void ConvolutionLayer::im2col(Blob &inpBlob, int imNum, int cnGroup)
{
uchar *srcPtr = inpBlob.ptr(imNum, cnGroup*inpGroupCn);
if (is1x1())
{
colMat = Mat(ksize, inpBlob.rows()*inpBlob.cols(), inpBlob.type(), srcPtr);
return;
}
#ifdef HAVE_OPENCL
if (useOpenCL && ocl::useOpenCL() && inpBlob.type() == CV_32F && !is1x1())
{
std::vector<Range> ranges(4, Range::all());
ranges[0] = Range(imNum, imNum+1);
ranges[1] = Range(cnGroup*inpGroupCn, (cnGroup + 1)*inpGroupCn);
UMat src = inpBlob.matRef()(&ranges[0]).getUMat(ACCESS_READ);
UMat dst(colMat.size(), colMat.type());
im2col_ocl(src, inpGroupCn, inpH, inpW, kerH, kerW, padH, padW, strideH, strideW, dst);
dst.copyTo(colMat);
return;
}
#endif // HAVE_OPENCL
if (inpBlob.type() == CV_32F)
im2col_cpu((float *)srcPtr, inpGroupCn, inpH, inpW, kerH, kerW, padH, padW, strideH, strideW, (float *)colMat.ptr());
if (inpBlob.type() == CV_64F)
im2col_cpu((double*)srcPtr, inpGroupCn, inpH, inpW, kerH, kerW, padH, padW, strideH, strideW, (double*)colMat.ptr());
}
void DeConvolutionLayer::computeInpOutShape(const Blob &inpBlob)
{
outH = inpBlob.rows();
outW = inpBlob.cols();
outCn = inpBlob.channels();
inpH = strideH * (outH - 1) + kerH - 2 * padH;
inpW = strideW * (outW - 1) + kerW - 2 * padW;
inpCn = numOutput;
topH = inpH; topW = inpW; topCn = inpCn;
}
void ConvolutionLayer::computeInpOutShape(const Blob &inpBlob)
{
inpH = inpBlob.rows();
inpW = inpBlob.cols();
inpCn = inpBlob.channels();
outH = (inpH + 2 * padH - kerH) / strideH + 1;
outW = (inpW + 2 * padW - kerW) / strideW + 1;
outCn = numOutput;
topH = outH; topW = outW; topCn = outCn;
}
static void colorizeSegmentation(Blob &score, Mat &segm, Mat &legend, vector<String> &classNames)
{
const int rows = score.rows();
const int cols = score.cols();
const int chns = score.channels();
vector<Vec3i> colors;
RNG rng(12345678);
cv::Mat maxCl(rows, cols, CV_8UC1);
cv::Mat maxVal(rows, cols, CV_32FC1);
for (int ch = 0; ch < chns; ch++)
{
colors.push_back(Vec3i(rng.uniform(0, 256), rng.uniform(0, 256), rng.uniform(0, 256)));
for (int row = 0; row < rows; row++)
{
const float *ptrScore = score.ptrf(0, ch, row);
uchar *ptrMaxCl = maxCl.ptr<uchar>(row);
float *ptrMaxVal = maxVal.ptr<float>(row);
for (int col = 0; col < cols; col++)
{
if (ptrScore[col] > ptrMaxVal[col])
{
ptrMaxVal[col] = ptrScore[col];
ptrMaxCl[col] = ch;
}
}
}
}
segm.create(rows, cols, CV_8UC3);
for (int row = 0; row < rows; row++)
{
const uchar *ptrMaxCl = maxCl.ptr<uchar>(row);
cv::Vec3b *ptrSegm = segm.ptr<cv::Vec3b>(row);
for (int col = 0; col < cols; col++)
{
ptrSegm[col] = colors[ptrMaxCl[col]];
}
}
if (classNames.size() == colors.size())
{
int blockHeight = 30;
legend.create(blockHeight*classNames.size(), 200, CV_8UC3);
for(int i = 0; i < classNames.size(); i++)
{
cv::Mat block = legend.rowRange(i*blockHeight, (i+1)*blockHeight);
block = colors[i];
putText(block, classNames[i], Point(0, blockHeight/2), FONT_HERSHEY_SIMPLEX, 0.5, Scalar());
}
}
}
void PoolingLayerImpl::maxPooling_cpu(Blob &src, Blob &dst)
{
CV_DbgAssert(dst.rows() == out.height && dst.cols() == out.width);
for (int n = 0; n < src.num(); ++n)
{
for (int c = 0; c < src.channels(); ++c)
{
const float *srcData = src.ptrf(n, c);
float *dstData = dst.ptrf(n, c);
for (int ph = 0; ph < out.height; ++ph)
{
for (int pw = 0; pw < out.width; ++pw)
{
int hstart = ph * stride.height - pad.height;
int wstart = pw * stride.width - pad.width;
int hend = min(hstart + kernel.height, inp.height);
int wend = min(wstart + kernel.width, inp.width);
hstart = max(hstart, 0);
wstart = max(wstart, 0);
const int poolIndex = ph * out.width + pw;
float max_val = -FLT_MAX;
for (int h = hstart; h < hend; ++h)
for (int w = wstart; w < wend; ++w)
{
const int index = h * inp.width + w;
if (srcData[index] > max_val)
max_val = srcData[index];
}
dstData[poolIndex] = max_val;
}
}
}
}
}
