mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-06-08 01:53:19 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add a flag to manage average pooling with padding

Browse Source
This commit is contained in:
Dmitry Kurtaev 2018-02-14 16:56:31 +03:00
parent 252e871a8b
commit f8d0d6365e
5 changed files with 44 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
modules/dnn/include/opencv2/dnn/all_layers.hpp
View File

@ -239,6 +239,10 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
bool computeMaxIdx;
String padMode;
bool ceilMode;
// If true for average pooling with padding, divide an every output region
// by a whole kernel area. Otherwise exclude zero padded values and divide
// by number of real values.
bool avePoolPaddedArea;
// ROIPooling parameters.
Size pooledSize;
float spatialScale;

18
modules/dnn/src/layers/pooling_layer.cpp
View File

@ -106,6 +106,7 @@ public:
setParamsFrom(params);
ceilMode = params.get<bool>("ceil_mode", true);
spatialScale = params.get<float>("spatial_scale", 1);
avePoolPaddedArea = params.get<bool>("ave_pool_padded_area", true);
}
#ifdef HAVE_OPENCL
@ -259,7 +260,7 @@ public:
const Mat* src, *rois;
Mat *dst, *mask;
Size kernel, stride, pad;
String padMode;
bool avePoolPaddedArea;
int nstripes;
bool computeMaxIdx;
std::vector<int> ofsbuf;
@ -270,7 +271,7 @@ public:
computeMaxIdx(0), poolingType(MAX), spatialScale(0) {}
static void run(const Mat& src, const Mat& rois, Mat& dst, Mat& mask, Size kernel,
Size stride, Size pad, String padMode, int poolingType, float spatialScale,
Size stride, Size pad, bool avePoolPaddedArea, int poolingType, float spatialScale,
bool computeMaxIdx, int nstripes)
{
CV_Assert(src.isContinuous(), dst.isContinuous(),
@ -289,7 +290,7 @@ public:
p.kernel = kernel;
p.stride = stride;
p.pad = pad;
p.padMode = padMode;
p.avePoolPaddedArea = avePoolPaddedArea;
p.nstripes = nstripes;
p.computeMaxIdx = computeMaxIdx;
p.poolingType = poolingType;
@ -369,6 +370,7 @@ public:
yend = min(ystart + kernel_h, inp_height + pad_h);
srcData = src->ptr<float>(n, c);
}
int ydelta = yend - ystart;
ystart = max(ystart, 0);
yend = min(yend, inp_height);
float *dstData = dst->ptr<float>(n, c, y0);
@ -532,14 +534,14 @@ public:
}
else if (poolingType == AVE)
{
bool isSamePad = padMode == "SAME";
for( ; x0 < x1; x0++ )
{
int xstart = x0 * stride_w - pad_w;
int xend = min(xstart + kernel_w, inp_width + pad_w);
int xdelta = xend - xstart;
xstart = max(xstart, 0);
xend = min(xend, inp_width);
float inv_kernel_area = isSamePad ? (yend - ystart) * (xend - xstart) : kernel.area();
float inv_kernel_area = avePoolPaddedArea ? xdelta * ydelta : ((yend - ystart) * (xend - xstart));
inv_kernel_area = 1.0 / inv_kernel_area;
#if CV_SIMD128
if( xstart > 0 && x0 + 7 < x1 && (x0 + 7) * stride_w - pad_w + kernel_w < inp_width )
@ -651,21 +653,21 @@ public:
{
const int nstripes = getNumThreads();
Mat rois;
PoolingInvoker::run(src, rois, dst, mask, kernel, stride, pad, padMode, type, spatialScale, computeMaxIdx, nstripes);
PoolingInvoker::run(src, rois, dst, mask, kernel, stride, pad, avePoolPaddedArea, type, spatialScale, computeMaxIdx, nstripes);
}
void avePooling(Mat &src, Mat &dst)
{
const int nstripes = getNumThreads();
Mat rois, mask;
PoolingInvoker::run(src, rois, dst, mask, kernel, stride, pad, padMode, type, spatialScale, computeMaxIdx, nstripes);
PoolingInvoker::run(src, rois, dst, mask, kernel, stride, pad, avePoolPaddedArea, type, spatialScale, computeMaxIdx, nstripes);
}
void roiPooling(const Mat &src, const Mat &rois, Mat &dst)
{
const int nstripes = getNumThreads();
Mat mask;
PoolingInvoker::run(src, rois, dst, mask, kernel, stride, pad, padMode, type, spatialScale, computeMaxIdx, nstripes);
PoolingInvoker::run(src, rois, dst, mask, kernel, stride, pad, avePoolPaddedArea, type, spatialScale, computeMaxIdx, nstripes);
}
virtual Ptr<BackendNode> initMaxPoolingHalide(const std::vector<Ptr<BackendWrapper> > &inputs)

1
modules/dnn/src/tensorflow/tf_importer.cpp
View File

@ -1078,6 +1078,7 @@ void TFImporter::populateNet(Net dstNet)
else if (type == "AvgPool")
{
layerParams.set("pool", "ave");
layerParams.set("ave_pool_padded_area", false);
setKSize(layerParams, layer);
setStrides(layerParams, layer);

4
modules/dnn/src/torch/torch_importer.cpp
View File

@ -559,7 +559,11 @@ struct TorchImporter
layerParams.set("indices_blob_id", tensorParams["indices"].first);
}
if (nnName == "SpatialAveragePooling")
{
layerParams.set("pool", "AVE");
layerParams.set("ave_pool_padded_area", scalarParams.has("count_include_pad") &&
scalarParams.get<bool>("count_include_pad"));
}
convertTorchKernelsParams(scalarParams, layerParams);
CV_Assert(scalarParams.has("ceil_mode"));

25
modules/dnn/test/test_layers.cpp
View File

@ -806,4 +806,29 @@ INSTANTIATE_TEST_CASE_P(Layer_Test, Crop, Combine(
/*offset value*/ Values(3, 4)
));
// Check that by default average pooling layer should not count zero padded values
// into the normalization area.
TEST(Layer_Test_Average_pooling_kernel_area, Accuracy)
{
LayerParams lp;
lp.name = "testAvePool";
lp.type = "Pooling";
lp.set("kernel_size", 2);
lp.set("stride", 2);
lp.set("pool", "AVE");
Net net;
net.addLayerToPrev(lp.name, lp.type, lp);
// 1 2 | 3
// 4 5 | 6
// ----+--
// 7 8 | 9
Mat inp = (Mat_<float>(3, 3) << 1, 2, 3, 4, 5, 6, 7, 8, 9);
Mat target = (Mat_<float>(2, 2) << (1 + 2 + 4 + 5) / 4.f, (3 + 6) / 2.f, (7 + 8) / 2.f, 9);
Mat tmp = blobFromImage(inp);
net.setInput(blobFromImage(inp));
Mat out = net.forward();
normAssert(out, blobFromImage(target));
}
}} // namespace