def train_val_dataset_for_bias(self, train_dataset):
exemplars_indexes = np.hstack(self.exemplar_sets)
exemplars_labels = np.hstack(
[[label] * len(self.exemplar_sets[label])
for label in range(len(self.exemplar_sets))])
exemplar_train_ind, exemplar_val_ind = train_test_split(
exemplars_indexes, stratify=exemplars_labels, test_size=500)
train_dataset_ind = train_dataset.indices
_, train_dataset_labels = self.dataset.get_items_of(train_dataset_ind)
train_dataset_ind, val_dataset_ind = train_test_split(
train_dataset_ind, stratify=train_dataset_labels, test_size=500)
exemplar_train_imgs, exemplar_train_labels = self.dataset.get_items_of(
exemplar_train_ind)
exemplar_val_imgs, exemplar_val_labels = self.dataset.get_items_of(
exemplar_val_ind)
train_dataset = Subset(self.dataset, train_dataset_ind)
val_dataset = Subset(self.dataset, val_dataset_ind)
exemplar_train_set = ExemplarSet(exemplar_train_imgs,
exemplar_train_labels,
utils.get_train_eval_transforms()[0])
exemplar_val_set = ExemplarSet(exemplar_val_imgs, exemplar_val_labels,
utils.get_train_eval_transforms()[0])
train_dataset = utils.create_augmented_dataset(train_dataset,
exemplar_train_set)
val_dataset = utils.create_augmented_dataset(val_dataset,
exemplar_val_set)
return train_dataset, val_dataset
def combine_trainset_exemplars(self, train_dataset: Cifar100):
exemplar_indexes = np.hstack(self.exemplar_sets)
images, labels = self.dataset.get_items_of(exemplar_indexes)
exemplar_dataset = ExemplarSet(images, labels, utils.get_train_eval_transforms()[0])
return utils.create_augmented_dataset(train_dataset, exemplar_dataset)