def train_model(model, train_loader, test_loader, val_loader, obj=None, LMIs=None, regularizers=None, log_dir=default_log_dir, options=None):
print("Beginnning training at {}".format(time.ctime()))
if obj is None:
obj = torch.nn.MSELoss()
if options is None:
options = nlsdp.make_stochastic_nlsdp_options()
problem = nlsdp.stochastic_nlsdp(model=model, criterion=obj, train_loader=train_loader, val_loader=val_loader, **options)
if LMIs is not None:
for lmi in LMIs:
problem.addSDPconstraint(lmi)
if regularizers is not None:
for reg in regularizers:
problem.add_regularizer(reg)
log = problem.solve()
print("Training Complete")
return log
val_bs=10,
ar=False,
val_set=val_set)
dataset_options["subject"] = subject
train_loader, val_loader, test_loader, scaling_factors = load_data.load_dataset(
dataset="gait_prediction_stairs",
dataset_options=dataset_options)
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_bs=10,
ar=ar,
val_set=val_set)
dataset_options["subject"] = subject
train_loader, val_loader, test_loader = load_data.load_dataset(
dataset="gait_prediction_stairs",
dataset_options=dataset_options)
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=5.0E-4,
mu0=500,
lr_decay=0.987,
patience=20)
# Train Unconstrained model - still project onto stable models for stable initial point
name = "uncon_sub{:d}_val{:d}".format(subject, val_set)
model = dnb.dnbRNN(nu, width, ny, layers, nBatches=9, init_var=1.3)
log, best_model = train.train_model(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)
# Load the data set
dataset_options = load_data.make_default_options(train_bs=40,
train_sl=200,
val_set=val_set,
test_sl=2000)
dataset_options["gain"] = 1.4
train_loader, val_loader, test_loader = load_data.load_dataset(
dataset="chen", dataset_options=dataset_options)
nu = train_loader.nu
ny = train_loader.ny
# Options for the solver
solver_options = nlsdp.make_stochastic_nlsdp_options(
max_epochs=max_epochs,
lr=0.1E-4,
mu0=2000,
lr_decay=0.96,
patience=10)
# Train Contracting implicit model ------------------------------------------------------------------------
name = "contracting_sub{:d}_val{:d}".format(subject, val_set)
model = diRNN.diRNN(nu,
width,
ny,
layers,
nBatches=dataset_options["train_batch_size"] -
1)
model.init_l2(mu=mu, epsilon=eps, init_var=1.2)
log, best_model = train.train_model(model,
train_loader=train_loader,