void DeConvolutionLayer::forward(std::vector<Blob*> &inputs, std::vector<Blob> &outputs)
{
Blob &wghtBlob = blobs[0];
for (size_t ii = 0; ii < outputs.size(); ii++)
{
Blob &convBlob = *inputs[ii];
Blob &decnBlob = outputs[ii];
for (int n = 0; n < convBlob.num(); n++)
{
for (int g = 0; g < group; g++)
{
Mat dstMat(inpGroupCn, inpH*inpW, decnBlob.type(), decnBlob.ptr(n, g*inpGroupCn));
if (is1x1())
colMat = dstMat;
Mat convMat(outGroupCn, outH*outW, convBlob.type(), convBlob.ptr(n, g*outGroupCn));
Mat wghtMat(outGroupCn, ksize, wghtBlob.type(), wghtBlob.ptr(g*outGroupCn));
gemmCPU(wghtMat, convMat, 1, colMat, 0, GEMM_1_T);
col2im(dstMat);
if (bias)
{
float *biasPtr = blobs[1].ptrf() + g*inpGroupCn;
Mat biasMat(inpGroupCn, 1, CV_32F, biasPtr);
gemmCPU(biasMat, biasOnesMat, 1, dstMat, 1); //TODO: gemv
}
}
}
}
}
void ConvolutionLayer::forward(std::vector<Blob*> &inputs, std::vector<Blob> &outputs)
{
Blob &wgtBlob = blobs[0];
for (size_t ii = 0; ii < outputs.size(); ii++)
{
Blob &inpBlob = *inputs[ii];
Blob &outBlob = outputs[ii];
for (int n = 0; n < inpBlob.num(); n++)
{
for (int g = 0; g < group; g++)
{
im2col(inpBlob, n, g);
Mat kerMat(outGroupCn, ksize, wgtBlob.type(), wgtBlob.ptr(g*outGroupCn));
Mat dstMat(outGroupCn, outH*outW, outBlob.type(), outBlob.ptr(n, g*outGroupCn));
gemmCPU(kerMat, colMat, 1, dstMat, 0);
if (bias)
{
float *biasPtr = blobs[1].ptrf() + g*outGroupCn;
Mat biasMat(outGroupCn, 1, CV_32F, biasPtr);
gemmCPU(biasMat, biasOnesMat, 1, dstMat, 1); //TODO: gemv
}
}
}
}
}
Mat CutTheRect(Mat &in, Rect &rect)
{
int size = in.cols; // (rect.width>rect.height)?rect.width:rect.height;
Mat dstMat(size, size, CV_8UC1);
dstMat.setTo(Scalar(0, 0, 0));
int x = (int)floor((float)(size - rect.width) / 2.0f);
int y = (int)floor((float)(size - rect.height) / 2.0f);
//把rect中的数据 考取到dstMat的中间
for (int i = 0; i < rect.height; ++i) {
//宽
for (int j = 0; j < rect.width; ++j) {
dstMat.data[dstMat.step[0] * (i + y) + j + x] =
in.data[in.step[0] * (i + rect.y) + j + rect.x];
}
}
//
return dstMat;
}
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 FullyConnectedLayer::forward(std::vector<Blob*> &input, std::vector<Blob> &output)
{
for (size_t i = 0; i < input.size(); i++)
{
int M = (int)input[i]->total(0, axis);
int N = numOutputs;
int K = innerSize;
Mat srcMat(M, K, input[i]->type(), input[i]->ptrf());
Mat weight(N, K, blobs[0].type(), blobs[0].ptrf());
Mat dstMat(M, N, output[i].type(), output[i].ptrf());
//important: for perfomance purposes Caffe stores weights as transposed array
gemmCPU(srcMat, weight, 1, dstMat, 0, GEMM_2_T);
if (bias)
{
Mat biasOnesMat = Mat::ones(M, 1, CV_32F);
Mat biasMat(1, N, CV_32F, blobs[1].ptrf());
gemmCPU(biasOnesMat, biasMat, 1, dstMat, 1);
}
}
}
int main(int argc, char *argv[]) {
const unsigned int cameraIndex = 0u;
const unsigned int numImagesPerFPSMeasurement = 240u;
const int windowWidth = 1440;
const int windowHeight = 900;
const char cascadeFilename[] = "haarcascade_frontalface_alt.xml";
const double detectionScaleFactor = 1.25;
const int detectionMinNeighbours = 4;
const int detectionFlags = CV_HAAR_SCALE_IMAGE;
const cv::Size detectionMinSize(120, 120);
const cv::Size detectionMaxSize;
const cv::Scalar detectionDrawColor(255.0, 0.0, 255.0);
char strBuffer[256u];
const size_t strBufferSize = 256u;
int matType;
cv::Mat equalizedGrayMat;
#ifdef _WIN32
snprintf(strBuffer, strBufferSize, "%s/../%s", argv[0], cascadeFilename);
cv::CascadeClassifier detector(strBuffer);
#else
cv::CascadeClassifier detector(cascadeFilename);
#endif
if (detector.empty()) {
snprintf(strBuffer, strBufferSize, "%s could not be loaded.",
cascadeFilename);
SDL_ShowSimpleMessageBox(
SDL_MESSAGEBOX_ERROR, "Failed to Load Cascade File", strBuffer, NULL);
return EXIT_FAILURE;
}
std::vector<cv::Rect> detectionRects;
fc2Error error;
fc2Image image;
error = fc2CreateImage(&image);
if (error != FC2_ERROR_OK) {
showFC2Error(error);
return EXIT_FAILURE;
}
fc2Context context;
error = fc2CreateContext(&context);
if (error != FC2_ERROR_OK) {
showFC2Error(error);
return EXIT_FAILURE;
}
fc2PGRGuid cameraGUID;
error = fc2GetCameraFromIndex(context, cameraIndex, &cameraGUID);
if (error != FC2_ERROR_OK) {
showFC2Error(error);
return EXIT_FAILURE;
}
error = fc2Connect(context, &cameraGUID);
if (error != FC2_ERROR_OK) {
showFC2Error(error);
return EXIT_FAILURE;
}
error = fc2StartCapture(context);
if (error != FC2_ERROR_OK) {
fc2Disconnect(context);
showFC2Error(error);
return EXIT_FAILURE;
}
if (SDL_Init(SDL_INIT_VIDEO) < 0) {
fc2StopCapture(context);
fc2Disconnect(context);
showSDLError();
return EXIT_FAILURE;
}
SDL_Window *window = SDL_CreateWindow(
"LookSpry", SDL_WINDOWPOS_UNDEFINED, SDL_WINDOWPOS_UNDEFINED,
windowWidth, windowHeight, 0u);
if (window == NULL) {
fc2StopCapture(context);
fc2Disconnect(context);
showSDLError();
return EXIT_FAILURE;
}
SDL_Renderer *renderer = SDL_CreateRenderer(window, -1, 0u);
if (renderer == NULL) {
fc2StopCapture(context);
fc2Disconnect(context);
SDL_DestroyWindow(window);
showSDLError();
return EXIT_FAILURE;
}
SDL_RendererInfo rendererInfo;
SDL_GetRendererInfo(renderer, &rendererInfo);
if (strcmp(rendererInfo.name, "direct3d") == 0) {
SDL_SetHint(SDL_HINT_RENDER_SCALE_QUALITY, "best");
} else if (strcmp(rendererInfo.name, "opengl") == 0) {
SDL_SetHint(SDL_HINT_RENDER_SCALE_QUALITY, "linear");
}
snprintf(strBuffer, strBufferSize, "LookSpry | %s", rendererInfo.name);
SDL_SetWindowTitle(window, strBuffer);
SDL_Texture *videoTex = NULL;
void *videoTexPixels;
int pitch;
clock_t startTicks = clock();
clock_t endTicks;
unsigned int numImagesCaptured = 0u;
bool running = true;
bool detecting = true;
bool mirroring = true;
SDL_Event event;
while (running) {
while (SDL_PollEvent(&event)) {
if (event.type == SDL_QUIT) {
running = false;
break;
} else if (event.type == SDL_KEYUP) {
switch(event.key.keysym.sym) {
// When 'd' is pressed, start or stop [d]etection.
case SDLK_d:
detecting = !detecting;
break;
// When 'm' is pressed, [m]irror or un-mirror the video.
case SDLK_m:
mirroring = !mirroring;
break;
default:
break;
}
}
}
error = fc2RetrieveBuffer(context, &image);
if (error != FC2_ERROR_OK) {
fc2Disconnect(context);
SDL_DestroyTexture(videoTex);
SDL_DestroyRenderer(renderer);
SDL_DestroyWindow(window);
showFC2Error(error);
return EXIT_FAILURE;
}
if (videoTex == NULL) {
equalizedGrayMat.create(image.rows, image.cols, CV_8UC1);
SDL_RenderSetLogicalSize(renderer, image.cols, image.rows);
Uint32 videoTexPixelFormat;
switch (image.format) {
// For monochrome capture modes, plan to render captured data to the Y
// plane of a planar YUV texture.
case FC2_PIXEL_FORMAT_RAW8:
case FC2_PIXEL_FORMAT_MONO8:
videoTexPixelFormat = SDL_PIXELFORMAT_YV12;
matType = CV_8UC1;
break;
// For color capture modes, plan to render captured data to the entire
// space of a texture in a matching color format.
case FC2_PIXEL_FORMAT_422YUV8:
videoTexPixelFormat = SDL_PIXELFORMAT_UYVY;
matType = CV_8UC2;
break;
case FC2_PIXEL_FORMAT_RGB:
videoTexPixelFormat = SDL_PIXELFORMAT_RGB24;
matType = CV_8UC3;
break;
case FC2_PIXEL_FORMAT_BGR:
videoTexPixelFormat = SDL_PIXELFORMAT_BGR24;
matType = CV_8UC3;
break;
default:
fc2StopCapture(context);
fc2Disconnect(context);
SDL_DestroyTexture(videoTex);
SDL_DestroyRenderer(renderer);
SDL_DestroyWindow(window);
SDL_ShowSimpleMessageBox(
SDL_MESSAGEBOX_ERROR, "Unsupported FlyCapture2 Pixel Format",
"LookSpry supports RAW8, MONO8, 422YUV8, RGB, and BGR.", NULL);
return EXIT_FAILURE;
}
videoTex = SDL_CreateTexture(
renderer, videoTexPixelFormat, SDL_TEXTUREACCESS_STREAMING,
image.cols, image.rows);
if (videoTex == NULL) {
fc2StopCapture(context);
fc2Disconnect(context);
SDL_DestroyRenderer(renderer);
SDL_DestroyWindow(window);
showSDLError();
return EXIT_FAILURE;
}
snprintf(
strBuffer, strBufferSize, "LookSpry | %s | %dx%d --> %dx%d",
rendererInfo.name, image.cols, image.rows, windowWidth,
windowHeight);
SDL_SetWindowTitle(window, strBuffer);
}
cv::Mat srcMat(image.rows, image.cols, matType, image.pData, image.stride);
if (detecting) {
switch (image.format) {
// For monochrome capture modes, just equalize.
case FC2_PIXEL_FORMAT_RAW8:
case FC2_PIXEL_FORMAT_MONO8:
cv::equalizeHist(srcMat, equalizedGrayMat);
break;
// For color capture modes, convert to gray and equalize.
case FC2_PIXEL_FORMAT_422YUV8:
cv::cvtColor(srcMat, equalizedGrayMat, cv::COLOR_YUV2GRAY_UYVY);
cv::equalizeHist(equalizedGrayMat, equalizedGrayMat);
break;
case FC2_PIXEL_FORMAT_RGB:
cv::cvtColor(srcMat, equalizedGrayMat, cv::COLOR_RGB2GRAY);
cv::equalizeHist(equalizedGrayMat, equalizedGrayMat);
break;
case FC2_PIXEL_FORMAT_BGR:
cv::cvtColor(srcMat, equalizedGrayMat, cv::COLOR_BGR2GRAY);
cv::equalizeHist(equalizedGrayMat, equalizedGrayMat);
break;
default:
break;
}
// Run the detector on the equalized image.
detector.detectMultiScale(
equalizedGrayMat, detectionRects, detectionScaleFactor,
detectionMinNeighbours, detectionFlags, detectionMinSize,
detectionMaxSize);
// Draw the resulting detection rectangles on the original image.
for (cv::Rect detectionRect : detectionRects) {
cv::rectangle(srcMat, detectionRect, detectionDrawColor);
}
}
SDL_LockTexture(videoTex, NULL, &videoTexPixels, &pitch);
switch (image.format) {
case FC2_PIXEL_FORMAT_RAW8:
case FC2_PIXEL_FORMAT_MONO8:
// Make the planar YUV video gray by setting all bytes in its U and V
// planes to 128 (the middle of the range).
memset(((unsigned char *)videoTexPixels + image.dataSize), 128,
image.dataSize / 2u);
break;
default:
break;
}
if (mirroring) {
// Flip the image data while copying it to the texture.
cv::Mat dstMat(image.rows, image.cols, matType, videoTexPixels,
image.stride);
cv::flip(srcMat, dstMat, 1);
} else {
// Copy the image data, as-is, to the texture.
// Note that the PointGrey image and srcMat have pointers to the same
// data, so the following code does reference the data that we modified
// earlier via srcMat.
memcpy(videoTexPixels, image.pData, image.dataSize);
}
SDL_UnlockTexture(videoTex);
SDL_RenderCopy(renderer, videoTex, NULL, NULL);
SDL_RenderPresent(renderer);
numImagesCaptured++;
if (numImagesCaptured >= numImagesPerFPSMeasurement) {
endTicks = clock();
snprintf(
strBuffer, strBufferSize, "LookSpry | %s | %dx%d --> %dx%d | %ld FPS",
rendererInfo.name, image.cols, image.rows, windowWidth,
windowHeight,
numImagesCaptured * CLOCKS_PER_SEC / (endTicks - startTicks));
SDL_SetWindowTitle(window, strBuffer);
startTicks = endTicks;
numImagesCaptured = 0u;
}
}
fc2StopCapture(context);
fc2Disconnect(context);
SDL_DestroyTexture(videoTex);
SDL_DestroyRenderer(renderer);
SDL_DestroyWindow(window);
return EXIT_SUCCESS;
}