nu = train_loader.nu
ny = train_loader.ny
# Options for the solver
# solver_options = nlsdp.make_stochastic_nlsdp_options(max_epochs=max_epochs, lr=5.0E-4, mu0=100, lr_decay=0.98)
solver_options = nlsdp.make_stochastic_nlsdp_options(
max_epochs=max_epochs,
lr=lr,
mu0=10,
lr_decay=lr_decay,
patience=patience)
# Train an LSTM network
name = "RNN_sub{:d}_val{:d}".format(subject, val_set)
model = rnn.rnn(nu, lstm_width, ny, layers=layers)
log, best_model = train.train_model_ipm(model,
train_loader=train_loader,
val_loader=val_loader,
test_loader=test_loader,
options=solver_options)
test_and_save_model(name,
best_model,
train_loader,
val_loader,
test_loader,
log,
params=scaling_factors)
# # for gamma in [0.5, 1, 1.5, 2.5, 5]:
def generate_model(nu, ny, batches, args, loader=None, solver="SCS"):
r'Function to easily re-generate models for training on different data sets.'
print('Creating model', args.model, ' width = ', args.width)
if args.model == "cirnn":
model = ciRNN.ciRNN(nu, args.width, ny, args.depth, nBatches=batches)
model.init_l2(0.0, 1E-3)
constraints = {
"lmi": model.contraction_lmi(0, 1E-5),
"inequality": None
}
elif args.model == "RobustRnn":
model = RobustRnn.RobustRnn(nu,
args.width,
ny,
args.res_size,
nBatches=batches,
method=args.multiplier,
supply_rate=args.supply_rate)
if args.supply_rate == "dl2_gain":
print('\t supply rate: dl2 gamma = ', args.gamma)
if args.init_type == 'n4sid':
model.init_lipschitz_ss(gamma=args.gamma,
loader=loader,
solver=solver)
else:
model.initialize_lipschitz_LMI(gamma=args.gamma,
eps=1E-3,
init_var=args.init_var)
constraints = {
"lmi": model.lipschitz_LMI(gamma=args.gamma, eps=1E-5),
"inequality": [model.multiplier_barrier]
}
elif args.supply_rate == "stable":
print('\t supply rate: stable')
if args.init_type == 'n4sid':
model.init_stable_ss(loader)
else:
model.initialize_stable_LMI(eps=1E-3,
init_var=args.init_var,
obj=args.init_type)
constraints = {
"lmi": model.stable_LMI(eps=1E-5),
"inequality": [model.multiplier_barrier]
}
elif args.model == "rnn":
model = rnn.rnn(nu, args.width, ny, nBatches=batches)
constraints = {"lmi": None, "inequality": None}
elif args.model == "lstm": # only constraint is invertible E
model = lstm.lstm(nu, args.width, ny, nBatches=batches)
constraints = {"lmi": None, "inequality": None}
elif args.model == 'dnb':
model = dnb.dnbRNN(nu, args.width, ny, nBatches=batches)
constraints = {
"lmi": model.norm_ball_lmi(eps=0.001),
"inequality": None
}
return model, constraints
model.load_state_dict(torch.load(path + name + ".params"))
res = vary_amplitude(model)
io.savemat('./results/msd/generalization/amp_' + name + '.mat', res)
# # lstm
print("Running tests on LSTM")
name = 'lstm_w10_gamma0.0_n4'
model = lstm.lstm(nu, width, ny, layers=1, nBatches=batches)
model.load_state_dict(torch.load(path + name + ".params"))
res = vary_amplitude(model)
io.savemat('./results/msd/generalization/amp_' + name + '.mat', res)
# rnn
print("Running tests on RNN")
name = 'rnn_w10_gamma0.0_n4'
model = rnn.rnn(nu, width, ny, 1, nBatches=batches)
model.load_state_dict(torch.load(path + name + ".params"))
res = vary_amplitude(model)
io.savemat('./results/msd/generalization/amp_' + name + '.mat', res)
# cirnn
print("Running tests on cirnn")
name = 'cirnn_w10_gamma0.0_n4'
model = ciRNN.ciRNN(nu, width, ny, 1, nBatches=100)
model.load_state_dict(torch.load(path + name + ".params"))
res = vary_amplitude(model)
io.savemat('./results/msd/generalization/amp_' + name + '.mat', res)
# srnn
print("Running tests on srnn")
name = 'dnb_w10_gamma0.0_n4'
data = new_data.copy()
noise = np.random.rand(data.shape[0], data.shape[1], data.shape[2])
noise /= 10 # small amount of noise
post_ground_truth = np.append(ground_truth[:, 1:, :],
ground_truth[:, 0:1, :],
axis=1)
########## LOAD MODEL ##########
learning_rate = 1e-4
model = rnn(embedding_size=256,
recurrent_dropout=0,
single_timestep_elements=data[0].shape[-1],
single_timestep_gt=post_ground_truth[0].shape[-1],
learning_rate=learning_rate,
loss='categorical_crossentropy')
print(model.summary())
########## CALLBACKS ##########
callbacks = []
tqdm_callback = TQDMCallback(leave_inner=False,
show_inner=False,
outer_description="Training")
callbacks.append(tqdm_callback)
########## TRAIN ##########