int _svm_struct_learn (int argc, char* argv[])
{
char trainfile[200]; /* file with training examples */
char modelfile[200]; /* file for resulting classifier */
SAMPLE sample; /* training sample */
LEARN_PARM learn_parm;
KERNEL_PARM kernel_parm;
STRUCT_LEARN_PARM struct_parm;
STRUCTMODEL structmodel;
int alg_type;
HIDEO_ENV *hideo_env=create_env();
svm_struct_learn_api_init(argc,argv);
svm_struct_main_read_input_parameters(argc,argv,trainfile,modelfile,&verbosity,
&struct_verbosity,&struct_parm,&learn_parm,
&kernel_parm,&alg_type);
if(struct_verbosity>=1) {
printf("Reading training examples..."); fflush(stdout);
}
/* read the training examples */
sample=read_struct_examples(trainfile,&struct_parm);
if(struct_verbosity>=1) {
printf("done\n"); fflush(stdout);
}
/* Do the learning and return structmodel. */
if(alg_type == 1)
svm_learn_struct(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,hideo_env);
else if(alg_type == 2)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,PRIMAL_ALG,hideo_env);
else if(alg_type == 3)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,DUAL_ALG,hideo_env);
else if(alg_type == 4)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,DUAL_CACHE_ALG,hideo_env);
else
exit(1);
/* Warning: The model contains references to the original data 'docs'.
If you want to free the original data, and only keep the model, you
have to make a deep copy of 'model'. */
if(struct_verbosity>=1) {
printf("Writing learned model...");fflush(stdout);
}
write_struct_model(modelfile,&structmodel,&struct_parm);
if(struct_verbosity>=1) {
printf("done\n");fflush(stdout);
}
free_struct_sample(sample);
free_struct_model(structmodel);
svm_struct_learn_api_exit();
return 0;
}
int _svm_struct_learn (int argc, char* argv[])
{
SAMPLE sample; /* training sample */
LEARN_PARM learn_parm;
KERNEL_PARM kernel_parm;
STRUCT_LEARN_PARM struct_parm;
STRUCTMODEL structmodel;
int alg_type;
svm_struct_learn_api_init(argc,argv);
_svm_struct_learn_read_input_parameters(argc,argv,trainfile,modelfile,&verbosity,
&struct_verbosity,&struct_parm,&learn_parm,
&kernel_parm,&alg_type);
if(struct_verbosity>=1) {
printf("Reading training examples..."); fflush(stdout);
}
/* read the training examples */
sample=read_struct_examples(trainfile,&struct_parm);
if(struct_verbosity>=1) {
printf("done\n"); fflush(stdout);
}
/* Do the learning and return structmodel. */
if(alg_type == 0)
svm_learn_struct(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,NSLACK_ALG);
else if(alg_type == 1)
svm_learn_struct(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,NSLACK_SHRINK_ALG);
else if(alg_type == 2)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,ONESLACK_PRIMAL_ALG);
else if(alg_type == 3)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,ONESLACK_DUAL_ALG);
else if(alg_type == 4)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,ONESLACK_DUAL_CACHE_ALG);
else if(alg_type == 9)
svm_learn_struct_joint_custom(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel);
else
exit(1);
/* Warning: The model contains references to the original data 'docs'.
If you want to free the original data, and only keep the model, you
have to make a deep copy of 'model'. */
if(struct_verbosity>=1) {
printf("Writing learned model...");fflush(stdout);
}
write_struct_model(modelfile,&structmodel,&struct_parm);
if(struct_verbosity>=1) {
printf("done\n");fflush(stdout);
}
free_struct_sample(sample);
free_struct_model(structmodel);
svm_struct_learn_api_exit();
return 0;
}
int main (int argc, char* argv[])
{
SAMPLE sample; /* training sample */
LEARN_PARM learn_parm;
KERNEL_PARM kernel_parm;
STRUCT_LEARN_PARM struct_parm;
STRUCTMODEL structmodel;
int alg_type;
/* Allow the API to perform whatever initialization is required. */
api_initialize(argv[0]);
read_input_parameters(argc,argv,trainfile,modelfile,&verbosity,
&struct_verbosity,&struct_parm,&learn_parm,
&kernel_parm,&alg_type);
if(struct_verbosity>=1) {
printf("Reading training examples..."); fflush(stdout);
}
/* read the training examples */
sample=read_struct_examples(trainfile,&struct_parm);
if(struct_verbosity>=1) {
printf("done\n"); fflush(stdout);
}
/* Do the learning and return structmodel. */
if(alg_type == 1)
svm_learn_struct(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel);
else if(alg_type == 2)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,PRIMAL_ALG);
else if(alg_type == 3)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,DUAL_ALG);
else if(alg_type == 4)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,DUAL_CACHE_ALG);
else
exit(1);
/* Warning: The model contains references to the original data 'docs'.
If you want to free the original data, and only keep the model, you
have to make a deep copy of 'model'. */
if(struct_verbosity>=1) {
printf("Writing learned model...");fflush(stdout);
}
write_struct_model(modelfile,&structmodel,&struct_parm);
if(struct_verbosity>=1) {
printf("done\n");fflush(stdout);
}
free_struct_sample(sample);
free_struct_model(structmodel);
/* Allow the API to perform whatever cleanup is required. */
api_finalize();
return 0;
}
int main (int argc, char* argv[])
{
SAMPLE sample; /* training sample */
LEARN_PARM learn_parm;
KERNEL_PARM kernel_parm;
STRUCT_LEARN_PARM struct_parm;
STRUCTMODEL structmodel;
int alg_type;
svm_struct_learn_api_init(argc,argv);
read_input_parameters(argc,argv,trainfile,modelfile,&verbosity,
&struct_verbosity,&struct_parm,&learn_parm,
&kernel_parm,&alg_type);
if(struct_verbosity>=1) {
//verbose = true;
printf("Reading training examples..."); fflush(stdout);
}
/* read the training examples */
sample=read_struct_examples(trainfile,&struct_parm);
if(struct_verbosity>=1) {
printf("done\n"); fflush(stdout);
}
string config_tmp;
bool update_loss_function = false;
if(Config::Instance()->getParameter("update_loss_function", config_tmp)) {
update_loss_function = config_tmp.c_str()[0] == '1';
}
printf("[Main] update_loss_function=%d\n", (int)update_loss_function);
if(!update_loss_function) {
printf("update_loss_function should be true\n");
exit(-1);
}
eUpdateType updateType = UPDATE_NODE_EDGE;
if(Config::Instance()->getParameter("update_type", config_tmp)) {
updateType = (eUpdateType)atoi(config_tmp.c_str());
}
printf("[Main] update_type=%d\n", (int)updateType);
mkdir(loss_dir, 0777);
// check if parameter vector files exist
const char* parameter_vector_dir = "parameter_vector";
int idx = 0;
string parameter_vector_dir_last = findLastFile(parameter_vector_dir, "", &idx);
string parameter_vector_file_pattern = parameter_vector_dir_last + "/iteration_";
int idx_1 = 1;
string parameter_vector_file_last = findLastFile(parameter_vector_file_pattern, ".txt", &idx_1);
printf("[Main] Checking parameter vector file %s\n", parameter_vector_file_last.c_str());
// vectors used to store RF weights
vector<double>* alphas = new vector<double>[sample.n];
vector<double>* alphas_edge = 0;
if(updateType == UPDATE_NODE_EDGE) {
alphas_edge = new vector<double>[sample.n];
}
int alphas_idx = 0;
if(fileExists("alphas.txt") && fileExists(parameter_vector_file_last)) {
// Loading alpha coefficients
ifstream ifs("alphas.txt");
string line;
int lineIdx = 0;
while(lineIdx < sample.n && getline(ifs, line)) {
vector<string> tokens;
splitString(line, tokens);
for(vector<string>::iterator it = tokens.begin();
it != tokens.end(); ++it) {
alphas[lineIdx].push_back(atoi(it->c_str()));
}
++lineIdx;
}
ifs.close();
if(lineIdx > 0) {
alphas_idx = alphas[0].size();
}
// Loading parameters
printf("[Main] Found parameter vector file %s\n", parameter_vector_file_last.c_str());
struct_parm.ssvm_iteration = idx + 1;
update_output_dir(struct_parm.ssvm_iteration);
//EnergyParam param(parameter_vector_file_last.c_str());
//updateCoeffs(sample, param, struct_parm, updateType, alphas, alphas_idx);
//alphas_idx = 1;
} else {
struct_parm.ssvm_iteration = 0;
// insert alpha coefficients for first iteration
for(int i = 0; i < sample.n; ++i) {
alphas[i].push_back(1);
}
ofstream ofs("alphas.txt", ios::app);
int i = 0;
for(; i < sample.n - 1; ++i) {
ofs << alphas[i][alphas_idx] << " ";
}
if(i < sample.n) {
ofs << alphas[i][alphas_idx];
}
ofs << endl;
ofs.close();
// edges
for(int i = 0; i < sample.n; ++i) {
alphas_edge[i].push_back(1);
}
ofstream ofse("alphas_edge.txt", ios::app);
i = 0;
for(; i < sample.n - 1; ++i) {
ofse << alphas_edge[i][alphas_idx] << " ";
}
if(i < sample.n) {
ofse << alphas_edge[i][alphas_idx];
}
ofse << endl;
ofse.close();
++alphas_idx;
}
const int nMaxIterations = 5;
bool bIterate = true;
do {
printf("-----------------------------------------SSVM-ITERATION-%d-START\n",
struct_parm.ssvm_iteration);
struct_parm.iterationId = 1;
/* Do the learning and return structmodel. */
if(alg_type == 0)
svm_learn_struct(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,NSLACK_ALG);
else if(alg_type == 1)
svm_learn_struct(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,NSLACK_SHRINK_ALG);
else if(alg_type == 2)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,ONESLACK_PRIMAL_ALG);
else if(alg_type == 3)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,ONESLACK_DUAL_ALG);
else if(alg_type == 4)
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,ONESLACK_DUAL_CACHE_ALG);
else if(alg_type == 9)
svm_learn_struct_joint_custom(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel);
else
exit(1);
char _modelfile[BUFFER_SIZE];
//sprintf(_modelfile, "%s_%d", modelfile, struct_parm.ssvm_iteration);
sprintf(_modelfile, "%s_%d", modelfile, struct_parm.ssvm_iteration);
printf("[Main] Writing learned model to %s\n", _modelfile);
write_struct_model(_modelfile, &structmodel, &struct_parm);
// Run inference on training data and increase loss for misclassified points
printf("[Main] Loading learned model to %s\n", _modelfile);
EnergyParam param(_modelfile);
updateCoeffs(sample, param, struct_parm, updateType, alphas, alphas_edge,
struct_parm.ssvm_iteration + 1);
ofstream ofs("alphas.txt", ios::app);
int i = 0;
for(; i < sample.n - 1; ++i) {
ofs << alphas[i][alphas_idx] << " ";
}
if(i < sample.n) {
ofs << alphas[i][alphas_idx];
}
ofs << endl;
ofs.close();
ofstream ofse("alphas_edge.txt", ios::app);
i = 0;
for(; i < sample.n - 1; ++i) {
ofse << alphas_edge[i][alphas_idx] << " ";
}
if(i < sample.n) {
ofse << alphas_edge[i][alphas_idx];
}
ofse << endl;
ofse.close();
++alphas_idx;
printf("-----------------------------------------SSVM-ITERATION-%d-END\n",
struct_parm.ssvm_iteration);
++struct_parm.ssvm_iteration;
bIterate = (nMaxIterations == -1 || struct_parm.ssvm_iteration < nMaxIterations);
} while(bIterate);
// Output final segmentation for all examples
long nExamples = sample.n;
int nRFs = struct_parm.ssvm_iteration;
double* lossPerLabel = 0;
labelType* groundTruthLabels = 0;
for(int i = 0; i < nExamples; i++) { /*** example loop ***/
Slice_P* slice = sample.examples[i].x.slice;
Feature* feature = sample.examples[i].x.feature;
//map<sidType, nodeCoeffType>* nodeCoeffs = sample.examples[i].x.nodeCoeffs;
//map<sidType, edgeCoeffType>* edgeCoeffs = sample.examples[i].x.edgeCoeffs;
map<sidType, nodeCoeffType>* nodeCoeffs = 0;
map<sidType, edgeCoeffType>* edgeCoeffs = 0;
int nNodes = slice->getNbSupernodes();
stringstream soutPb;
soutPb << loss_dir;
soutPb << "pb_";
soutPb << getNameFromPathWithoutExtension(slice->getName());
soutPb << "_";
soutPb << "combined";
//soutPb << setw(5) << setfill('0') << ssvm_iteration;
soutPb << ".tif";
printf("[Main] Exporting %s\n", soutPb.str().c_str());
labelType* inferredLabels =
computeCombinedLabels(slice, feature, groundTruthLabels,
lossPerLabel, nRFs, alphas, i,
nodeCoeffs, edgeCoeffs, soutPb.str().c_str());
stringstream sout;
sout << loss_dir;
sout << getNameFromPathWithoutExtension(slice->getName());
sout << "_";
sout << "combined";
//sout << setw(5) << setfill('0') << ssvm_iteration;
sout << ".tif";
printf("[Main] Exporting %s\n", sout.str().c_str());
slice->exportOverlay(sout.str().c_str(), inferredLabels);
stringstream soutBW;
soutBW << loss_dir;
soutBW << getNameFromPathWithoutExtension(slice->getName());
soutBW << "_";
soutBW << "combined";
//soutBW << setw(5) << setfill('0') << ssvm_iteration;
soutBW << "_BW.tif";
printf("[Main] Exporting %s\n", soutBW.str().c_str());
slice->exportSupernodeLabels(soutBW.str().c_str(),
struct_parm.nClasses,
inferredLabels, nNodes,
&(struct_parm.labelToClassIdx));
delete[] inferredLabels;
}
free_struct_sample(sample);
free_struct_model(structmodel);
svm_struct_learn_api_exit();
return 0;
}
int main (int argc, char* argv[])
{
int o, i, j, cad_num;
char filename[256];
CAD **cads, *cad;
SAMPLE sample, sample_part; /* training sample */
LEARN_PARM learn_parm;
KERNEL_PARM kernel_parm;
STRUCT_LEARN_PARM struct_parm;
STRUCTMODEL structmodel;
int alg_type;
int rank;
MPI_Init(&argc, &argv);
MPI_Comm_rank(MPI_COMM_WORLD, &rank);
/* select GPU */
select_gpu(rank);
svm_struct_learn_api_init(argc,argv);
read_input_parameters(argc, argv, trainfile, cadfile, testfile, &verbosity,
&struct_verbosity, &struct_parm, &learn_parm,
&kernel_parm, &alg_type);
/* read cad models */
cads = read_cad_model(cadfile, &cad_num, 0, &struct_parm);
/* if cad_num == 1, train the final model */
if(cad_num == 1)
{
printf("Train the hierarchical model\n");
/* set the cad model for structmodel */
structmodel.cad_num = 1;
structmodel.cads = cads;
printf("Read training samples\n");
sample = read_struct_examples(trainfile, &struct_parm, &structmodel);
printf("Read training samples done\n");
if(struct_parm.is_root == 1 || struct_parm.is_aspectlet == 1)
{
/* first train weights for root parts */
printf("Train root models\n");
cad = cads[0];
struct_parm.cad_index = 0;
/* for each part */
for(i = 0; i < cad->part_num; i++)
{
/* choose what parts to train */
if((cad->roots[i] == -1 && struct_parm.is_root == 1) || (cad->roots[i] == 1 && struct_parm.is_aspectlet == 1))
{
printf("Train part %d\n", i);
/* training iteration index */
struct_parm.iter = 0;
struct_parm.part_index = i;
/* select training samples for part */
if(rank == 0)
select_examples_part(trainfile, sample, cad, 0, i);
MPI_Barrier(MPI_COMM_WORLD);
sample_part = read_struct_examples("temp_part.dat", &struct_parm, &structmodel);
/* train the root template */
struct_parm.deep = 0;
/* Do the learning and return structmodel. */
if(alg_type == 1)
svm_learn_struct(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel);
else if(alg_type == 2)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, PRIMAL_ALG);
else if(alg_type == 3)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_ALG);
else if(alg_type == 4)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_CACHE_ALG);
else
exit(1);
/* if aspectlet, train the subtree */
if(cad->roots[i] == 1 && struct_parm.is_aspectlet == 1)
{
printf("Train subtree for part %d\n", i);
struct_parm.deep = 1;
struct_parm.iter++;
/* select training samples for part */
if(rank == 0)
select_examples_part(trainfile, sample, cad, 0, i);
MPI_Barrier(MPI_COMM_WORLD);
free_struct_sample(sample_part);
sample_part = read_struct_examples("temp_part.dat", &struct_parm, &structmodel);
free_struct_model(structmodel);
/* set the cad model for structmodel */
structmodel.cad_num = 1;
structmodel.cads = cads;
if(alg_type == 1)
svm_learn_struct(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel);
else if(alg_type == 2)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, PRIMAL_ALG);
else if(alg_type == 3)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_ALG);
else if(alg_type == 4)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_CACHE_ALG);
else
exit(1);
}
/* data mining hard examples */
for(j = 0; j < struct_parm.hard_negative; j++)
{
/* increase iteration number */
struct_parm.iter++;
data_mining_hard_examples("temp_part.dat", testfile, &struct_parm, &structmodel);
/* read the training examples */
if(struct_verbosity>=1)
{
printf("Reading training examples...");
fflush(stdout);
}
free_struct_sample(sample_part);
sample_part = read_struct_examples("temp.dat", &struct_parm, &structmodel);
if(struct_verbosity>=1)
{
printf("done\n");
fflush(stdout);
}
/* Do the learning and return structmodel. */
free_struct_model(structmodel);
/* set the cad model for structmodel */
structmodel.cad_num = 1;
structmodel.cads = cads;
if(alg_type == 1)
svm_learn_struct(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel);
else if(alg_type == 2)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, PRIMAL_ALG);
else if(alg_type == 3)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_ALG);
else if(alg_type == 4)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_CACHE_ALG);
else
exit(1);
}
/* save constraints for training the full model */
if(rank == 0)
save_constraints(&struct_parm, &structmodel);
MPI_Barrier(MPI_COMM_WORLD);
free_struct_sample(sample_part);
free_struct_model(structmodel);
/* set the cad model for structmodel */
structmodel.cad_num = 1;
structmodel.cads = cads;
}
} /* end for each part */
if(rank == 0)
{
write_constraints(struct_parm.cset, &struct_parm);
free(struct_parm.cset.rhs);
for(i = 0; i < struct_parm.cset.m; i++)
free_example(struct_parm.cset.lhs[i], 1);
free(struct_parm.cset.lhs);
}
MPI_Barrier(MPI_COMM_WORLD);
} /* end if is_root == 1 */
/* train the full model */
printf("Train the full model\n");
struct_parm.iter = 0;
struct_parm.cad_index = -1;
struct_parm.part_index = -1;
struct_parm.deep = 1;
/* Do the learning and return structmodel. */
if(alg_type == 1)
svm_learn_struct(sample, &struct_parm, &learn_parm, &kernel_parm, &structmodel);
else if(alg_type == 2)
svm_learn_struct_joint(sample, &struct_parm, &learn_parm, &kernel_parm, &structmodel, PRIMAL_ALG);
else if(alg_type == 3)
svm_learn_struct_joint(sample, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_ALG);
else if(alg_type == 4)
svm_learn_struct_joint(sample, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_CACHE_ALG);
else
exit(1);
/* data mining hard examples */
while(struct_parm.hard_negative > 0)
{
/* increase iteration number */
struct_parm.iter++;
data_mining_hard_examples(trainfile, testfile, &struct_parm, &structmodel);
/* read the training examples */
if(struct_verbosity>=1)
{
printf("Reading training examples...");
fflush(stdout);
}
free_struct_sample(sample);
sample = read_struct_examples("temp.dat", &struct_parm, &structmodel);
if(struct_verbosity>=1)
{
printf("done\n");
fflush(stdout);
}
/* Do the learning and return structmodel. */
free_struct_model(structmodel);
/* set the cad model for structmodel */
structmodel.cad_num = 1;
structmodel.cads = cads;
if(alg_type == 1)
svm_learn_struct(sample, &struct_parm, &learn_parm, &kernel_parm, &structmodel);
else if(alg_type == 2)
svm_learn_struct_joint(sample, &struct_parm, &learn_parm, &kernel_parm, &structmodel, PRIMAL_ALG);
else if(alg_type == 3)
svm_learn_struct_joint(sample, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_ALG);
else if(alg_type == 4)
svm_learn_struct_joint(sample, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_CACHE_ALG);
else
exit(1);
struct_parm.hard_negative--;
}
if(rank == 0)
{
if(struct_verbosity >= 1)
{
printf("Writing learned model...");
fflush(stdout);
}
sprintf(modelfile, "%s.mod", struct_parm.cls);
write_struct_model(modelfile, &structmodel, &struct_parm);
if(struct_verbosity>=1)
{
printf("done\n");
fflush(stdout);
}
}
MPI_Barrier(MPI_COMM_WORLD);
free_struct_sample(sample);
free_struct_model(structmodel);
}
/* train weights for aspectlets */
/* start with the second aspectlet, the first one is the whole object */
for(o = 1; o < cad_num; o++)
{
printf("Train aspectlet %d\n", o);
cad = cads[o];
/* set the cad model for structmodel */
structmodel.cad_num = 1;
structmodel.cads = &cad;
/* training iteration index */
struct_parm.iter = 0;
struct_parm.cad_index = -1;
struct_parm.part_index = -1;
struct_parm.deep = 1;
/* select training samples for the aspectlet */
if(rank == 0)
select_examples_aspectlet(trainfile, cads, o);
MPI_Barrier(MPI_COMM_WORLD);
printf("Read training samples\n");
sample_part = read_struct_examples("temp_part.dat", &struct_parm, &structmodel);
printf("Read training samples done\n");
/* Do the learning and return structmodel. */
if(alg_type == 1)
svm_learn_struct(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel);
else if(alg_type == 2)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, PRIMAL_ALG);
else if(alg_type == 3)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_ALG);
else if(alg_type == 4)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_CACHE_ALG);
else
exit(1);
/* data mining hard examples */
for(i = 0; i < struct_parm.hard_negative; i++)
{
/* increase iteration number */
struct_parm.iter++;
data_mining_hard_examples("temp_part.dat", testfile, &struct_parm, &structmodel);
/* read the training examples */
if(struct_verbosity>=1)
{
printf("Reading training examples...");
fflush(stdout);
}
free_struct_sample(sample_part);
sample_part = read_struct_examples("temp.dat", &struct_parm, &structmodel);
if(struct_verbosity>=1)
{
printf("done\n");
fflush(stdout);
}
/* Do the learning and return structmodel. */
free_struct_model(structmodel);
/* set the cad model for structmodel */
structmodel.cad_num = 1;
structmodel.cads = &cad;
if(alg_type == 1)
svm_learn_struct(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel);
else if(alg_type == 2)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, PRIMAL_ALG);
else if(alg_type == 3)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_ALG);
else if(alg_type == 4)
svm_learn_struct_joint(sample_part, &struct_parm, &learn_parm, &kernel_parm, &structmodel, DUAL_CACHE_ALG);
else
exit(1);
}
if(rank == 0)
{
if(struct_verbosity>=1)
{
printf("Writing learned model...");
fflush(stdout);
}
sprintf(modelfile, "%s_cad%03d.mod", struct_parm.cls, o);
write_struct_model(modelfile, &structmodel, &struct_parm);
if(struct_verbosity>=1)
{
printf("done\n");
fflush(stdout);
}
}
MPI_Barrier(MPI_COMM_WORLD);
free_struct_sample(sample_part);
free_struct_model(structmodel);
} /* end for each cad model */
for(i = 0; i < cad_num; i++)
destroy_cad(cads[i]);
free(cads);
svm_struct_learn_api_exit();
MPI_Finalize();
return 0;
}
void MedSTC::svmStructSolver(char *dataFileName, Params *param, double *res)
{
LEARN_PARM learn_parm;
KERNEL_PARM kernel_parm;
STRUCT_LEARN_PARM struct_parm;
STRUCTMODEL structmodel;
int alg_type = 2;
/* set the parameters. */
set_init_param(&struct_parm, &learn_parm, &kernel_parm, &alg_type);
struct_parm.C = m_dC;
/* read the training examples */
SAMPLE sample = read_struct_examples(dataFileName, &struct_parm);
if(param->SVM_ALGTYPE == 0)
svm_learn_struct(sample, &struct_parm, &learn_parm, &kernel_parm, &structmodel, NSLACK_ALG);
//else if(alg_type == 1)
// svm_learn_struct(sample, &struct_parm, &learn_parm, &kernel_parm, &structmodel, NSLACK_SHRINK_ALG);
else if(param->SVM_ALGTYPE == 2) {
struct_parm.C = m_dC * sample.n; // Note: in n-slack formulation, C is not divided by N.
svm_learn_struct_joint(sample, &struct_parm, &learn_parm,
&kernel_parm, &structmodel, ONESLACK_PRIMAL_ALG);
} else if ( param->SVM_ALGTYPE == 3 ) {
struct_parm.C = m_dC * sample.n; // Note: in n-slack formulation, C is not divided by N.
int nEtaNum = m_nLabelNum * m_nK;
for ( int i=1; i<=nEtaNum; i++ ) {
initEta_[i] = m_dEta[i-1];
}
svm_learn_struct_joint( sample, &struct_parm, &learn_parm,
&kernel_parm, &structmodel, ONESLACK_PRIMAL_ALG, initEta_, nEtaNum );
}
/* get the optimal lagrangian multipliers.
* Note: for 1-slack formulation: the "marginalization" is
* needed for fast computation.
*/
int nVar = sample.n * m_nLabelNum;
for ( int k=0; k<nVar; k++ ) m_dMu[k] = 0;
if ( param->SVM_ALGTYPE == 0 ) {
for ( int k=1; k<structmodel.svm_model->sv_num; k++ ) {
int docnum = structmodel.svm_model->supvec[k]->orgDocNum;
m_dMu[docnum] = structmodel.svm_model->alpha[k];
}
} else if ( param->SVM_ALGTYPE == 2 ) {
for ( int k=1; k<structmodel.svm_model->sv_num; k++ ) {
int *vecLabel = structmodel.svm_model->supvec[k]->lvec;
double dval = structmodel.svm_model->alpha[k] / sample.n;
for ( int d=0; d<sample.n; d++ ) {
int label = vecLabel[d];
m_dMu[d*m_nLabelNum + label] += dval;
}
}
} else ;
//FILE *fileptr = fopen("SVMLightSolution.txt", "a");
// set the SVM parameters.
m_dB = structmodel.svm_model->b;
for ( int y=0; y<m_nLabelNum; y++ ) {
for ( int k=0; k<m_nK; k++ ){
int etaIx = y * m_nK + k;
m_dEta[etaIx] = structmodel.w[etaIx+1];
}
}
m_dsvm_primalobj = structmodel.primalobj;
// free the memory
free_struct_sample(sample);
free_struct_model(structmodel);
}
void
mexFunction (int nout, mxArray ** out, int nin, mxArray const ** in)
{
SAMPLE sample; /* training sample */
LEARN_PARM learn_parm;
KERNEL_PARM kernel_parm;
STRUCT_LEARN_PARM struct_parm;
STRUCTMODEL structmodel;
int alg_type;
enum {IN_ARGS=0, IN_SPARM} ;
enum {OUT_W=0} ;
/* SVM-light is not fully reentrant, so we need to run this patch first */
init_qp_solver() ;
verbosity = 0 ;
kernel_cache_statistic = 0 ;
if (nin != 2) {
mexErrMsgTxt("Two arguments required") ;
}
/* Parse ARGS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */
char arg [1024 + 1] ;
int argc ;
char ** argv ;
if (! uIsString(in[IN_ARGS], -1)) {
mexErrMsgTxt("ARGS must be a string") ;
}
mxGetString(in[IN_ARGS], arg, sizeof(arg) / sizeof(char)) ;
arg_split (arg, &argc, &argv) ;
svm_struct_learn_api_init(argc+1, argv-1) ;
read_input_parameters (argc+1,argv-1,
&verbosity, &struct_verbosity,
&struct_parm, &learn_parm,
&kernel_parm, &alg_type ) ;
if (kernel_parm.kernel_type != LINEAR &&
kernel_parm.kernel_type != CUSTOM) {
mexErrMsgTxt ("Only LINEAR or CUSTOM kerneles are supported") ;
}
/* Parse SPARM ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */
mxArray const * sparm_array = in [IN_SPARM] ;
mxArray const * patterns_array ;
mxArray const * labels_array ;
mxArray const * kernelFn_array ;
int numExamples, ei ;
if (! sparm_array) {
mexErrMsgTxt("SPARM must be a structure") ;
}
struct_parm.mex = sparm_array ;
patterns_array = mxGetField(sparm_array, 0, "patterns") ;
if (! patterns_array ||
! mxIsCell(patterns_array)) {
mexErrMsgTxt("SPARM.PATTERNS must be a cell array") ;
}
numExamples = mxGetNumberOfElements(patterns_array) ;
labels_array = mxGetField(sparm_array, 0, "labels") ;
if (! labels_array ||
! mxIsCell(labels_array) ||
! mxGetNumberOfElements(labels_array) == numExamples) {
mexErrMsgTxt("SPARM.LABELS must be a cell array "
"with the same number of elements of "
"SPARM.PATTERNS") ;
}
sample.n = numExamples ;
sample.examples = (EXAMPLE *) my_malloc (sizeof(EXAMPLE) * numExamples) ;
for (ei = 0 ; ei < numExamples ; ++ ei) {
sample.examples[ei].x.mex = mxGetCell(patterns_array, ei) ;
sample.examples[ei].y.mex = mxGetCell(labels_array, ei) ;
sample.examples[ei].y.isOwner = 0 ;
}
if (struct_verbosity >= 1) {
mexPrintf("There are %d training examples\n", numExamples) ;
}
kernelFn_array = mxGetField(sparm_array, 0, "kernelFn") ;
if (! kernelFn_array && kernel_parm.kernel_type == CUSTOM) {
mexErrMsgTxt("SPARM.KERNELFN must be define for CUSTOM kernels") ;
}
if (kernelFn_array) {
MexKernelInfo * info ;
if (mxGetClassID(kernelFn_array) != mxFUNCTION_CLASS) {
mexErrMsgTxt("SPARM.KERNELFN must be a valid function handle") ;
}
info = (MexKernelInfo*) kernel_parm.custom ;
info -> structParm = sparm_array ;
info -> kernelFn = kernelFn_array ;
}
/* Learning ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */
switch (alg_type) {
case 0:
svm_learn_struct(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,NSLACK_ALG) ;
break ;
case 1:
svm_learn_struct(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,NSLACK_SHRINK_ALG);
break ;
case 2:
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,ONESLACK_PRIMAL_ALG);
break ;
case 3:
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,ONESLACK_DUAL_ALG);
break ;
case 4:
svm_learn_struct_joint(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel,ONESLACK_DUAL_CACHE_ALG);
break ;
case 9:
svm_learn_struct_joint_custom(sample,&struct_parm,&learn_parm,&kernel_parm,&structmodel);
break ;
default:
mexErrMsgTxt("Unknown algorithm type") ;
}
/* Write output ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */
/* Warning: The model contains references to the original data 'docs'.
If you want to free the original data, and only keep the model, you
have to make a deep copy of 'model'. */
mxArray * model_array = newMxArrayEncapsulatingSmodel (&structmodel) ;
out[OUT_W] = mxDuplicateArray (model_array) ;
destroyMxArrayEncapsulatingSmodel (model_array) ;
free_struct_sample (sample) ;
free_struct_model (structmodel) ;
svm_struct_learn_api_exit () ;
free_qp_solver () ;
}
int svm_struct_learn (int argc, char* argv[], SAMPLE *sample, STRUCTMODEL *model, STRUCT_LEARN_PARM *struct_parm)
{
char trainfile[200]; /* file with training examples */
char modelfile[200]; /* file for resulting classifier */
STRUCTMODEL structmodel;
LEARN_PARM learn_parm;
KERNEL_PARM kernel_parm;
int alg_type;
//SAMPLE _sample;
//int i, j;
HIDEO_ENV *hideo_env=create_env();
svm_struct_learn_api_init(argc,argv);
svm_struct_read_input_parameters(argc,argv,trainfile,modelfile,&verbosity,
&struct_verbosity,struct_parm,&learn_parm,
&kernel_parm,&alg_type);
// _sample=read_struct_examples("C:\\NewWork\\SvmLightLib\\SvmLightLibDemo\\Examples\\Multiclass\\train.dat",struct_parm);
// // compare _sample to *sample
// assert(_sample.n == sample->n);
// for (i = 0; i < _sample.n; i++)
// {
// SVECTOR *vec_1 = _sample.examples[i].x.doc->fvec;
// SVECTOR *vec_2 = sample->examples[i].x.doc->fvec;
// assert(vec_1->factor == vec_2->factor);
// assert(vec_1->kernel_id == vec_2->kernel_id);
// assert(vec_1->next == vec_2->next);
// assert(vec_1->twonorm_sq == vec_2->twonorm_sq);
// assert(strcmp(vec_1->userdefined, vec_2->userdefined) == 0);
// j = 0;
// while (vec_1->words[j].wnum > 0 || vec_2->words[j].wnum > 0)
// {
// //printf("%d %d\n", vec_1->words[j].wnum, vec_2->words[j].wnum);
// //printf("%f %f\n", vec_1->words[j].weight, vec_2->words[j].weight);
// assert(vec_1->words[j].wnum == vec_2->words[j].wnum);
// assert(vec_1->words[j].weight == vec_2->words[j].weight);
// j++;
// }
// }
// //sample=&_sample;
/* Do the learning and return structmodel. */
if(alg_type == 1)
svm_learn_struct(*sample,struct_parm,&learn_parm,&kernel_parm,&structmodel,hideo_env);
else if(alg_type == 2)
svm_learn_struct_joint(*sample,struct_parm,&learn_parm,&kernel_parm,&structmodel,PRIMAL_ALG,hideo_env);
else if(alg_type == 3)
svm_learn_struct_joint(*sample,struct_parm,&learn_parm,&kernel_parm,&structmodel,DUAL_ALG,hideo_env);
else if(alg_type == 4)
svm_learn_struct_joint(*sample,struct_parm,&learn_parm,&kernel_parm,&structmodel,DUAL_CACHE_ALG,hideo_env);
else
exit(1);
/* Warning: The model contains references to the original data 'docs'.
If you want to free the original data, and only keep the model, you
have to make a deep copy of 'model'. */
model->sizePsi=structmodel.sizePsi;
model->svm_model=copy_model(structmodel.svm_model);
model->w=model->svm_model->lin_weights;
free_struct_model(structmodel);
svm_struct_learn_api_exit();
return 0;
}
