def test_core50_ni_benchmark(self):
if "FAST_TEST" in os.environ:
pass
else:
benchmark = CORe50(scenario="ni")
for experience in benchmark.train_stream:
pass
def test_core50_ni_scenario(self):
if "FAST_TEST" in os.environ:
pass
else:
scenario = CORe50(scenario="ni")
for experience in scenario.train_stream:
pass
def test_core50_ni_scenario(self):
if "FAST_TEST" in os.environ:
pass
else:
scenario = CORe50(scenario="ni")
for task_info in scenario:
pass
def test_core50_nc_scenario(self):
benchmark_instance = CORe50(scenario='nc')
self.assertEqual(1, len(benchmark_instance.test_stream))
classes_in_test = benchmark_instance.\
classes_in_experience['test'][0]
self.assertSetEqual(
set(range(50)),
set(classes_in_test))
def test_core50_nc_benchmark(self):
if "FAST_TEST" in os.environ:
pass
else:
benchmark_instance = CORe50(scenario="nc")
self.assertEqual(1, len(benchmark_instance.test_stream))
classes_in_test = benchmark_instance.classes_in_experience["test"][
0]
self.assertSetEqual(set(range(50)), set(classes_in_test))
def main(args):
# Device config
device = torch.device(f"cuda:{args.cuda}"
if torch.cuda.is_available() and
args.cuda >= 0 else "cpu")
print('device ', device)
# ---------
# --- TRANSFORMATIONS
_mu = [0.485, 0.456, 0.406] # imagenet normalization
_std = [0.229, 0.224, 0.225]
transform = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(mean=_mu,
std=_std)
])
# ---------
# --- SCENARIO CREATION
scenario = CORe50(scenario=args.scenario, train_transform=transform,
eval_transform=transform)
# ---------
eval_plugin = EvaluationPlugin(
loss_metrics(epoch=True, experience=True, stream=True),
accuracy_metrics(epoch=True, experience=True, stream=True),
forgetting_metrics(experience=True, stream=True),
loggers=[InteractiveLogger()]
)
criterion = torch.nn.CrossEntropyLoss()
model = SLDAResNetModel(device=device, arch='resnet18',
imagenet_pretrained=args.imagenet_pretrained)
# CREATE THE STRATEGY INSTANCE
cl_strategy = StreamingLDA(model, criterion,
args.feature_size, args.n_classes,
eval_mb_size=args.batch_size,
train_mb_size=args.batch_size,
train_epochs=1,
shrinkage_param=args.shrinkage,
streaming_update_sigma=args.plastic_cov,
device=device, evaluator=eval_plugin)
warnings.warn(
"The Deep SLDA example is not perfectly aligned with "
"the paper implementation since it does not use a base "
"initialization phase and instead starts streming from "
"pre-trained weights.")
# TRAINING LOOP
print('Starting experiment...')
for i, exp in enumerate(scenario.train_stream):
# fit SLDA model to batch (one sample at a time)
cl_strategy.train(exp)
# evaluate model on test data
cl_strategy.eval(scenario.test_stream)
def test_core50_ni_benchmark(self):
benchmark = CORe50(scenario="ni")
for experience in benchmark.train_stream:
pass