def test_time(tmpdir):
global DATA_PATH
cl_dataset = CIFAR100(data_path=DATA_PATH,
download=False,
train=True,
labels_type="category",
task_labels="lifelong")
# in practice the construction is part by part to reduce data load but here we do it at once
x, y, t = cl_dataset.get_data()
h5_filename = os.path.join(tmpdir, "test_time_h5.hdf5")
h5dataset = H5Dataset(x, y, t, data_path=h5_filename)
task_set = H5TaskSet(h5_filename, y=h5dataset.get_class_vector(), t=h5dataset.get_task_indexes(), trsf=None)
start = time.time()
for i in range(10000):
a = task_set[5]
end = time.time()
print(f"normal __getitem__ {end - start}")
start = time.time()
with h5py.File(h5_filename, 'r') as hf:
for i in range(10000):
x = hf['x'][5]
y = hf['y'][5]
if 't' in hf.keys():
t = hf['t'][5]
else:
t = -1
end = time.time()
print(f"open only once __getitem__ {end - start}")
def test_scenario_CIFAR100_Scenarios():
dataset = CIFAR100(DATA_PATH,
train=True,
labels_type="category",
task_labels="category")
scenario = ContinualScenario(dataset)
assert scenario.nb_classes == 20
assert scenario.nb_tasks == 20
dataset = CIFAR100(DATA_PATH,
train=True,
labels_type="category",
task_labels="class")
scenario = ContinualScenario(dataset)
assert scenario.nb_classes == 20
assert scenario.nb_tasks == 100
dataset = CIFAR100(DATA_PATH,
train=True,
labels_type="class",
task_labels="class")
scenario = ContinualScenario(dataset)
assert scenario.nb_classes == 100
assert scenario.nb_tasks == 100
dataset = CIFAR100(DATA_PATH,
train=True,
labels_type="class",
task_labels="category")
scenario = ContinualScenario(dataset)
assert scenario.nb_classes == 100
assert scenario.nb_tasks == 20
dataset = CIFAR100(DATA_PATH,
train=True,
labels_type="category",
task_labels="lifelong")
scenario = ContinualScenario(dataset)
assert scenario.nb_classes == 20
assert scenario.nb_tasks == 5
def test_on_array_dataset(tmpdir):
filename_h5 = os.path.join(tmpdir, "test_CIFAR100_h5.hdf5")
cl_dataset = CIFAR100(data_path=DATA_PATH,
download=False,
train=True,
labels_type="category",
task_labels="lifelong")
# in practice the construction is part by part to reduce data load but here we do it at once
x, y, t = cl_dataset.get_data()
h5dataset = H5Dataset(x, y, t, data_path=filename_h5)
scenario = ContinualScenario(h5dataset)
for task_set in scenario:
loader = DataLoader(task_set, batch_size=64)
for x, y, t in loader:
assert x.shape == torch.Size([64, 3, 32, 32])
break
assert scenario.nb_tasks == 5 # number of task of CIFAR100Lifelong
def test_on_array_dataset_incremental(tmpdir):
filename_h5 = os.path.join(tmpdir, "test_CIFAR100_h5.hdf5")
nb_tasks = 10
cl_dataset = CIFAR100(data_path=DATA_PATH,
download=False,
train=True)
# in practice the construction is part by part to reduce data load but here we do it at once
x, y, t = cl_dataset.get_data()
h5dataset = H5Dataset(x, y, t, data_path=filename_h5)
scenario = ClassIncremental(h5dataset, nb_tasks=nb_tasks)
for task_set in scenario:
loader = DataLoader(task_set, batch_size=64)
for x, y, t in loader:
assert x.shape == torch.Size([64, 3, 32, 32])
break
assert scenario.nb_tasks == nb_tasks # number of task of CIFAR100Lifelong
def test_h5dataset_reloading_slow(tmpdir):
filename_h5 = os.path.join(tmpdir, "test_h5.hdf5")
nb_tasks = 5
cl_dataset = CIFAR100(data_path=DATA_PATH,
download=False,
train=True,
labels_type="category",
task_labels="lifelong")
x, y, t = cl_dataset.get_data()
# create dataset
h5dataset = H5Dataset(x, y, t, data_path=filename_h5)
# destroy object
del h5dataset
# reload data set
h5dataset_reloaded = H5Dataset(x=None, y=None, t=None, data_path=filename_h5)
scenario = ContinualScenario(h5dataset_reloaded)
for task_set in scenario:
loader = DataLoader(task_set)
for _ in loader:
pass
assert scenario.nb_tasks == nb_tasks
task_order = np.arange(nb_tasks)
sub_scenario = create_subscenario(scenario, task_order[:-1])
assert sub_scenario.nb_tasks == nb_tasks-1
np.random.shuffle(task_order)
sub_scenario = create_subscenario(scenario, task_order)
assert sub_scenario.nb_tasks == nb_tasks
def test_scenario_CIFAR100_CoarseLabels():
dataset = CIFAR100(DATA_PATH, train=True, labels_type="category")
scenario = ClassIncremental(dataset, increment=10)
assert scenario.nb_classes == 20
assert scenario.nb_tasks == 2
def test_scenario_CIFAR100_ClassIncremental():
dataset = CIFAR100(DATA_PATH, train=True)
scenario = ClassIncremental(dataset, increment=50)
assert scenario.nb_classes == 100
assert scenario.nb_tasks == 2