Ghat.computeGFT()
S = Ghat.W / np.max(np.real(Ghat.E))
S, order = graphTools.permIdentity(S)
#S = torch.tensor(S).to(device)
################
# ARCHITECTURE #
################
#\\\\\\\
#\\\ MODEL: GIN
#\\\\\\\\\\\\
GIN = archit.SelectionGNN(hParamsGIN['F'], hParamsGIN['K'],
hParamsGIN['bias'], hParamsGIN['sigma'],
hParamsGIN['N'], hParamsGIN['rho'],
hParamsGIN['alpha'],
hParamsGIN['dimLayersMLP'], S)
GIN.to(device) # Move architecture to the selected device
# Optimizer
optimizer = optim.Adam(GIN.parameters(),
lr=learningRate,
betas=(beta1, beta2))
# Loss function
chosenLoss = lossFunction()
# Model
modelBind = model.Model(GIN, chosenLoss, optimizer,
hParamsGIN['name'], saveDir, order)
############
# TRAINING # (and VALIDATION)
#\\\ Ordering
S, order = graphTools.permIdentity(G.S / np.max(np.diag(G.E)))
# order is an np.array with the ordering of the nodes with respect
# to the original GSO (the original GSO is kept in G.S).
################
# ARCHITECTURE #
################
thisArchit = archit.SelectionGNN( # Graph filtering
hParamsSelGNNnpl['F'],
hParamsSelGNNnpl['K'],
hParamsSelGNNnpl['bias'],
# Nonlinearity
hParamsSelGNNnpl['sigma'],
# Pooling
hParamsSelGNNnpl['N'],
hParamsSelGNNnpl['rho'],
hParamsSelGNNnpl['alpha'],
# MLP
hParamsSelGNNnpl['dimLayersMLP'],
# Structure
S)
# This is necessary to move all the learnable parameters to be
# stored in the device (mostly, if it's a GPU)
thisArchit.to(device)
#############
# OPTIMIZER #
#############
if thisTrainer == 'ADAM':
################
# Override parameters with grid parameters.
hParamsPolynomial['F'] = nFeatures
hParamsPolynomial['K'] = nShifts
hParamsPolynomial['N'] = [nNodes]
if doPrint:
print('COMBINATION {0}, {1}'.format(str(hParamsPolynomial['F']), str(hParamsPolynomial['K'])))
thisArchit = archit.SelectionGNN( # Graph filtering
hParamsPolynomial['F'],
hParamsPolynomial['K'],
hParamsPolynomial['bias'],
# Nonlinearity
hParamsPolynomial['sigma'],
# Pooling
hParamsPolynomial['N'],
hParamsPolynomial['rho'],
hParamsPolynomial['alpha'],
# MLP
hParamsPolynomial['dimLayersMLP'],
# Structure
S)
# This is necessary to move all the learnable parameters to be
# stored in the device (mostly, if it's a GPU)
thisArchit.to(device)
#############
# OPTIMIZER #
#############
if thisTrainer == 'ADAM':