sys.stderr = open(os.path.join(scoresPath, 'gridsearch_err.txt'),
'w') #log to a file
#variables inizialization
nFolds = 1
C_range = 2.0**np.arange(-5, 15 + 2, 2) # libsvm range
gamma_range = 2.0**np.arange(-15, 3 + 2, 2) # libsvm range
mixtures = 2**np.arange(0, 7, 1)
scores = np.zeros((mixtures.shape[0], nFolds))
cBestValues = np.zeros((mixtures.shape[0], nFolds))
gBestValues = np.zeros((mixtures.shape[0], nFolds))
mIdx = 0
#LOAD DATASET
snoring_dataset = dm.load_ComParE2017(featPath, filetype) # load dataset
trainset, develset, testset = dm.split_ComParE2017_simple(
snoring_dataset
) # creo i trainset per calcolare media e varianza per poter normalizzare
labels = dm.label_loading(
os.path.join(root_dir, 'lab', 'ComParE2017_Snore.tsv'))
trainset_l, develset_l, _ = dm.split_ComParE2017_simple(labels)
del snoring_dataset
y = []
for seq in trainset:
y.append(seq[0])
yd = []
for seq in develset:
yd.append(seq[0])
def process_subfold(sf, fold):
print("Fold " + str(fold))
t0 = time.time()
snoring_dataset = dm.load_ComParE2017(featPath, filetype) # load dataset
trainset, develset, testset = dm.split_ComParE2017_simple(snoring_dataset)
# creo i trainset per calcolare media e varianza per poter normalizzare
del snoring_dataset
# Read dataset size and preallocate
a = trainset[0][1].shape
if filetype == 'npy':
nfeat = a[0]
else:
nfeat = a[1]
# Read the features
trainFeat = np.empty([1, nfeat])
for seq in trainset:
if filetype == 'npy':
feat = seq[1].transpose()
else:
feat = seq[1]
# metto tutte le features in una matrice che poi passero al gmm.fit per adattaare l'UBM
trainFeat = np.vstack((trainFeat, feat))
trainFeat = np.delete(trainFeat, 0, 0)
print("DONE!")
# trainFeat = trainFeat.astype(dtype='float32')
for m in mixtures:
# Train the UBM
print("Fold " + str(fold) + "-->Mixture: " + str(m) + " ")
sys.stdout.flush()
gmm = mixture.GMM(n_components=m, n_iter=1000, random_state=1)
gmm.fit(trainFeat)
ubmPath = os.path.join(curUbmsPath, str(m))
if not os.path.exists(ubmPath):
try: # handle the simultaneous creation of folders from multiple processes
os.makedirs(ubmPath)
except OSError:
print("OSError.errno 17 ignored")
if not gmm.converged_:
print("Fold " + str(fold) + "-->Convergence not reached with " +
str(m) + " mixtures")
joblib.dump(gmm, os.path.join(ubmPath, "ubm_" + str(sf)))
# salvo l'ubm. mi crea le varie compie tipo ubm_1_02 ecc... per poterle magari riutilizzare per il debug
# Extract trainset supervectors
curSupervecSubPath = os.path.join(curSupervecPath, str(m))
if (not os.path.exists(curSupervecSubPath)):
try: # handle the simultaneous creation of folders from multiple processes
os.makedirs(curSupervecSubPath)
except OSError:
print("OSError.errno 17 ignored")
for seq in trainset:
gmmMap = GmmMap(n_components=m, n_iter=5, params="m")
# gli passo i parametri del'ubm calcolato in precedenza
gmmMap.weights_ = copy.deepcopy(gmm.weights_)
gmmMap.means_ = copy.deepcopy(gmm.means_)
gmmMap.covars_ = copy.deepcopy(gmm.covars_)
# leggo una feature
if filetype == 'npy':
feat = seq[1].transpose()
else:
feat = seq[1]
gmmMap.map_adapt(feat)
# adatta l'ubm ad una feature
# means_and_covars = np.hstack((gmmMap.means_, gmmMap.covars_))
svFilePath = os.path.join(
curSupervecSubPath,
os.path.splitext(os.path.basename(seq[0]))[0])
np.save(svFilePath, gmmMap.means_)
# np.save(svFilePath, means_and_covars,)
# Extract devset supervectors
for seq in develset:
gmmMap = GmmMap(n_components=m, n_iter=5, params="m")
gmmMap.weights_ = copy.deepcopy(gmm.weights_)
gmmMap.means_ = copy.deepcopy(gmm.means_)
gmmMap.covars_ = copy.deepcopy(gmm.covars_)
if filetype == 'npy':
feat = seq[1].transpose()
else:
feat = seq[1]
gmmMap.map_adapt(feat)
# adatta l'ubm ad una feature
means_and_covars = np.hstack((gmmMap.means_, gmmMap.covars_))
svFilePath = os.path.join(
curSupervecSubPath,
os.path.splitext(os.path.basename(seq[0]))[0])
np.save(svFilePath, gmmMap.means_)
# np.save(svFilePath, means_and_covars,)
for seq in testset:
gmmMap = GmmMap(n_components=m, n_iter=5, params="m")
gmmMap.weights_ = copy.deepcopy(gmm.weights_)
gmmMap.means_ = copy.deepcopy(gmm.means_)
gmmMap.covars_ = copy.deepcopy(gmm.covars_)
if filetype == 'npy':
feat = seq[1].transpose()
else:
feat = seq[1]
gmmMap.map_adapt(feat)
# adatta l'ubm ad una feature
means_and_covars = np.hstack((gmmMap.means_, gmmMap.covars_))
svFilePath = os.path.join(
curSupervecSubPath,
os.path.splitext(os.path.basename(seq[0]))[0])
np.save(svFilePath, gmmMap.means_)
# np.save(svFilePath, means_and_covars,)
t1 = time.time()
print("Fold " + str(fold) + "--Time: " + str(t1 - t0))
def process_subfold(sf,fold):
print("Fold "+str(fold));
t0 = time.time();
snoring_dataset = dm.load_ComParE2017(featPath, filetype) # load dataset
trainset, develset, testset = dm.split_ComParE2017_simple(snoring_dataset) # creo i trainset per calcolare media e varianza per poter normalizzare
del snoring_dataset
# Read dataset size and preallocate
a=trainset[0][1].shape
if (filetype == 'npy'):
nfeat = a[0]
else:
nfeat = a[1]
# Read the features
trainFeat=np.empty([1,nfeat])
#for seq in trainset:
for seq in develset:
if (filetype == 'npy'):
feat = seq[1].transpose()
else:
feat = seq[1]
# metto tutte le features in una matrice che poi passero al gmm.fit per adattaare l'UBM
trainFeat = np.vstack((trainFeat, feat))
trainFeat = np.delete(trainFeat, 0, 0)
print("DONE!")
#trainFeat = trainFeat.astype(dtype='float32')
for m in mixtures:
# Train the UBM
print("Fold "+str(fold)+"-->Mixture: "+str(m)+" ");
sys.stdout.flush();
gmm = mixture.GMM(n_components=m, n_iter=1000, random_state=1);
gmm.fit(trainFeat);
ubmPath = os.path.join(curUbmsPath, str(m));
if (not os.path.exists(ubmPath)):
try:#handle the simultaneous creation of folders from multiple processes
os.makedirs(ubmPath);
except OSError, e:
if e.errno != 17:
raise
else:
print "OSError.errno 17 ignored"
pass
if (not gmm.converged_):
print("Fold "+str(fold)+"-->Convergence not reached with " + str(m) +" mixtures");
joblib.dump(gmm, os.path.join(ubmPath, "ubm_" + str(sf))); #salvo l'ubm. mi crea le varie compie tipo ubm_1_02 ecc... per poterle magari riutilizzare per il debug
# Extract trainset supervectors
curSupervecSubPath = os.path.join(curSupervecPath, str(m));
if (not os.path.exists(curSupervecSubPath)):
try:#handle the simultaneous creation of folders from multiple processes
os.makedirs(curSupervecSubPath);
except OSError, e:
if e.errno != 17:
raise
else:
print "OSError.errno 17 ignored"
pass
with open(experiments_db, 'a+') as f:
f.write(line)
EXPERIMENT_TAG = fold_name
### Create directories ###
FOLDER_PREFIX = path.join(root_dir, RESULTS_DIR, EXPERIMENT_TAG)
if not path.exists(FOLDER_PREFIX):
makedirs(FOLDER_PREFIX)
MODEL_PATH = path.join(FOLDER_PREFIX, 'model')
if not path.exists(MODEL_PATH):
makedirs(MODEL_PATH)
SCORES_PATH = path.join(FOLDER_PREFIX, 'scores')
if not path.exists(SCORES_PATH):
makedirs(SCORES_PATH)
#GESTIONE DATASET
snoring_dataset = dm.load_ComParE2017(
path.join(root_dir, 'dataset', args.featureset)) #load dataset
labels = dm.label_loading(path.join(root_dir, 'lab', 'ComParE2017_Snore.tsv'))
trainset, develset, testset = dm.split_ComParE2017_simple(
snoring_dataset
) #creo i trainset per calcolare media e varianza per poter normalizzare
trainset_l, develset_l, _ = dm.split_ComParE2017_simple(labels)
del snoring_dataset
trainset, mean, std = dm.normalize_data(
trainset) #compute mean and std of the trainset and normalize the trainset
#normalize the dataset with the mean and std of the trainset
develset, _, _ = dm.normalize_data(develset, mean, std)
#testset, _, _ = dm.normalize_data(testset, mean, std)