def test_gdumb(self):
# SIT scenario
model, optimizer, criterion, my_nc_benchmark = self.init_sit()
strategy = GDumb(
model,
optimizer,
criterion,
mem_size=200,
train_mb_size=64,
device=self.device,
eval_mb_size=50,
train_epochs=2,
)
self.run_strategy(my_nc_benchmark, strategy)
# MT scenario
strategy = GDumb(
model,
optimizer,
criterion,
mem_size=200,
train_mb_size=64,
device=self.device,
eval_mb_size=50,
train_epochs=2,
)
benchmark = self.load_benchmark(use_task_labels=True)
self.run_strategy(benchmark, strategy)
def test_gdumb(self):
model = self.get_model(fast_test=self.fast_test)
optimizer = SGD(model.parameters(), lr=1e-3)
criterion = CrossEntropyLoss()
# SIT scenario
my_nc_scenario = self.load_scenario(fast_test=self.fast_test)
strategy = GDumb(model,
optimizer,
criterion,
mem_size=200,
train_mb_size=64,
device=self.device,
eval_mb_size=50,
train_epochs=2)
self.run_strategy(my_nc_scenario, strategy)
# MT scenario
strategy = GDumb(model,
optimizer,
criterion,
mem_size=200,
train_mb_size=64,
device=self.device,
eval_mb_size=50,
train_epochs=2)
scenario = self.load_scenario(fast_test=self.fast_test,
use_task_labels=True)
self.run_strategy(scenario, strategy)
elif (args.cl_strategy == "AR1"):
cl_strategy = AR1(model,
Adam(model.parameters(), lr=0.001),
CrossEntropyLoss(),
ewc_lambda=0.5,
train_mb_size=args.batch_size,
train_epochs=args.num_epochs,
eval_mb_size=args.batch_size * 2,
evaluator=eval_plugin,
device=device)
elif (args.cl_strategy == "GDumb"):
cl_strategy = GDumb(model,
Adam(model.parameters(), lr=0.001),
CrossEntropyLoss(),
mem_size=200,
train_mb_size=args.batch_size,
train_epochs=args.num_epochs,
eval_mb_size=args.batch_size * 2,
evaluator=eval_plugin,
device=device)
else:
print("Strategy is not implemented!")
raise NotImplementedError
# TRAINING LOOP
print('Starting experiment...')
results = []
for experience in scenario.train_stream:
curr_experience = experience.current_experience
print("Start of experience: ", curr_experience)
print("Current Classes: ", experience.classes_in_this_experience)
