const int outGroupCn = blobs[0].size[1];
const int group = numOutput / outGroupCn;
const int inpGroupCn = blobs[0].size[0] / group;
Halide::Var x("x"), y("y"), c("c"), n("n");
Halide::Func top = (name.empty() ? Halide::Func() : Halide::Func(name));
Halide::Func padded_input(name + "_constant_exterior");
auto weights = wrapToHalideBuffer(blobs[0], {kernel.width,
kernel.height, outC, inC});
auto weights = wrapToHalideBuffer(blobs[0]);
Halide::Func dilated_input("dilated_input");
dilated_input(x, y, c, n) = 0.0f;
@@ -1153,13 +1140,21 @@ public:
0, inC, 0, inN);
padded_input(x, y, c, n) = bounded(x, y, c, n);
Halide::RDom r(0, kernel.width, 0, kernel.height, 0, inC);
Halide::Expr topExpr = sum(
padded_input(x + pad.width - r.x, y + pad.height - r.y, r.z, n) *
weights(r.x, r.y, c, r.z));
Halide::RDom r(0, kernel.width, 0, kernel.height, 0, inpGroupCn);
Halide::Expr kx = x + pad.width - r.x;
Halide::Expr ky = y + pad.height - r.y;
Halide::Expr kInC = r.z;
Halide::Expr kOutC = c;
for (int i = 1; i < group; ++i)
{
kInC = select(c < outGroupCn * i, kInC, inpGroupCn * i + r.z);
kOutC = select(c < outGroupCn * i, kOutC, c - outGroupCn * i);
}
Halide::Expr topExpr = sum(padded_input(kx, ky, kInC, n) *
weights(r.x, r.y, kOutC, kInC));
if (hasBias())
{
auto bias = wrapToHalideBuffer(blobs[1], {outC});
auto bias = wrapToHalideBuffer(blobs[1], {numOutput});
topExpr += bias(c);
}
top(x, y, c, n) = topExpr;
@@ -1194,13 +1189,13 @@ static void initConvDeconvLayerFromCaffe(Ptr<BaseConvolutionLayer> l, const Laye
l->dilation.width, l->padMode);
bool bias = params.get<bool>("bias_term", true);
int numOutput = params.get<int>("num_output");
l->numOutput = params.get<int>("num_output");
int ngroups = params.get<int>("group", 1);
l->adjustPad.height = params.get<int>("adj_h", 0);
l->adjustPad.width = params.get<int>("adj_w", 0);
CV_Assert(numOutput % ngroups == 0);
CV_Assert(l->numOutput % ngroups == 0);
CV_Assert((bias && l->blobs.size() == 2) || (!bias && l->blobs.size() == 1));
CV_Assert(l->adjustPad.width < l->stride.width &&
l->adjustPad.height < l->stride.height);