numHiddentUnits_decoder=400
numberOfInducingPoints =500
learning_rate = 1e-3
numTestSamples = 100
numHiddenLayers_decoder = 1
print "Initialising"
va = VA(
numberOfInducingPoints, # Number of inducing ponts in sparse GP
batchSize, # Size of mini batch
dimX, # Dimensionality of the latent co-ordinates
dimZ, # Dimensionality of the latent variables
x_train, # [NxP] matrix of observations
kernelType=kernelType,
encoderType_qX=encoderType_qX, # 'FreeForm1', 'FreeForm2', 'MLP', 'Kernel'.
encoderType_rX=encoderType_rX, # 'MLP', 'Kernel', 'NoEncoding'.
Xu_optimise=Xu_optimise,
numHiddenUnits_encoder=numHiddenUnits_encoder,
numHiddenUnits_decoder=numHiddentUnits_decoder,
numHiddenLayers_decoder=numHiddenLayers_decoder,
continuous=True
)
va.randomise()
# va.Xz.set_value()
va.init_Xu_from_Xz()
theta = np.ones((1,dimX+1))*10
va.setKernelParameters(theta)
def checkpoint0(dataset):
if dataset == 'MNIST':
continuous=True
else:
RuntimeError('Case not implemented')
load_dataset_from_name(dataset)
model = VA(
numberOfInducingPoints, # Number of inducing ponts in sparse GP
batchSize, # Size of mini batch
dimX, # Dimensionality of the latent co-ordinates
dimZ, # Dimensionality of the latent variables
x_train, # [NxP] matrix of observations
kernelType=kernelType,
encoderType_qX=encoderType_qX, # 'FreeForm', 'MLP', 'Kernel'.
encoderType_rX=encoderType_rX, # 'FreeForm', 'MLP', 'Kernel', 'NoEncoding'.
encoderType_ru=encoderType_ru, # 'FreeForm', 'MLP', 'NoEncoding'
Xu_optimise=Xu_optimise,
numHiddenUnits_encoder=numHiddenUnits_encoder,
numHiddentUnits_decoder=numHiddentUnits_decoder,
continuous=continuous
)
model.construct_L_using_r()
model.setKernelParameters(0.01, 5*np.ones((2,)),
1e-100, 0.5,
[1e-10,1e-10], [10,10] )
model.randomise()
model.constructUpdateFunction()
model = model.randomise()
srng = utils.srng()
return model, srng
