double classify_example(MODEL *model, DOC *ex)
/* classifies one example */
{
register long i;
register double dist;
if((model->kernel_parm.kernel_type == LINEAR) && (model->lin_weights))
return(classify_example_linear(model,ex));
dist=0;
for(i=1;i<model->sv_num;i++) {
dist+=kernel(&model->kernel_parm,model->supvec[i],ex)*model->alpha[i];
}
return(dist-model->b);
}
int SVMLightRunner::librarySVMClassifyMain(
int argc, char **argv, bool use_gmumr, SVMConfiguration &config
) {
LOG(
config.log,
LogLevel::DEBUG_LEVEL,
__debug_prefix__ + ".librarySVMClassifyMain() Started."
);
DOC *doc; /* test example */
WORD *words;
long max_docs,max_words_doc,lld;
long totdoc=0,queryid,slackid;
long correct=0,incorrect=0,no_accuracy=0;
long res_a=0,res_b=0,res_c=0,res_d=0,wnum,pred_format;
long j;
double t1,runtime=0;
double dist,doc_label,costfactor;
char *line,*comment;
FILE *predfl,*docfl;
MODEL *model;
// GMUM.R changes {
librarySVMClassifyReadInputParameters(
argc, argv, docfile, modelfile, predictionsfile, &verbosity,
&pred_format, use_gmumr, config);
if (!use_gmumr) {
nol_ll(docfile,&max_docs,&max_words_doc,&lld); /* scan size of input file */
lld+=2;
line = (char *)my_malloc(sizeof(char)*lld);
} else {
max_docs = config.target.n_rows;
max_words_doc = config.getDataDim();
config.result = arma::zeros<arma::vec>(max_docs);
// Prevent writing to the file
pred_format = -1;
// lld used only for file reading
}
max_words_doc+=2;
words = (WORD *)my_malloc(sizeof(WORD)*(max_words_doc+10));
// GMUM.R changes }
model=libraryReadModel(modelfile, use_gmumr, config);
// GMUM.R changes }
if(model->kernel_parm.kernel_type == 0) { /* linear kernel */
/* compute weight vector */
add_weight_vector_to_linear_model(model);
}
if(verbosity>=2) {
C_PRINTF("Classifying test examples.."); C_FFLUSH(stdout);
}
// GMUM.R changes {
bool newline;
if (!use_gmumr) {
if ((predfl = fopen (predictionsfile, "w")) == NULL)
{ perror (predictionsfile); EXIT (1); }
if ((docfl = fopen (docfile, "r")) == NULL)
{ perror (docfile); EXIT (1); }
newline = (!feof(docfl)) && fgets(line,(int)lld,docfl);
} else {
newline = false;
if (totdoc < config.getDataExamplesNumber()) {
newline = true;
std::string str = SVMConfigurationToSVMLightLearnInputLine(config, totdoc);
line = new char[str.size() + 1];
std::copy(str.begin(), str.end(), line);
line[str.size()] = '\0';
}
}
while(newline) {
if (use_gmumr) {
std::string stringline = "";
}
// GMUM.R changes }
if(line[0] == '#') continue; /* line contains comments */
parse_document(line,words,&doc_label,&queryid,&slackid,&costfactor,&wnum,
max_words_doc,&comment);
totdoc++;
if(model->kernel_parm.kernel_type == 0) { /* linear kernel */
for(j=0;(words[j]).wnum != 0;j++) { /* Check if feature numbers */
if((words[j]).wnum>model->totwords) /* are not larger than in */
(words[j]).wnum=0; /* model. Remove feature if */
} /* necessary. */
doc = create_example(-1,0,0,0.0,create_svector(words,comment,1.0));
t1=get_runtime();
dist=classify_example_linear(model,doc);
runtime+=(get_runtime()-t1);
free_example(doc,1);
}
else { /* non-linear kernel */
doc = create_example(-1,0,0,0.0,create_svector(words,comment,1.0));
t1=get_runtime();
dist=classify_example(model,doc);
runtime+=(get_runtime()-t1);
free_example(doc,1);
}
if(dist>0) {
if(pred_format==0) { /* old weired output format */
C_FPRINTF(predfl,"%.8g:+1 %.8g:-1\n",dist,-dist);
}
if(doc_label>0) correct++; else incorrect++;
if(doc_label>0) res_a++; else res_b++;
}
else {
if(pred_format==0) { /* old weired output format */
C_FPRINTF(predfl,"%.8g:-1 %.8g:+1\n",-dist,dist);
}
if(doc_label<0) correct++; else incorrect++;
if(doc_label>0) res_c++; else res_d++;
}
if(pred_format==1) { /* output the value of decision function */
C_FPRINTF(predfl,"%.8g\n",dist);
}
if((int)(0.01+(doc_label*doc_label)) != 1)
{ no_accuracy=1; } /* test data is not binary labeled */
if(verbosity>=2) {
if(totdoc % 100 == 0) {
C_PRINTF("%ld..",totdoc); C_FFLUSH(stdout);
}
}
// GMUM.R changes {
if (!use_gmumr) {
newline = (!feof(docfl)) && fgets(line,(int)lld,docfl);
} else {
newline = false;
// Store prediction result in config
config.result[totdoc-1] = dist;
// Read next line
if (totdoc < config.getDataExamplesNumber()) {
newline = true;
std::string str = SVMConfigurationToSVMLightLearnInputLine(config, totdoc);
line = new char[str.size() + 1];
std::copy(str.begin(), str.end(), line);
line[str.size()] = '\0';
}
}
}
if (!use_gmumr) {
fclose(predfl);
fclose(docfl);
free(line);
}
// GMUM.R changes }
free(words);
free_model(model,1);
if(verbosity>=2) {
C_PRINTF("done\n");
/* Note by Gary Boone Date: 29 April 2000 */
/* o Timing is inaccurate. The timer has 0.01 second resolution. */
/* Because classification of a single vector takes less than */
/* 0.01 secs, the timer was underflowing. */
C_PRINTF("Runtime (without IO) in cpu-seconds: %.2f\n",
(float)(runtime/100.0));
}
if((!no_accuracy) && (verbosity>=1)) {
C_PRINTF("Accuracy on test set: %.2f%% (%ld correct, %ld incorrect, %ld total)\n",(float)(correct)*100.0/totdoc,correct,incorrect,totdoc);
C_PRINTF("Precision/recall on test set: %.2f%%/%.2f%%\n",(float)(res_a)*100.0/(res_a+res_b),(float)(res_a)*100.0/(res_a+res_c));
}
return(0);
}
int main_classify (int argc, char* argv[])
{
DOC *doc; /* test example */
WORDSVM *words;
long max_docs,max_words_doc,lld;
long totdoc=0,queryid,slackid;
long correct=0,incorrect=0,no_accuracy=0;
long res_a=0,res_b=0,res_c=0,res_d=0,wnum,pred_format;
long j;
double t1,runtime=0;
double dist,doc_label,costfactor;
char *line,*comment;
FILE *predfl,*docfl;
MODEL *model;
read_input_parameters(argc,argv,docfile,modelfile,predictionsfile,
&verbosity,&pred_format);
nol_ll(docfile,&max_docs,&max_words_doc,&lld); /* scan size of input file */
max_words_doc+=2;
lld+=2;
line = (char *)my_malloc(sizeof(char)*lld);
words = (WORDSVM *)my_malloc(sizeof(WORDSVM)*(max_words_doc+10));
model=read_model(modelfile);
if(model->kernel_parm.kernel_type == 0) { /* linear kernel */
/* compute weight vector */
add_weight_vector_to_linear_model(model);
}
if(verbosity>=2) {
printf("Classifying test examples.."); fflush(stdout);
}
if ((docfl = fopen (docfile, "r")) == NULL)
{ perror (docfile); exit (1); }
if ((predfl = fopen (predictionsfile, "w")) == NULL)
{ perror (predictionsfile); exit (1); }
while((!feof(docfl)) && fgets(line,(int)lld,docfl)) {
if(line[0] == '#') continue; /* line contains comments */
parse_document(line,words,&doc_label,&queryid,&slackid,&costfactor,&wnum,
max_words_doc,&comment);
totdoc++;
if(model->kernel_parm.kernel_type == 0) { /* linear kernel */
for(j=0;(words[j]).wnum != 0;j++) { /* Check if feature numbers */
if((words[j]).wnum>model->totwords) /* are not larger than in */
(words[j]).wnum=0; /* model. Remove feature if */
} /* necessary. */
doc = create_example(-1,0,0,0.0,create_svector(words,comment,1.0));
t1=get_runtime();
dist=classify_example_linear(model,doc);
runtime+=(get_runtime()-t1);
free_example(doc,1);
}
else { /* non-linear kernel */
doc = create_example(-1,0,0,0.0,create_svector(words,comment,1.0));
t1=get_runtime();
dist=classify_example(model,doc);
runtime+=(get_runtime()-t1);
free_example(doc,1);
}
if(dist>0) {
if(pred_format==0) { /* old weired output format */
fprintf(predfl,"%.8g:+1 %.8g:-1\n",dist,-dist);
}
if(doc_label>0) correct++; else incorrect++;
if(doc_label>0) res_a++; else res_b++;
}
else {
if(pred_format==0) { /* old weired output format */
fprintf(predfl,"%.8g:-1 %.8g:+1\n",-dist,dist);
}
if(doc_label<0) correct++; else incorrect++;
if(doc_label>0) res_c++; else res_d++;
}
if(pred_format==1) { /* output the value of decision function */
fprintf(predfl,"%.8g\n",dist);
}
if((int)(0.01+(doc_label*doc_label)) != 1)
{ no_accuracy=1; } /* test data is not binary labeled */
if(verbosity>=2) {
if(totdoc % 100 == 0) {
printf("%ld..",totdoc); fflush(stdout);
}
}
}
free(line);
free(words);
free_model(model,1);
if(verbosity>=2) {
printf("done\n");
/* Note by Gary Boone Date: 29 April 2000 */
/* o Timing is inaccurate. The timer has 0.01 second resolution. */
/* Because classification of a single vector takes less than */
/* 0.01 secs, the timer was underflowing. */
printf("Runtime (without IO) in cpu-seconds: %.2f\n",
(float)(runtime/100.0));
}
if((!no_accuracy) && (verbosity>=1)) {
printf("Accuracy on test set: %.2f%% (%ld correct, %ld incorrect, %ld total)\n",(float)(correct)*100.0/totdoc,correct,incorrect,totdoc);
printf("Precision/recall on test set: %.2f%%/%.2f%%\n",(float)(res_a)*100.0/(res_a+res_b),(float)(res_a)*100.0/(res_a+res_c));
}
return(0);
}
int Classifier::getZone(IplImage* frame, double& confidence, FrameAnnotation& fa) {
if (!leftEye || !rightEye || !nose) {
string err = "Classifier::getZone. Location extractors malformed.";
throw (err);
}
// the roi offset
CvPoint offset;
// LOIs
CvPoint leftEyeLocation;
CvPoint rightEyeLocation;
CvPoint noseLocation;
// computing the confidence of the location identification
double leftPSR;
double rightPSR;
double nosePSR;
CvPoint center = fa.getLOI(Annotations::Face);
if (!center.x || !center.y) {
center.x = Globals::imgWidth / 2;
center.y = Globals::imgHeight / 2;
fa.setFace(center);
}
offset.x = offset.y = 0;
IplImage* roi = (roiFunction)? roiFunction(frame, fa, offset, Annotations::Face) : 0;
// all location extractors do identical preprocessing. Therefore, preprocess
// once using say the left eye extractor and re-use it for all three extractors
fftw_complex* preprocessedImage = leftEye->getPreprocessedImage((roi)? roi : frame);
#pragma omp parallel sections num_threads(2)
{
#pragma omp section
{
leftEye->setImage(preprocessedImage);
leftEye->apply();
leftEye->getMaxLocation(leftEyeLocation, leftPSR);
leftEyeLocation.x += offset.x;
leftEyeLocation.y += offset.y;
}
#pragma omp section
{
// get the location of the right eye
rightEye->setImage(preprocessedImage);
rightEye->apply();
rightEye->getMaxLocation(rightEyeLocation, rightPSR);
rightEyeLocation.x += offset.x;
rightEyeLocation.y += offset.y;
}
}
if (roi)
cvReleaseImage(&roi);
center.x = (leftEyeLocation.x + rightEyeLocation.x) / 2;
center.y = leftEyeLocation.y + Globals::noseDrop;
fa.setNose(center);
offset.x = offset.y = 0;
roi = (roiFunction)? roiFunction(frame, fa, offset, Annotations::Nose) : 0;
// free the preprocessed image
fftw_free(preprocessedImage);
// all location extractors do identical preprocessing. Therefore, preprocess
// once using say the left eye extractor and re-use it for all three extractors
preprocessedImage = nose->getPreprocessedImage((roi)? roi : frame);
// get the location of the nose
nose->setImage(preprocessedImage);
nose->apply();
nose->getMaxLocation(noseLocation, nosePSR);
noseLocation.x += offset.x;
noseLocation.y += offset.y;
// free the preprocessed image
fftw_free(preprocessedImage);
fa.setLeftIris(leftEyeLocation);
fa.setRightIris(rightEyeLocation);
fa.setNose(noseLocation);
// we are done with the images at this point. Free roi if not zero
if (roi)
cvReleaseImage(&roi);
// cout << "Confidence (L, R, N) = (" << leftPSR << ", " <<
// rightPSR << ")" << endl;
// extract features vector
vector<double> data;
for (int i = 0; i < nFeatures; i++) {
double value = featureExtractors[i]->extract(&fa);
data.push_back(value);
}
// normalize
normalize(data);
// create SVM Light objects to classify
DOC* doc;
WORD* words = (WORD*)malloc(sizeof(WORD) * (nFeatures + 1));
for (int i = 0; i < nFeatures; i++) {
words[i].wnum = featureExtractors[i]->getId();
words[i].weight = data[i];
}
// SVM Light expects that the features vector has a zero element
// to indicate termination and hence
words[nFeatures].wnum = 0;
words[nFeatures].weight = 0.0;
// create doc
string comment = "Gaze SVM";
doc = create_example(-1, 0, 0, 0.0, create_svector(words, (char*)comment.c_str(), 1.0));
int maxIndex = 0;
confidence = -FLT_MAX;
double dists[Globals::numZones];
// classify using each zone model
#pragma omp parallel for num_threads(Globals::numZones)
for (unsigned int i = 0; i < Globals::numZones; i++) {
if (kernelType == Trainer::Linear)
dists[i] = classify_example_linear(models[i], doc);
else
dists[i] = classify_example(models[i], doc);
}
for (unsigned int i = 0; i < Globals::numZones; i++) {
if (confidence < dists[i]) {
confidence = dists[i];
maxIndex = i + 1;
}
}
free_example(doc, 1);
free(words);
return maxIndex;
}
