int main(int argc, const char** argv)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG(argc);
CV_TRACE_ARG_VALUE(argv0, "argv0", argv[0]);
CV_TRACE_ARG_VALUE(argv1, "argv1", argv[1]);
cv::CommandLineParser parser(argc, argv,
"{ help h usage ? | | show this help message }"
"{ verbose v | | show build configuration log }"
);
if (parser.has("help"))
{
parser.printMessage();
}
else if (parser.has("verbose"))
{
std::cout << cv::getBuildInformation().c_str() << std::endl;
}
else
{
std::cout << CV_VERSION << std::endl;
}
return 0;
}
void forward(InputArrayOfArrays inputs_arr, OutputArrayOfArrays outputs_arr, OutputArrayOfArrays internals_arr)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
Layer::forward_fallback(inputs_arr, outputs_arr, internals_arr);
}
void forward(std::vector<Mat*> &inputs, std::vector<Mat> &outputs, std::vector<Mat> &internals)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
for (size_t i = 0; i < inputs.size(); i++)
{
Mat srcBlob = *inputs[i];
MatShape inputShape = shape(srcBlob), outShape = shape(outputs[i]);
float *dstData = outputs[0].ptr<float>();
const float *srcData = srcBlob.ptr<float>();
int channels = inputShape[1], height = inputShape[2], width = inputShape[3];
int out_c = channels / (reorgStride*reorgStride);
for (int k = 0; k < channels; ++k) {
for (int j = 0; j < height; ++j) {
for (int i = 0; i < width; ++i) {
int out_index = i + width*(j + height*k);
int c2 = k % out_c;
int offset = k / out_c;
int w2 = i*reorgStride + offset % reorgStride;
int h2 = j*reorgStride + offset / reorgStride;
int in_index = w2 + width*reorgStride*(h2 + height*reorgStride*c2);
dstData[out_index] = srcData[in_index];
}
}
}
}
}
void forward(std::vector<Mat*> &inputs, std::vector<Mat> &outputs, std::vector<Mat> &internals)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
CV_Assert(inputs.size() == 1 && outputs.size() == 1);
CV_Assert(inputs[0]->total() == outputs[0].total());
const Mat& inp0 = *inputs[0];
Mat& buffer = internals[0];
size_t num = inp0.size[0];
size_t channels = inp0.size[1];
size_t channelSize = inp0.total() / (num * channels);
for (size_t n = 0; n < num; ++n)
{
Mat src = Mat(channels, channelSize, CV_32F, (void*)inp0.ptr<float>(n));
Mat dst = Mat(channels, channelSize, CV_32F, (void*)outputs[0].ptr<float>(n));
cv::pow(abs(src), pnorm, buffer);
if (acrossSpatial)
{
// add eps to avoid overflow
float absSum = sum(buffer)[0] + epsilon;
float norm = pow(absSum, 1.0f / pnorm);
multiply(src, 1.0f / norm, dst);
}
else
{
Mat norm;
reduce(buffer, norm, 0, REDUCE_SUM);
norm += epsilon;
// compute inverted norm to call multiply instead divide
cv::pow(norm, -1.0f / pnorm, norm);
repeat(norm, channels, 1, buffer);
multiply(src, buffer, dst);
}
if (!blobs.empty())
{
// scale the output
Mat scale = blobs[0];
if (scale.total() == 1)
{
// _scale: 1 x 1
dst *= scale.at<float>(0, 0);
}
else
{
// _scale: _channels x 1
CV_Assert(scale.total() == channels);
repeat(scale, 1, dst.cols, buffer);
multiply(dst, buffer, dst);
}
}
}
}
void forward(std::vector<Mat *> &inputs, std::vector<Mat> &outputs, std::vector<Mat> &internals)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
Mat &input = *inputs[0];
Mat &output = outputs[0];
input(&crop_ranges[0]).copyTo(output);
}
void forward(InputArrayOfArrays inputs_arr, OutputArrayOfArrays outputs_arr, OutputArrayOfArrays internals_arr)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
CV_OCL_RUN((preferableTarget == DNN_TARGET_OPENCL) &&
OCL_PERFORMANCE_CHECK(ocl::Device::getDefault().isIntel()),
forward_ocl(inputs_arr, outputs_arr, internals_arr))
Layer::forward_fallback(inputs_arr, outputs_arr, internals_arr);
}
void forward(std::vector<Mat*> &inputs, std::vector<Mat> &outputs, std::vector<Mat> &internals)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
for (size_t i = 0; i < inputs.size(); i++)
{
Mat srcBlob = *inputs[i];
if (outputs[i].data != srcBlob.data)
srcBlob.reshape(1, shape(outputs[i])).copyTo(outputs[i]);
}
}
void forward(std::vector<Mat*> &inputs, std::vector<Mat> &outputs, std::vector<Mat> &internals)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
if (paddingType == "constant")
{
outputs[0].setTo(paddingValue);
inputs[0]->copyTo(outputs[0](dstRanges));
}
else if (paddingType == "reflect")
{
CV_Assert(inputs.size() == 1);
CV_Assert(outputs.size() == 1);
CV_Assert(inputs[0]->dims == 4);
CV_Assert(outputs[0].dims == 4);
if (inputs[0]->size[0] != outputs[0].size[0] || inputs[0]->size[1] != outputs[0].size[1])
CV_Error(Error::StsNotImplemented, "Only spatial reflection padding is supported.");
const int inpHeight = inputs[0]->size[2];
const int inpWidth = inputs[0]->size[3];
const int outHeight = outputs[0].size[2];
const int outWidth = outputs[0].size[3];
const int padTop = dstRanges[2].start;
const int padBottom = outHeight - dstRanges[2].end;
const int padLeft = dstRanges[3].start;
const int padRight = outWidth - dstRanges[3].end;
CV_Assert(padTop < inpHeight, padBottom < inpHeight,
padLeft < inpWidth, padRight < inpWidth);
for (size_t n = 0; n < inputs[0]->size[0]; ++n)
{
for (size_t ch = 0; ch < inputs[0]->size[1]; ++ch)
{
copyMakeBorder(getPlane(*inputs[0], n, ch),
getPlane(outputs[0], n, ch),
padTop, padBottom, padLeft, padRight,
BORDER_REFLECT_101);
}
}
}
else
CV_Error(Error::StsNotImplemented, "Unknown padding type: " + paddingType);
}
void forward(std::vector<Mat*> &inputs, std::vector<Mat> &outputs, std::vector<Mat> &internals)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
if (outHeight == inputs[0]->size[2] && outWidth == inputs[0]->size[3])
return;
Mat& inp = *inputs[0];
Mat& out = outputs[0];
for (size_t n = 0; n < inputs[0]->size[0]; ++n)
{
for (size_t ch = 0; ch < inputs[0]->size[1]; ++ch)
{
resize(getPlane(inp, n, ch), getPlane(out, n, ch),
Size(outWidth, outHeight), 0, 0, INTER_NEAREST);
}
}
}
void forward(std::vector<Mat*> &inputs, std::vector<Mat> &outputs, std::vector<Mat> &internals)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
for (size_t i = 0; i < inputs.size(); i++)
{
Mat srcBlob = *inputs[i];
MatShape inputShape = shape(srcBlob), outShape = shape(outputs[i]);
if (performReordering)
{
float *dstData = internals[i].ptr<float>();
const float *srcData = srcBlob.ptr<float>();
int num = inputShape[0], channels = inputShape[1], height = inputShape[2], width = inputShape[3];
int total = num*channels*height*width;
for(int i_n = 0; i_n < num; i_n++) {
for(int i_c = 0; i_c < channels; i_c++) {
for(int i_h = 0; i_h < height; i_h++) {
for(int i_w = 0; i_w < width; i_w++) {
int src_i = channels*height*width*i_n + height*width*i_c + width*i_h + i_w;
int dst_i = channels*height*width*i_n + i_c + channels*width*i_h + channels*i_w;
CV_Assert(dst_i < total);
CV_Assert(src_i < total);
dstData[dst_i] = srcData[src_i];
}
}
}
}
internals[i].copyTo(outputs[i]);
}
else
{
if (outputs[i].data != srcBlob.data)
srcBlob.reshape(1, outShape).copyTo(outputs[i]);
}
}
}
virtual void forward(std::vector<Mat*> &inputs, std::vector<Mat> &outputs, std::vector<Mat> &internals)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
CV_Assert(inputs.size() > 0);
CV_Assert(blobs.size() > 0);
if(inputs[0]->dims == blobs[0].dims)
{
for (size_t ii = 0; ii < outputs.size(); ii++)
{
Mat &inpBlob = *inputs[ii];
Mat &outBlob = outputs[ii];
outBlob = inpBlob + blobs[0];
}
}
else
{
Mat biasOnesMat = internals[0];
biasOnesMat.setTo(1);
for (size_t ii = 0; ii < outputs.size(); ii++)
{
Mat &inpBlob = *inputs[ii];
Mat &outBlob = outputs[ii];
inpBlob.copyTo(outBlob);
for (int n = 0; n < inpBlob.size[0]; n++)
{
Mat dstMat(inpBlob.size[1], inpBlob.size[2] * inpBlob.size[3],
outBlob.type(), outBlob.ptr(n));
gemm(blobs[0], biasOnesMat, 1, dstMat, 1, dstMat); //TODO: gemv
}
}
}
}
void forward(std::vector<Mat*> &inputs, std::vector<Mat> &outputs, std::vector<Mat> &internals)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
checkInputs(inputs);
Mat& buffer = internals[0], sumChannelMultiplier = internals[1],
sumSpatialMultiplier = internals[2];
sumChannelMultiplier.setTo(1.0);
sumSpatialMultiplier.setTo(1.0);
const Mat& inp0 = *inputs[0];
size_t num = inp0.size[0];
size_t channels = inp0.size[1];
size_t channelSize = inp0.size[2] * inp0.size[3];
Mat zeroBuffer(channels, channelSize, CV_32F, Scalar(0));
Mat absDiff;
Mat scale = blobs[0];
for (size_t j = 0; j < inputs.size(); j++)
{
for (size_t n = 0; n < num; ++n)
{
Mat src = Mat(channels, channelSize, CV_32F, inputs[j]->ptr<float>(n));
Mat dst = Mat(channels, channelSize, CV_32F, outputs[j].ptr<float>(n));
buffer = src.mul(src);
if (_across_spatial)
{
absdiff(buffer, zeroBuffer, absDiff);
// add eps to avoid overflow
double absSum = sum(absDiff)[0] + _eps;
float norm = sqrt(absSum);
dst = src / norm;
}
else
{
Mat norm(channelSize, 1, buffer.type()); // 1 x channelSize
// (_channels x channelSize)T * _channels x 1 -> channelSize x 1
gemm(buffer, sumChannelMultiplier, 1, norm, 0, norm, GEMM_1_T);
// compute norm
pow(norm, 0.5f, norm);
// scale the layer
// _channels x 1 * (channelSize x 1)T -> _channels x channelSize
gemm(sumChannelMultiplier, norm, 1, buffer, 0, buffer, GEMM_2_T);
dst = src / buffer;
}
// scale the output
if (_channel_shared)
{
// _scale: 1 x 1
dst *= scale.at<float>(0, 0);
}
else
{
// _scale: _channels x 1
// _channels x 1 * 1 x channelSize -> _channels x channelSize
gemm(scale, sumSpatialMultiplier, 1, buffer, 0, buffer);
dst = dst.mul(buffer);
}
}
}
}
void forward(std::vector<Mat*> &inputs, std::vector<Mat> &outputs, std::vector<Mat> &internals)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
CV_Assert(inputs.size() >= 1);
int const cell_size = classes + coords + 1;
const float* biasData = blobs[0].ptr<float>();
for (size_t ii = 0; ii < outputs.size(); ii++)
{
Mat &inpBlob = *inputs[ii];
Mat &outBlob = outputs[ii];
int rows = inpBlob.size[1];
int cols = inpBlob.size[2];
const float *srcData = inpBlob.ptr<float>();
float *dstData = outBlob.ptr<float>();
// logistic activation for t0, for each grid cell (X x Y x Anchor-index)
for (int i = 0; i < rows*cols*anchors; ++i) {
int index = cell_size*i;
float x = srcData[index + 4];
dstData[index + 4] = logistic_activate(x); // logistic activation
}
if (useSoftmaxTree) { // Yolo 9000
CV_Error(cv::Error::StsNotImplemented, "Yolo9000 is not implemented");
}
else if (useSoftmax) { // Yolo v2
// softmax activation for Probability, for each grid cell (X x Y x Anchor-index)
for (int i = 0; i < rows*cols*anchors; ++i) {
int index = cell_size*i;
softmax_activate(srcData + index + 5, classes, 1, dstData + index + 5);
}
for (int x = 0; x < cols; ++x)
for(int y = 0; y < rows; ++y)
for (int a = 0; a < anchors; ++a) {
int index = (y*cols + x)*anchors + a; // index for each grid-cell & anchor
int p_index = index * cell_size + 4;
float scale = dstData[p_index];
if (classfix == -1 && scale < .5) scale = 0; // if(t0 < 0.5) t0 = 0;
int box_index = index * cell_size;
dstData[box_index + 0] = (x + logistic_activate(srcData[box_index + 0])) / cols;
dstData[box_index + 1] = (y + logistic_activate(srcData[box_index + 1])) / rows;
dstData[box_index + 2] = exp(srcData[box_index + 2]) * biasData[2 * a] / cols;
dstData[box_index + 3] = exp(srcData[box_index + 3]) * biasData[2 * a + 1] / rows;
int class_index = index * cell_size + 5;
if (useSoftmaxTree) {
CV_Error(cv::Error::StsNotImplemented, "Yolo9000 is not implemented");
}
else {
for (int j = 0; j < classes; ++j) {
float prob = scale*dstData[class_index + j]; // prob = IoU(box, object) = t0 * class-probability
dstData[class_index + j] = (prob > thresh) ? prob : 0; // if (IoU < threshold) IoU = 0;
}
}
}
}
if (nmsThreshold > 0) {
do_nms_sort(dstData, rows*cols*anchors, thresh, nmsThreshold);
}
}
}
