def sample(self, B, N, K, **kwargs):
dataset = self.get_MiniImagenet(train=False)
loader = get_random_data_loader(
self.get_MiniImagenet(False),
B, N, K, 1, TEST_NUM_PER_CLASS, **kwargs)
# transform=self.transform, **kwargs)
return next(iter(loader))
def get_train_loader(self):
return get_random_data_loader(self.get_ImageNet32(),
self.B,
self.N,
self.K,
self.num_steps,
TRAIN_NUM_PER_CLASS,
classes=range(TRAIN_NUM_CLASSES))
def get_train_loader(self):
classes = range(TRAIN_NUM_CLASSES) if self.novel else None
return get_random_data_loader(self.get_EMNIST(),
self.B,
self.N,
self.K,
self.num_steps,
TRAIN_NUM_PER_CLASS,
classes=classes)
def get_train_loader(self):
if self.phase == 1:
classes = range(TRAIN_NUM_CLASSES // 2)
else:
classes = range(TRAIN_NUM_CLASSES)
return get_random_data_loader(self.get_EMNIST(),
self.B,
self.N,
self.K,
self.num_steps,
TRAIN_NUM_PER_CLASS,
classes=classes)
def sample(self, B, N, K, **kwargs):
classes = range(TRAIN_NUM_CLASSES,
TRAIN_NUM_CLASSES + TEST_NUM_CLASSES_NOVEL) \
if self.novel else None
loader = get_random_data_loader(self.get_EMNIST(False),
B,
N,
K,
1,
TEST_NUM_PER_CLASS,
classes=classes,
**kwargs)
return next(iter(loader))
def get_train_loader(self):
dataset = EMNIST(os.path.join(datasets_path, 'emnist'),
split='balanced',
download=True,
train=True)
def transform(x):
return torch.bernoulli(x.unsqueeze(-3).float().div(255))
classes = torch.arange(20) if self.novel else None
return get_random_data_loader(dataset,
self.B,
self.N,
self.K,
self.num_steps,
TRAIN_NUM_PER_CLASS,
transform=transform,
classes=classes)
def sample(self, B, N, K, **kwargs):
dataset = EMNIST(os.path.join(datasets_path, 'emnist'),
split='balanced',
download=True,
train=False)
def transform(x):
return torch.bernoulli(x.unsqueeze(-3).float().div(255))
loader = get_random_data_loader(
dataset,
B,
N,
K,
1,
TEST_NUM_PER_CLASS,
transform=transform,
classes=(torch.arange(20, 47) if self.novel else None),
transform=transform,
**kwargs)
return next(iter(loader))
def get_train_loader(self):
return get_random_data_loader(self.get_Kkanji(), self.B, self.N,
self.K, self.num_steps,
TRAIN_NUM_PER_CLASS)
def sample(self, B, N, K, **kwargs):
loader = get_random_data_loader(self.get_Kkanji(False), B, N, K, 1,
TEST_NUM_PER_CLASS, **kwargs)
return next(iter(loader))