def test_nc_sit_type(self):
mnist_train = MNIST(root=expanduser("~") + "/.avalanche/data/mnist/",
train=True,
download=True)
mnist_test = MNIST(root=expanduser("~") + "/.avalanche/data/mnist/",
train=False,
download=True)
my_nc_benchmark = nc_benchmark(mnist_train,
mnist_test,
5,
task_labels=False)
for batch_info in my_nc_benchmark.train_stream:
self.assertIsInstance(batch_info, Experience)
for batch_info in my_nc_benchmark.test_stream:
self.assertIsInstance(batch_info, Experience)
def test_nc_mt_type(self):
mnist_train = MNIST(root=expanduser("~") + "/.avalanche/data/mnist/",
train=True,
download=True)
mnist_test = MNIST(root=expanduser("~") + "/.avalanche/data/mnist/",
train=False,
download=True)
my_nc_benchmark = nc_benchmark(mnist_train,
mnist_test,
5,
task_labels=True,
class_ids_from_zero_in_each_exp=True)
for task_info in my_nc_benchmark.train_stream:
self.assertIsInstance(task_info, Experience)
for task_info in my_nc_benchmark.test_stream:
self.assertIsInstance(task_info, Experience)
def SplitTinyImageNet(
n_experiences=10,
*,
return_task_id=False,
seed=0,
fixed_class_order=None,
shuffle: bool = True,
train_transform: Optional[Any] = _default_train_transform,
eval_transform: Optional[Any] = _default_eval_transform,
dataset_root: Union[str, Path] = None):
"""
Creates a CL benchmark using the Tiny ImageNet dataset.
If the dataset is not present in the computer, this method will
automatically download and store it.
The returned benchmark will return experiences containing all patterns of a
subset of classes, which means that each class is only seen "once".
This is one of the most common scenarios in the Continual Learning
literature. Common names used in literature to describe this kind of
scenario are "Class Incremental", "New Classes", etc. By default,
an equal amount of classes will be assigned to each experience.
This generator doesn't force a choice on the availability of task labels,
a choice that is left to the user (see the `return_task_id` parameter for
more info on task labels).
The benchmark instance returned by this method will have two fields,
`train_stream` and `test_stream`, which can be iterated to obtain
training and test :class:`Experience`. Each Experience contains the
`dataset` and the associated task label.
The benchmark API is quite simple and is uniform across all benchmark
generators. It is recommended to check the tutorial of the "benchmark" API,
which contains usage examples ranging from "basic" to "advanced".
:param n_experiences: The number of experiences in the current benchmark.
:param return_task_id: if True, a progressive task id is returned for every
experience. If False, all experiences will have a task ID of 0.
:param seed: A valid int used to initialize the random number generator.
Can be None.
:param fixed_class_order: A list of class IDs used to define the class
order. If None, value of ``seed`` will be used to define the class
order. If non-None, ``seed`` parameter will be ignored.
Defaults to None.
:param shuffle: If true, the class order in the incremental experiences is
randomly shuffled. Default to false.
:param train_transform: The transformation to apply to the training data,
e.g. a random crop, a normalization or a concatenation of different
transformations (see torchvision.transform documentation for a
comprehensive list of possible transformations).
If no transformation is passed, the default train transformation
will be used.
:param eval_transform: The transformation to apply to the test data,
e.g. a random crop, a normalization or a concatenation of different
transformations (see torchvision.transform documentation for a
comprehensive list of possible transformations).
If no transformation is passed, the default test transformation
will be used.
:param dataset_root: The root path of the dataset.
Defaults to None, which means that the default location for
'tinyimagenet' will be used.
:returns: A properly initialized :class:`NCScenario` instance.
"""
train_set, test_set = _get_tiny_imagenet_dataset(dataset_root)
if return_task_id:
return nc_benchmark(
train_dataset=train_set,
test_dataset=test_set,
n_experiences=n_experiences,
task_labels=True,
seed=seed,
fixed_class_order=fixed_class_order,
shuffle=shuffle,
class_ids_from_zero_in_each_exp=True,
train_transform=train_transform,
eval_transform=eval_transform,
)
else:
return nc_benchmark(
train_dataset=train_set,
test_dataset=test_set,
n_experiences=n_experiences,
task_labels=False,
seed=seed,
fixed_class_order=fixed_class_order,
shuffle=shuffle,
train_transform=train_transform,
eval_transform=eval_transform,
)
def run_experiment(config):
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
torch.manual_seed(config.seed)
torch.cuda.manual_seed(config.seed)
np.random.seed(config.seed)
random.seed(config.seed)
torch.backends.cudnn.enabled = False
torch.backends.cudnn.deterministic = True
per_pixel_mean = get_dataset_per_pixel_mean(
CIFAR100(
expanduser("~") + "/.avalanche/data/cifar100/",
train=True,
download=True,
transform=transforms.Compose([transforms.ToTensor()]),
)
)
transforms_group = dict(
eval=(
transforms.Compose(
[
transforms.ToTensor(),
lambda img_pattern: img_pattern - per_pixel_mean,
]
),
None,
),
train=(
transforms.Compose(
[
transforms.ToTensor(),
lambda img_pattern: img_pattern - per_pixel_mean,
icarl_cifar100_augment_data,
]
),
None,
),
)
train_set = CIFAR100(
expanduser("~") + "/.avalanche/data/cifar100/",
train=True,
download=True,
)
test_set = CIFAR100(
expanduser("~") + "/.avalanche/data/cifar100/",
train=False,
download=True,
)
train_set = AvalancheDataset(
train_set,
transform_groups=transforms_group,
initial_transform_group="train",
)
test_set = AvalancheDataset(
test_set,
transform_groups=transforms_group,
initial_transform_group="eval",
)
scenario = nc_benchmark(
train_dataset=train_set,
test_dataset=test_set,
n_experiences=config.nb_exp,
task_labels=False,
seed=config.seed,
shuffle=False,
fixed_class_order=config.fixed_class_order,
)
evaluator = EvaluationPlugin(
EpochAccuracy(),
ExperienceAccuracy(),
StreamAccuracy(),
loggers=[InteractiveLogger()],
)
model: IcarlNet = make_icarl_net(num_classes=100)
model.apply(initialize_icarl_net)
optim = SGD(
model.parameters(),
lr=config.lr_base,
weight_decay=config.wght_decay,
momentum=0.9,
)
sched = LRSchedulerPlugin(
MultiStepLR(optim, config.lr_milestones, gamma=1.0 / config.lr_factor)
)
strategy = ICaRL(
model.feature_extractor,
model.classifier,
optim,
config.memory_size,
buffer_transform=transforms.Compose([icarl_cifar100_augment_data]),
fixed_memory=True,
train_mb_size=config.batch_size,
train_epochs=config.epochs,
eval_mb_size=config.batch_size,
plugins=[sched],
device=device,
evaluator=evaluator,
)
for i, exp in enumerate(scenario.train_stream):
eval_exps = [e for e in scenario.test_stream][: i + 1]
strategy.train(exp, num_workers=4)
strategy.eval(eval_exps, num_workers=4)