ReorgLayerImpl(const LayerParams& params)
{
setParamsFrom(params);
reorgStride = params.get<int>("reorg_stride", 2);
CV_Assert(reorgStride > 0);
}
MaxUnpoolLayerImpl(const LayerParams& params)
{
setParamsFrom(params);
poolKernel = Size(params.get<int>("pool_k_w"), params.get<int>("pool_k_h"));
poolPad = Size(params.get<int>("pool_pad_w"), params.get<int>("pool_pad_h"));
poolStride = Size(params.get<int>("pool_stride_w"), params.get<int>("pool_stride_h"));
}
NormalizeBBoxLayerImpl(const LayerParams ¶ms)
{
_eps = getParameter<float>(params, "eps", 0, false, 1e-10f);
_across_spatial = getParameter<bool>(params, "across_spatial");
_channel_shared = getParameter<bool>(params, "channel_shared");
setParamsFrom(params);
}
NormalizeBBoxLayerImpl(const LayerParams& params)
{
setParamsFrom(params);
pnorm = params.get<float>("p", 2);
epsilon = params.get<float>("eps", 1e-10f);
acrossSpatial = params.get<bool>("across_spatial", true);
CV_Assert(pnorm > 0);
}
ResizeNearestNeighborLayerImpl(const LayerParams& params)
{
setParamsFrom(params);
CV_Assert(params.has("width"), params.has("height"));
outWidth = params.get<float>("width");
outHeight = params.get<float>("height");
alignCorners = params.get<bool>("align_corners", false);
if (alignCorners)
CV_Error(Error::StsNotImplemented, "Nearest neighborhood resize with align_corners=true is not implemented");
}
CropLayerImpl(const LayerParams& params)
{
setParamsFrom(params);
startAxis = params.get<int>("axis", 2);
const DictValue *paramOffset = params.ptr("offset");
if (paramOffset)
{
for (int i = 0; i < paramOffset->size(); i++)
offset.push_back(paramOffset->get<int>(i));
}
}
SplitLayerImpl(const LayerParams ¶ms)
{
setParamsFrom(params);
//TODO: maybe "top_count" param is useless because it can be determined by output connections number
if (params.has("top_count"))
{
outputsCount = params.get<int>("top_count");
CV_Assert(outputsCount >= 0);
}
else
{
outputsCount = -1;
}
}
ReshapeLayerImpl(const LayerParams& params)
{
setParamsFrom(params);
int axis = params.get<int>("axis", 0);
int numAxes = params.get<int>("num_axes", -1);
CV_Assert(numAxes >= -1);
newShapeRange = (numAxes == -1) ? Range(axis, INT_MAX) : Range(axis, axis + numAxes);
newShapeDesc.clear();
if (params.has("dim"))
{
const DictValue ¶mShape = params.get("dim");
int i, dims = paramShape.size();
newShapeDesc.resize(dims);
for (i = 0; i < dims; i++)
newShapeDesc[i] = paramShape.get<int>(i);
}
}
PaddingLayerImpl(const LayerParams ¶ms)
{
setParamsFrom(params);
paddingValue = params.get<float>("value", 0);
inputDims = params.get<int>("input_dims", -1);
paddingType = params.get<String>("type", "constant");
CV_Assert(params.has("paddings"));
const DictValue& paddingsParam = params.get("paddings");
CV_Assert((paddingsParam.size() & 1) == 0);
paddings.resize(paddingsParam.size() / 2);
for (int i = 0; i < paddings.size(); ++i)
{
paddings[i].first = paddingsParam.get<int>(i * 2); // Pad before.
paddings[i].second = paddingsParam.get<int>(i * 2 + 1); // Pad after.
CV_Assert(paddings[i].first >= 0, paddings[i].second >= 0);
}
}
LSTMLayerImpl(const LayerParams& params)
: numTimeStamps(0), numSamples(0)
{
setParamsFrom(params);
if (!blobs.empty())
{
CV_Assert(blobs.size() >= 3);
blobs[2] = blobs[2].reshape(1, 1);
const Mat& Wh = blobs[0];
const Mat& Wx = blobs[1];
const Mat& bias = blobs[2];
CV_Assert(Wh.dims == 2 && Wx.dims == 2);
CV_Assert(Wh.rows == Wx.rows);
CV_Assert(Wh.rows == 4*Wh.cols);
CV_Assert(Wh.rows == (int)bias.total());
CV_Assert(Wh.type() == Wx.type() && Wx.type() == bias.type());
// Peephole weights.
if (blobs.size() > 3)
{
CV_Assert(blobs.size() == 6);
const int N = Wh.cols;
for (int i = 3; i < 6; ++i)
{
CV_Assert(blobs[i].rows == N && blobs[i].cols == N);
CV_Assert(blobs[i].type() == bias.type());
}
}
}
useTimestampDim = params.get<bool>("use_timestamp_dim", true);
produceCellOutput = params.get<bool>("produce_cell_output", false);
forgetBias = params.get<float>("forget_bias", 0.0f);
cellClip = params.get<float>("cell_clip", 0.0f);
useCellClip = params.get<bool>("use_cell_clip", false);
usePeephole = params.get<bool>("use_peephole", false);
allocated = false;
outTailShape.clear();
}
PriorBoxLayerImpl(const LayerParams ¶ms)
{
setParamsFrom(params);
_minSize = getParameter<unsigned>(params, "min_size");
CV_Assert(_minSize > 0);
_flip = getParameter<bool>(params, "flip");
_clip = getParameter<bool>(params, "clip");
_aspectRatios.clear();
_aspectRatios.push_back(1.);
getAspectRatios(params);
getVariance(params);
_numPriors = _aspectRatios.size();
_maxSize = -1;
if (params.has("max_size"))
{
_maxSize = params.get("max_size").get<float>(0);
CV_Assert(_maxSize > _minSize);
_numPriors += 1;
}
if (params.has("step_h") || params.has("step_w")) {
CV_Assert(!params.has("step"));
_stepY = getParameter<float>(params, "step_h");
CV_Assert(_stepY > 0.);
_stepX = getParameter<float>(params, "step_w");
CV_Assert(_stepX > 0.);
} else if (params.has("step")) {
const float step = getParameter<float>(params, "step");
CV_Assert(step > 0);
_stepY = step;
_stepX = step;
} else {
_stepY = 0;
_stepX = 0;
}
}
RegionLayerImpl(const LayerParams& params)
{
setParamsFrom(params);
CV_Assert(blobs.size() == 1);
thresh = params.get<float>("thresh", 0.2);
coords = params.get<int>("coords", 4);
classes = params.get<int>("classes", 0);
anchors = params.get<int>("anchors", 5);
classfix = params.get<int>("classfix", 0);
useSoftmaxTree = params.get<bool>("softmax_tree", false);
useSoftmax = params.get<bool>("softmax", false);
nmsThreshold = params.get<float>("nms_threshold", 0.4);
CV_Assert(nmsThreshold >= 0.);
CV_Assert(coords == 4);
CV_Assert(classes >= 1);
CV_Assert(anchors >= 1);
CV_Assert(useSoftmaxTree || useSoftmax);
}
LRNLayerImpl(const LayerParams& params)
{
setParamsFrom(params);
type = -1;
String nrmType = params.get<String>("norm_region", "ACROSS_CHANNELS");
if (nrmType == "ACROSS_CHANNELS")
type = LRNLayer::CHANNEL_NRM;
else if (nrmType == "WITHIN_CHANNEL")
type = LRNLayer::SPATIAL_NRM;
else
CV_Error(Error::StsBadArg, "Unknown region type \"" + nrmType + "\"");
size = params.get<int>("local_size", 5);
if (size % 2 != 1 || size <= 0)
CV_Error(Error::StsBadArg, "LRN layer supports only positive odd values for local_size");
alpha = params.get<double>("alpha", 1);
beta = params.get<double>("beta", 0.75);
bias = params.get<double>("bias", 1);
normBySize = params.get<bool>("norm_by_size", true);
}
PriorBoxLayerImpl(const LayerParams ¶ms)
: _boxWidth(0), _boxHeight(0)
{
setParamsFrom(params);
_minSize = getParameter<float>(params, "min_size", 0, false, 0);
_flip = getParameter<bool>(params, "flip", 0, false, true);
_clip = getParameter<bool>(params, "clip", 0, false, true);
_bboxesNormalized = getParameter<bool>(params, "normalized_bbox", 0, false, true);
_scales.clear();
_aspectRatios.clear();
getAspectRatios(params);
getVariance(params);
getParams("scales", params, &_scales);
getParams("width", params, &_widths);
getParams("height", params, &_heights);
_explicitSizes = !_widths.empty();
CV_Assert(_widths.size() == _heights.size());
if (_explicitSizes)
{
CV_Assert(_aspectRatios.empty(), !params.has("min_size"), !params.has("max_size"));
_numPriors = _widths.size();
}
else
{
CV_Assert(!_aspectRatios.empty(), _minSize > 0);
_numPriors = _aspectRatios.size() + 1; // + 1 for an aspect ratio 1.0
}
_maxSize = -1;
if (params.has("max_size"))
{
_maxSize = params.get("max_size").get<float>(0);
CV_Assert(_maxSize > _minSize);
_numPriors += 1;
}
if (params.has("step_h") || params.has("step_w")) {
CV_Assert(!params.has("step"));
_stepY = getParameter<float>(params, "step_h");
CV_Assert(_stepY > 0.);
_stepX = getParameter<float>(params, "step_w");
CV_Assert(_stepX > 0.);
} else if (params.has("step")) {
const float step = getParameter<float>(params, "step");
CV_Assert(step > 0);
_stepY = step;
_stepX = step;
} else {
_stepY = 0;
_stepX = 0;
}
if (params.has("offset_h") || params.has("offset_w"))
{
CV_Assert(!params.has("offset"), params.has("offset_h"), params.has("offset_w"));
getParams("offset_h", params, &_offsetsY);
getParams("offset_w", params, &_offsetsX);
CV_Assert(_offsetsX.size() == _offsetsY.size());
_numPriors *= std::max((size_t)1, 2 * (_offsetsX.size() - 1));
}
else
{
float offset = getParameter<float>(params, "offset", 0, false, 0.5);
_offsetsX.assign(1, offset);
_offsetsY.assign(1, offset);
}
}
SoftMaxLayerImpl(const LayerParams& params)
{
axisRaw = params.get<int>("axis", 1);
logSoftMax = params.get<int>("log_softmax", false);
setParamsFrom(params);
}
ScaleLayerImpl(const LayerParams& params)
{
setParamsFrom(params);
hasBias = params.get<bool>("bias_term", false);
}
ShiftLayerImpl(const LayerParams ¶ms)
{
setParamsFrom(params);
CV_Assert(blobs.size() == 1);
}
PriorBoxLayerImpl(const LayerParams ¶ms)
{
setParamsFrom(params);
_minSize = getParameter<float>(params, "min_size", 0, false, 0);
_flip = getParameter<bool>(params, "flip", 0, false, true);
_clip = getParameter<bool>(params, "clip", 0, false, true);
_bboxesNormalized = getParameter<bool>(params, "normalized_bbox", 0, false, true);
_aspectRatios.clear();
getAspectRatios(params);
getVariance(params);
_maxSize = -1;
if (params.has("max_size"))
{
_maxSize = params.get("max_size").get<float>(0);
CV_Assert(_maxSize > _minSize);
}
std::vector<float> widths, heights;
getParams("width", params, &widths);
getParams("height", params, &heights);
_explicitSizes = !widths.empty();
CV_Assert(widths.size() == heights.size());
if (_explicitSizes)
{
CV_Assert(_aspectRatios.empty());
CV_Assert(!params.has("min_size"));
CV_Assert(!params.has("max_size"));
_boxWidths = widths;
_boxHeights = heights;
}
else
{
CV_Assert(_minSize > 0);
_boxWidths.resize(1 + (_maxSize > 0 ? 1 : 0) + _aspectRatios.size());
_boxHeights.resize(_boxWidths.size());
_boxWidths[0] = _boxHeights[0] = _minSize;
int i = 1;
if (_maxSize > 0)
{
// second prior: aspect_ratio = 1, size = sqrt(min_size * max_size)
_boxWidths[i] = _boxHeights[i] = sqrt(_minSize * _maxSize);
i += 1;
}
// rest of priors
for (size_t r = 0; r < _aspectRatios.size(); ++r)
{
float arSqrt = sqrt(_aspectRatios[r]);
_boxWidths[i + r] = _minSize * arSqrt;
_boxHeights[i + r] = _minSize / arSqrt;
}
}
CV_Assert(_boxWidths.size() == _boxHeights.size());
_numPriors = _boxWidths.size();
if (params.has("step_h") || params.has("step_w")) {
CV_Assert(!params.has("step"));
_stepY = getParameter<float>(params, "step_h");
CV_Assert(_stepY > 0.);
_stepX = getParameter<float>(params, "step_w");
CV_Assert(_stepX > 0.);
} else if (params.has("step")) {
const float step = getParameter<float>(params, "step");
CV_Assert(step > 0);
_stepY = step;
_stepX = step;
} else {
_stepY = 0;
_stepX = 0;
}
if (params.has("offset_h") || params.has("offset_w"))
{
CV_Assert(!params.has("offset"), params.has("offset_h"), params.has("offset_w"));
getParams("offset_h", params, &_offsetsY);
getParams("offset_w", params, &_offsetsX);
CV_Assert(_offsetsX.size() == _offsetsY.size());
_numPriors *= std::max((size_t)1, 2 * (_offsetsX.size() - 1));
}
else
{
float offset = getParameter<float>(params, "offset", 0, false, 0.5);
_offsetsX.assign(1, offset);
_offsetsY.assign(1, offset);
}
}
