def test_gem(self):
model = self.get_model(fast_test=self.fast_test)
optimizer = SGD(model.parameters(), lr=1e-1)
criterion = CrossEntropyLoss()
# SIT scenario
my_nc_scenario = self.load_scenario(fast_test=self.fast_test)
strategy = GEM(model,
optimizer,
criterion,
patterns_per_exp=256,
train_mb_size=10,
eval_mb_size=50,
train_epochs=2)
self.run_strategy(my_nc_scenario, strategy)
# MT scenario
strategy = GEM(model,
optimizer,
criterion,
patterns_per_exp=256,
train_mb_size=10,
eval_mb_size=50,
train_epochs=2)
self.run_strategy(my_nc_scenario, strategy)
scenario = self.load_scenario(fast_test=self.fast_test,
use_task_labels=True)
self.run_strategy(scenario, strategy)
def test_gem(self):
# SIT scenario
model, optimizer, criterion, my_nc_benchmark = self.init_sit()
strategy = GEM(
model,
optimizer,
criterion,
patterns_per_exp=256,
train_mb_size=10,
eval_mb_size=50,
train_epochs=2,
)
self.run_strategy(my_nc_benchmark, strategy)
# MT scenario
strategy = GEM(
model,
optimizer,
criterion,
patterns_per_exp=256,
train_mb_size=10,
eval_mb_size=50,
train_epochs=2,
)
self.run_strategy(my_nc_benchmark, strategy)
benchmark = self.load_benchmark(use_task_labels=True)
self.run_strategy(benchmark, strategy)
def main(args):
model = SimpleMLP(hidden_size=args.hs)
optimizer = torch.optim.SGD(model.parameters(), lr=args.lr)
criterion = torch.nn.CrossEntropyLoss()
# check if selected GPU is available or use CPU
assert args.cuda == -1 or args.cuda >= 0, "cuda must be -1 or >= 0."
device = torch.device(f"cuda:{args.cuda}"
if torch.cuda.is_available() and
args.cuda >= 0 else "cpu")
print(f'Using device: {device}')
# create scenario
if args.scenario == 'pmnist':
scenario = PermutedMNIST(n_experiences=args.permutations)
elif args.scenario == 'smnist':
scenario = SplitMNIST(n_experiences=5, return_task_id=False)
else:
raise ValueError("Wrong scenario name. Allowed pmnist, smnist.")
# choose some metrics and evaluation method
interactive_logger = InteractiveLogger()
eval_plugin = EvaluationPlugin(
accuracy_metrics(minibatch=True, epoch=True, experience=True, stream=True),
loss_metrics(minibatch=True, epoch=True, experience=True, stream=True),
forgetting_metrics(experience=True),
loggers=[interactive_logger])
# create strategy
if args.strategy == 'gem':
strategy = GEM(model, optimizer, criterion, args.patterns_per_exp,
args.memory_strength, train_epochs=args.epochs,
device=device, train_mb_size=10, evaluator=eval_plugin)
elif args.strategy == 'agem':
strategy = AGEM(model, optimizer, criterion, args.patterns_per_exp,
args.sample_size, train_epochs=args.epochs, device=device,
train_mb_size=10, evaluator=eval_plugin)
else:
raise ValueError("Wrong strategy name. Allowed gem, agem.")
# train on the selected scenario with the chosen strategy
print('Starting experiment...')
results = []
for experience in scenario.train_stream:
print("Start training on experience ", experience.current_experience)
strategy.train(experience)
print("End training on experience ", experience.current_experience)
print('Computing accuracy on the test set')
results.append(strategy.eval(scenario.test_stream[:]))
accuracy_metrics(minibatch=True, epoch=True, experience=True, stream=True),
loss_metrics(minibatch=True, epoch=True, experience=True, stream=True),
timing_metrics(epoch=True, epoch_running=True),
ExperienceForgetting(),
cpu_usage_metrics(experience=True),
StreamConfusionMatrix(num_classes=2, save_image=False),
disk_usage_metrics(minibatch=True, epoch=True, experience=True, stream=True),
loggers=[interactive_logger, text_logger, tb_logger],
)
cl_strategy = GEM(
model,
optimizer=Adam(model.parameters()),
patterns_per_exp=1470,
criterion=CrossEntropyLoss(),
train_mb_size=128,
train_epochs=50,
eval_mb_size=128,
evaluator=eval_plugin,
device=device,
)
# TRAINING LOOP
print("Starting experiment...")
os.makedirs(os.path.join("weights", f"SimpleMLP"), exist_ok=True)
results = []
i = 1
for task_number, experience in enumerate(generic_scenario.train_stream):
print("Start of experience: ", experience.current_experience)
cl_strategy = LwF(model,
Adam(model.parameters(), lr=0.001),
CrossEntropyLoss(),
alpha=0.5,
temperature=2.0,
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 == "GEM"):
cl_strategy = GEM(model,
Adam(model.parameters(), lr=0.001),
CrossEntropyLoss(),
patterns_per_exp=150,
memory_strength=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 == "EWC"):
cl_strategy = EWC(model,
Adam(model.parameters(), lr=0.001),
CrossEntropyLoss(),
ewc_lambda=0.5,
mode="separate",
train_mb_size=args.batch_size,
train_epochs=args.num_epochs,
eval_mb_size=args.batch_size * 2,
evaluator=eval_plugin,
device=device)