//识别阶段代码
void recognize()
{
int i, nTestFaces = 0; // 测试人脸数
CvMat * trainPersonNumMat = 0; // 训练阶段的人脸数
float * projectedTestFace = 0;
// 加载测试图像，并返回测试人脸数
nTestFaces = loadFaceImgArray("test.txt");
printf("%d test faces loaded\n", nTestFaces);
// 加载保存在.xml文件中的训练结果
if( !loadTrainingData( &trainPersonNumMat ) ) return;
//
projectedTestFace = (float *)cvAlloc( nEigens*sizeof(float) );
for(i=0; i<nTestFaces; i++)
{
int iNearest, nearest, truth;
//将测试图像投影到子空间中
cvEigenDecomposite(
faceImgArr[i],
nEigens,
eigenVectArr,
0, 0,
pAvgTrainImg,
projectedTestFace);
iNearest = findNearestNeighbor(projectedTestFace);
truth = personNumTruthMat->data.i[i];
nearest = trainPersonNumMat->data.i[iNearest];
printf("nearest = %d, Truth = %d\n", nearest, truth);
}
}
void recognize()
{
int i, nTestFaces = 0; // the number of test images
CvMat * trainPersonNumMat = 0; // the person numbers during training
float * projectedTestFace = 0;
// load test images and ground truth for person number
nTestFaces = loadFaceImgArray("test.txt");
printf("%d test faces loaded\n", nTestFaces);
// load the saved training data
if( !loadTrainingData( &trainPersonNumMat ) ) return;
// project the test images onto the PCA subspace
projectedTestFace = (float *)cvAlloc( nEigens*sizeof(float) );
for(i=0; i<nTestFaces; i++)
{
int iNearest, nearest, truth;
//project the test image onto the PCA subspace
cvEigenDecomposite(
faceImgArr[i],
nEigens,
eigenVectArr,
0, 0,
pAvgTrainImg,
projectedTestFace);
iNearest = findNearestNeighbor(projectedTestFace);
truth = personNumTruthMat->data.i[i];
nearest = trainPersonNumMat->data.i[iNearest];
printf("nearest = %d, Truth = %d\n", nearest, truth);
}
}
//////////////////////////////////
// recognize()
//返回本次训练通过的图片数
int faceRecognition::recognize()
{
int i, nTestFaces = 0; // the number of test images
CvMat * trainPersonNumMat = 0; // the person numbers during training
float * projectedTestFace = 0;
// load test images and ground truth for person number
nTestFaces = loadFaceImgArray(testFileListPath);
// load the saved training data
if( !loadTrainingData( &trainPersonNumMat ) ) return 0;
// project the test images onto the PCA subspace
projectedTestFace = (float *)cvAlloc( nEigens*sizeof(float) );
//处理输出结果,记录一次训练中正确匹配的图片数
int count=0;
for(i=0; i<nTestFaces; i++)
{ int iNearest, nearest, truth;
// project the test image onto the PCA subspace
cvEigenDecomposite(
faceImgArr[i],
nEigens,
eigenVectArr,
0, 0,
pAvgTrainImg,
projectedTestFace);
iNearest = findNearestNeighbor(projectedTestFace);
truth = personNumTruthMat->data.i[i];
nearest = trainPersonNumMat->data.i[iNearest];
// AfxMessageBox("nearest = %d, Truth = %d", nearest, truth);
if(nearest==truth)
count++;
}//for
return count;
}
bool z3ann::loadTrainingDataSet(const std::vector<trainingData> &data)
{
std::vector<trainingData>::const_iterator it = data.begin();
std::vector<trainingData>::const_iterator end = data.end();
// _equations.resize(data.size());
for (; it != end; ++it)
if (!loadTrainingData(*it))
return false;
return true;
}
void RAE::training()
{
x = lbfgs_malloc(getRAEWeightSize());
Map<MatrixLBFGS>(x, getRAEWeightSize(), 1).setRandom();
lbfgs_parameter_t param;
iterTimes = atoi(para->getPara("IterationTime").c_str());
loadTrainingData();
lbfgs_parameter_init(¶m);
param.max_iterations = iterTimes;
lbfgsfloatval_t fx = 0;
int ret;
ret = lbfgs(getRAEWeightSize(), x, &fx, RAELBFGS::evaluate, RAELBFGS::progress, this, ¶m);
cout << "L-BFGS optimization terminated with status code = " << ret << endl;
cout << " fx = " << fx << endl;
updateWeights(x);
logWeights(para);
trainingData.clear();
lbfgs_free(x);
}
// Recognize the face in each of the test images given, and compare the results with the truth.
void recognizeFileList(char *szFileTest)
{
int i, nTestFaces = 0; // the number of test images
CvMat * trainPersonNumMat = 0; // the person numbers during training
float * projectedTestFace = 0;
char *answer;
int nCorrect = 0;
int nWrong = 0;
double timeFaceRecognizeStart;
double tallyFaceRecognizeTime;
float confidence;
// load test images and ground truth for person number
nTestFaces = loadFaceImgArray(szFileTest);
printf("%d test faces loaded\n", nTestFaces);
// load the saved training data
if( !loadTrainingData( &trainPersonNumMat ) ) return;
// project the test images onto the PCA subspace
projectedTestFace = (float *)cvAlloc( nEigens*sizeof(float) );
timeFaceRecognizeStart = (double)cvGetTickCount(); // Record the timing.
for(i=0; i<nTestFaces; i++)
{
int iNearest, nearest, truth;
// project the test image onto the PCA subspace
cvEigenDecomposite(
faceImgArr[i],
nEigens,
eigenVectArr,
0, 0,
pAvgTrainImg,
projectedTestFace);
iNearest = findNearestNeighbor(projectedTestFace, &confidence);
truth = personNumTruthMat->data.i[i];
if(iNearest!=-1)
{
nearest = trainPersonNumMat->data.i[iNearest];
}
else
{
nearest = 0;
}
if (nearest == truth) {
answer = "Correct";
nCorrect++;
}
else {
answer = "WRONG!";
nWrong++;
}
printf("nearest = %d, Truth = %d (%s). Confidence = %f\n", nearest, truth, answer, confidence);
}
tallyFaceRecognizeTime = (double)cvGetTickCount() - timeFaceRecognizeStart;
if (nCorrect+nWrong > 0) {
printf("TOTAL ACCURACY: %d%% out of %d tests.\n", nCorrect * 100/(nCorrect+nWrong), (nCorrect+nWrong));
printf("TOTAL TIME: %.1fms average.\n", tallyFaceRecognizeTime/((double)cvGetTickFrequency() * 1000.0 * (nCorrect+nWrong) ) );
}
}
void TrainingDataRenderer::init()
{
loadTrainingData("assets/mocap_data/positions_only_mocap_data.txt", false);
loadTrainingData("assets/mocap_data/positions_only_mocap_labels.txt", true);
//For now just hard code some stuff in here to see if everything else works!
_shader = new Shader();
_shader->registerShader("shaders/vertColoredVerts.glsl", ShaderType::VERTEX);
_shader->registerShader("shaders/fragColoredVerts.glsl", ShaderType::FRAGMENT);
_shader->compileShaders();
_shader->linkShaders();
std::vector<Color> colors = {
Color::white(),
Color::black(),
Color::red(),
Color::blue(),
Color::green()
};
Vector3 normal(1.0, 0.0,0.0);
Vector2 uv(0.0,0.0);
Vector4 tangent(1.0, 0.0, 0.0, 0.0);
_mesh = new Mesh();
for(std::vector<vec3> row : _positions)
{
int color_idx= 0;
for(vec3 v : row)
{
Color c = colors[color_idx];
Vector3 c3(c.r,c.g,c.b);
Vector4 c4(c.r,c.g,c.b, c.a);
Vector3 p(v.x ,v.y,v.z);
_mesh->addPosition(p);
//FIXME: THE COLOR CHANNEL IS OFF/INCORRECT. HAD TO STUFF COLORS INTO THE NORMAL
//CHANNEL. THE TANGENT OR UV IS WRONG.
_mesh->addColor(colors[color_idx]);
_mesh->addNormal(c3);
_mesh->addUV(uv);
_mesh->addTangent(c4);
color_idx++;
}
}
_mesh->constructBuffer();
_mesh->setPrimitiveTypeToPoints();
_mesh->bindAttributesToVAO(*_shader);
//_mesh->bindAttributesToVAO();
_labelsMesh = new Mesh();
for(vec3 v : _labels)
{
Color c(1.0, 1.0,0.0,1.0);
Vector3 n(c.r ,c.g,c.b);
Vector4 t(c.r ,c.g,c.b, c.a);
Vector3 p(v.x ,v.y,v.z);
_labelsMesh->addPosition(p);
//FIXME: THE COLOR CHANNEL IS OFF/INCORRECT. HAD TO STUFF COLORS INTO THE NORMAL
//CHANNEL. THE TANGENT OR UV IS WRONG.
_labelsMesh->addColor(c);
_labelsMesh->addNormal(n);
_labelsMesh->addTangent(t);
}
_labelsMesh->constructBuffer();
_labelsMesh->setPrimitiveTypeToPoints();
_labelsMesh->bindAttributesToVAO(*_shader);
_mvp.identity();
vec3 min, max;
_mesh->calculateBoundingBox(min, max);
printf("\n");
printf("Min %3.4f,%3.4f,%3.4f\n", min.x, min.y, min.z);
printf("Max %3.4f,%3.4f,%3.4f\n", max.x, max.y, max.z);
_fpsController = std::make_shared<FPSController>();
InputManager::addListener(_fpsController);
_fpsController->init();
}
