owen/lms
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

WIP, reworking features

Browse Source
This commit is contained in:
emeric
2019-11-08 13:34:07 +01:00
parent f3c02a84ba
commit 07eae9cf96
18 changed files with 328 additions and 339 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/Makefile.am
+1 -1
View File
@@ -1,4 +1,4 @@
if BUILD_TOOLS
SUBDIRS = similarity metadata
SUBDIRS = similarity similarity-parameters metadata
endif
tools/similarity-parameters/LmsSimilarityParameters.cpp
+49
View File
@@ -0,0 +1,49 @@
#include <iostream>
#include <filesystem>
#include <string>
#include "database/Db.hpp"
#include "utils/Config.hpp"
#include "utils/Service.hpp"
int main(int argc, char *argv[])
{
try
{
std::filesystem::path configFilePath {"/etc/lms.conf"};
if (argc >= 2)
configFilePath = std::string(argv[1], 0, 256);
ServiceProvider<Config>::create(configFilePath);
Database::Db db {getService<Config>()->getPath("working-dir") / "lms.db"};
auto session {db.createSession()};
/* const FeatureSettings
{
{ "lowlevel.average_loudness", 1 },
{ "lowlevel.dynamic_complexity", 1 },
{ "lowlevel.spectral_contrast_coeffs.median", 6 },
{ "lowlevel.erbbands.median", 40 },
{ "tonal.hpcp.median", 36 },
{ "lowlevel.melbands.median", 40 },
{ "lowlevel.barkbands.median", 27 },
{ "lowlevel.mfcc.mean", 13 },
{ "lowlevel.gfcc.mean", 13 },
};
const TrackFeaturesMap trackFeaturesMap {getAllTrackFeatures(*session)};
std::cout << "Found " << trackFeaturesMap.size() << " tracks with features!" << std::endl;*/
}
catch (std::exception& e)
{
std::cerr << "Caught exception: " << e.what() << std::endl;
}
return EXIT_SUCCESS;
}
tools/similarity-parameters/Makefile.am
+24
View File
@@ -0,0 +1,24 @@
noinst_PROGRAMS = lms-similarity-parameters
lms_similarity_parameters_SOURCES = \
$(srcdir)/LmsSimilarityParameters.cpp \
$(top_srcdir)/src/database/Artist.cpp \
$(top_srcdir)/src/database/Cluster.cpp \
$(top_srcdir)/src/database/Db.cpp \
$(top_srcdir)/src/database/TrackFeatures.cpp \
$(top_srcdir)/src/database/TrackList.cpp \
$(top_srcdir)/src/database/Release.cpp \
$(top_srcdir)/src/database/ScanSettings.cpp \
$(top_srcdir)/src/database/Session.cpp \
$(top_srcdir)/src/database/SimilaritySettings.cpp \
$(top_srcdir)/src/database/SqlQuery.cpp \
$(top_srcdir)/src/database/Track.cpp \
$(top_srcdir)/src/database/User.cpp \
$(top_srcdir)/src/similarity/features/som/DataNormalizer.cpp \
$(top_srcdir)/src/similarity/features/som/Network.cpp \
$(top_srcdir)/src/utils/Config.cpp \
$(top_srcdir)/src/utils/Logger.cpp \
$(top_srcdir)/src/utils/Utils.cpp
lms_similarity_parameters_CXXFLAGS=-std=c++17 -I$(top_srcdir)/src -D_REENTRANT
tools/similarity/LmsSimilarity.cpp
+13 -199
View File
@@ -1,88 +1,32 @@
#include <chrono>
#include <filesystem>
#include <iostream>
#include <stdexcept>
#include <stdlib.h>
#include <string>
#include "database/Db.hpp"
#include "database/Session.hpp"
#include "database/Track.hpp"
#include "database/Artist.hpp"
#include "database/Cluster.hpp"
#include "database/Release.hpp"
#include "database/TrackFeatures.hpp"
#include "utils/Config.hpp"
#include "utils/Service.hpp"
#include "similarity/features/som/DataNormalizer.hpp"
#include "similarity/features/som/Network.hpp"
static
std::ostream& operator<<(std::ostream& os, const Database::Track::pointer& track)
{
os << "[";
for (auto artist : track->getArtists())
os << artist->getName() << " - ";
if (track->getRelease())
os << track->getRelease()->getName() << " - ";
os << track->getName() << "]";
return os;
}
static
bool
getTrackFeatures(Database::Session&, const Database::Track::pointer& track, const std::map<std::string, std::size_t>& featuresSettings, SOM::InputVector& res)
{
std::map<std::string, std::vector<double>> features;
for (const auto& featureSettings : featuresSettings)
features[featureSettings.first] = {};
if (!track->getTrackFeatures()->getFeatures(features))
{
std::cout << "Skipping track '" << track->getMBID() << "': missing item" << std::endl;
return false;
};
std::size_t index {};
for (const auto& feature : features)
{
auto it = featuresSettings.find(feature.first);
if (it == featuresSettings.end() || (feature.second.size() != it->second))
return false;
for (double value : feature.second)
res[index++] = value;
}
return true;
}
#include "similarity/features/SimilarityFeaturesSearcher.hpp"
int main(int argc, char *argv[])
{
try
{
const std::size_t width = 5;
const std::size_t height = 5;
const std::size_t nbIterations = 10;
std::size_t nbTracks = 5000;
using namespace Similarity;
const std::map<std::string, std::size_t> featuresSettings =
const FeatureSettingsMap featuresSettings
{
// { "lowlevel.average_loudness", 1 },
// { "lowlevel.dynamic_complexity", 1 },
{ "lowlevel.spectral_contrast_coeffs.median", 6 },
{ "lowlevel.erbbands.median", 40 },
{ "tonal.hpcp.median", 36 },
{ "lowlevel.melbands.median", 40 },
{ "lowlevel.barkbands.median", 27 },
{ "lowlevel.mfcc.mean", 13 },
{ "lowlevel.gfcc.mean", 13 },
{ "lowlevel.spectral_contrast_coeffs.median", {1} },
{ "lowlevel.erbbands.median", {1} },
{ "tonal.hpcp.median", {1} },
{ "lowlevel.melbands.median", {1} },
{ "lowlevel.barkbands.median", {1} },
{ "lowlevel.mfcc.mean", {1} },
{ "lowlevel.gfcc.mean", {1} },
};
std::size_t nbDims = 0;
for (const auto& featureSettings : featuresSettings)
nbDims += featureSettings.second;
std::filesystem::path configFilePath {"/etc/lms.conf"};
if (argc >= 2)
@@ -94,147 +38,17 @@ int main(int argc, char *argv[])
auto session {db.createSession()};
std::cout << "Getting all features..." << std::endl;
auto transaction {session->createUniqueTransaction()};
std::vector<Database::IdType> trackIds {Database::Track::getAllIdsWithFeatures(*session, nbTracks)};
nbTracks = trackIds.size();
std::cout << "Getting features DONE (" << nbTracks << " tracks)" << std::endl;
std::cout << "Reading features..." << std::endl;
std::vector<SOM::InputVector> tracksFeatures;
for (Database::IdType trackId : trackIds)
{
Database::Track::pointer track {Database::Track::getById(*session, trackId)};
if (!track)
continue;
SOM::InputVector features {nbDims};
if (!getTrackFeatures(*session, track, featuresSettings, features))
continue;
tracksFeatures.emplace_back(std::move(features));
}
std::cout << "Reading features DONE" << std::endl;
SOM::Network network {width, height, nbDims};
SOM::DataNormalizer normalizer {nbDims};
SOM::InputVector weights {nbDims};
{
std::size_t index {};
for (const auto& featureSettings : featuresSettings)
{
for (std::size_t i {}; i < featureSettings.second; ++i)
weights[index++] = SOM::InputVector::value_type{1. / featureSettings.second};
}
}
network.setDataWeights(weights);
std::cout << "Weights: " << weights << std::endl;
std::cout << "Normalizing..." << std::endl;
normalizer.computeNormalizationFactors(tracksFeatures);
std::cout << "Dumping normalizer: " << std::endl;
normalizer.dump(std::cout);
std::cout << "Dumping normalizer DONE" << std::endl;
for (SOM::InputVector& features : tracksFeatures)
normalizer.normalizeData(features);
std::cout << "Normalizing DONE" << std::endl;
auto progress {[](const SOM::Network::CurrentIteration& iteration)
{
std::cout << "Iteration " << iteration.idIteration + 1 << " of " << iteration.iterationCount << std::endl;;
}};
std::cout << "Training..." << std::endl;
network.train(tracksFeatures, nbIterations, progress);
std::cout << "Training DONE" << std::endl;
auto meanDistance = network.computeRefVectorsDistanceMean();
std::cout << "MEAN distance = " << meanDistance << std::endl;
auto medianDistance = network.computeRefVectorsDistanceMedian();
std::cout << "MEDIAN distance = " << medianDistance << std::endl;
std::cout << "Classifying tracks..." << std::endl;
SOM::Matrix< std::vector<Database::Track::pointer> > tracksMap(width, height);
for (Database::IdType trackId : trackIds)
{
Database::Track::pointer track {Database::Track::getById(*session, trackId)};
if (!track)
continue;
SOM::InputVector features {nbDims};
if (!getTrackFeatures(*session, track, featuresSettings, features))
continue;
normalizer.normalizeData(features);
SOM::Position position = network.getClosestRefVectorPosition(features);
tracksMap[position].push_back(track);
}
// may be long...
FeaturesSearcher searcher {*session, featuresSettings};
std::cout << "Classifying tracks DONE" << std::endl;
// Dump tracks
for (SOM::Coordinate y = 0; y < tracksMap.getHeight(); ++y)
{
for (SOM::Coordinate x = 0; x < tracksMap.getWidth(); ++x)
{
std::cout << "{" << x << ", " << y << "}" << std::endl;
const auto& tracks = tracksMap[{x, y}];
for (const auto& track : tracks)
{
std::cout << " - " << track << std::endl;
}
}
}
// For each track, get the nearest tracks
for (Database::IdType trackId : trackIds)
{
Database::Track::pointer track {Database::Track::getById(*session, trackId)};
if (!track)
continue;
SOM::InputVector features {nbDims};
if (!getTrackFeatures(*session, track, featuresSettings, features))
continue;
normalizer.normalizeData(features);
SOM::Position refVectorPosition {network.getClosestRefVectorPosition(features)};
std::cout << "Getting nearest songs for track " << track << " in {" << refVectorPosition.x << ", " << refVectorPosition.y << "}:" << std::endl;
for (auto similarTrack : tracksMap[refVectorPosition])
std::cout << " - " << similarTrack << std::endl;
std::set<SOM::Position> neighbourPosition {refVectorPosition};
for (std::size_t i {}; i < 3; ++i)
{
auto position = network.getClosestRefVectorPosition(neighbourPosition, medianDistance);
if (!position)
break;
std::cout << " - in {" << position->x << ", " << position->y << "}, dist = " << network.getRefVectorsDistance(*position, refVectorPosition) << std::endl;
for (const auto& similarTrack : tracksMap[*position])
std::cout << " - " << similarTrack << std::endl;
neighbourPosition.insert(*position);
}
}
}
catch( std::exception& e)
{
std::cerr << "Caught exception: " << e.what() << std::endl;
return EXIT_FAILURE;
}
return EXIT_SUCCESS;
tools/similarity/Makefile.am
+3
View File
@@ -16,6 +16,9 @@ lms_similarity_SOURCES = \
$(top_srcdir)/src/database/User.cpp \
$(top_srcdir)/src/similarity/features/som/DataNormalizer.cpp \
$(top_srcdir)/src/similarity/features/som/Network.cpp \
$(top_srcdir)/src/similarity/features/SimilarityFeaturesCache.cpp \
$(top_srcdir)/src/similarity/features/SimilarityFeaturesSearcher.cpp \
$(top_srcdir)/src/similarity/features/SimilarityFeaturesDefs.cpp \
$(top_srcdir)/src/utils/Config.cpp \
$(top_srcdir)/src/utils/Logger.cpp \
$(top_srcdir)/src/utils/Utils.cpp