model_num_iterations = modelPickle['model_num_iterations']
kernelString = modelPickle['kernelString']
Q = modelPickle['Q']
economy_save = True
pose_index = ['']
pose_selection = 0
# # Creates a SAMpy object
mySAMpy = SAMDriver_interaction(False,
imgH=imgH,
imgW=imgW,
imgHNew=imgHNew,
imgWNew=imgWNew)
# # Reading face data, preparation of data and training of the model
mySAMpy.readData(dataPath, participantList, pose_index)
minImages = mySAMpy.Y.shape[1]
Ntr = int(minImages * ratioData / 100)
Ntest = minImages - Ntr
allPersonsY = mySAMpy.Y
allPersonsL = mySAMpy.L
for i in range(len(participantList)):
#print participantList[i]
mySAMpy.Y = allPersonsY[:, :, i, None]
mySAMpy.L = allPersonsL[:, :, i, None]
(Yalli, Lalli, YtestAlli, LtestAlli) = mySAMpy.prepareData(model_type,
Ntr,
pose_selection,
image_suffix = modelPickle['image_suffix'] model_type = modelPickle['model_type'] model_num_inducing = modelPickle['num_inducing'] model_init_iterations = modelPickle['model_init_iterations'] model_num_iterations = modelPickle['model_num_iterations'] kernelString = modelPickle['kernelString'] Q = modelPickle['Q'] economy_save = True pose_index=[''] pose_selection = 0 # # Creates a SAMpy object mySAMpy = SAMDriver_interaction(False, imgH = imgH, imgW = imgW, imgHNew = imgHNew, imgWNew = imgWNew) # # Reading face data, preparation of data and training of the model mySAMpy.readData(dataPath, participantList, pose_index) minImages = mySAMpy.Y.shape[1] Ntr = int(minImages*ratioData/100) Ntest = minImages - Ntr allPersonsY = mySAMpy.Y; allPersonsL = mySAMpy.L; for i in range(len(participantList)): #print participantList[i] mySAMpy.Y = allPersonsY[:,:,i,None] mySAMpy.L = allPersonsL[:,:,i,None] (Yalli, Lalli, YtestAlli, LtestAlli) = mySAMpy.prepareData(model_type, Ntr, pose_selection, randSeed=2) if(i==0):
# Specification of model type and training parameters
model_type = 'mrd'
model_num_inducing = 30
model_num_iterations = 700
model_init_iterations = 2000
fname = modelPath + '/models/' + 'mActions_' + model_type + '_exp' + str(experiment_number) #+ '.pickle'
# Enable to save the model and visualise GP nearest neighbour matching
save_model=True
economy_save = True # ATTENTION!! This is still BETA!!
visualise_output=False
test_mode = False
# Reading face data, preparation of data and training of the model
mySAMpy.readData(root_data_dir, participant_index, pose_index)
(Yall, Lall, YtestAll, LtestAll) = mySAMpy.prepareData(model_type, Ntr, pose_selection, randSeed=experiment_number)
Lunique = numpy.unique(mySAMpy.L)
L_index = dict()
for i in range(len(Lunique)):
L_index[Lunique[i]] = numpy.where(mySAMpy.L == i)[0]
mm = []
for i in range(len(Lunique)):
print('# Considering label: ' + str(Lunique[i]))
cur = SAMDriver_interaction(True, imgH = 400, imgW = 400, imgHNew = 200, imgWNew = 200,inputImagePort="/CLM/imageSeg/out", openPorts=False)
##############
Y_cur = Yall[L_index[i],:].copy()
Ytest_cur = YtestAll[L_index[i],:].copy()
if('.pickle' in modelPath):
fname = '/'.join(modelPath.split('/')[:-1]) + '/' + dataPath.split('/')[-1] + '__' + trainName + '__' + model_type + '__exp' + str(experiment_number)
else:
fname = modelPath + dataPath.split('/')[-1] + '__' + trainName + '__' + model_type + '__exp' + str(experiment_number) #+ '.pickle'
print fname
# Enable to save the model and visualise GP nearest neighbour matching
save_model = False
economy_save = True
visualise_output = False
test_mode = True
# Reading face data, preparation of data and training of the model
mySAMpy.readData(root_data_dir, participant_index, pose_index)
minImages = mySAMpy.Y.shape[1]
Ntr = int(minImages*ratioData/100)
Ntest = minImages - Ntr
allPersonsY = mySAMpy.Y;
allPersonsL = mySAMpy.L;
for i in range(len(participantList)):
#print participantList[i]
mySAMpy.Y = allPersonsY[:,:,i,None]
mySAMpy.L = allPersonsL[:,:,i,None]
(Yalli, Lalli, YtestAlli, LtestAlli) = mySAMpy.prepareData(model_type, Ntr, pose_selection, randSeed=experiment_number)
if(i==0):
