yamle.data.text module#

class yamle.data.text.TorchtextClassificationDataModule(dataset, *args, **kwargs)[source]#

Bases: BaseDataModule

Data module for the torchvision datasets.

Parameters:

  • dataset (str) – Name of the torchvision dataset. Currently supported are wiki_text_2, wiki_text_103, imdb.

  • validation_portion (float) – Portion of the training data to use for validation.

  • seed (int) – Seed for the random number generator.

  • data_dir (str) – Path to the data directory.

mean = None#
std = None#
task = 'text_classification'#
inputs_dim = None#
inputs_dtype = torch.int64#
outputs_dim = None#
outputs_dtype = torch.int64#
prepare_data()[source]#

Download and prepare the data, the data is stored in self._train_dataset, self._validation_dataset and self._test_dataset.

Return type:

None

plot(tester, save_path, specific_name='')[source]#

Sample random text sequences from the test set and plot them.

Return type:

None

available_transforms: List[str]#
available_test_augmentations: List[str]#
test_augmentations: List[str]#
class yamle.data.text.TorchtextClassificationModelWikiText2(*args, **kwargs)[source]#

Bases: TorchtextClassificationDataModule

Data module for the WikiText2 dataset.

inputs_dim = (20,)#
outputs_dim = 28782#
targets_dim = 20#
available_transforms: List[str]#
available_test_augmentations: List[str]#
test_augmentations: List[str]#
class yamle.data.text.TorchtextClassificationModelWikiText103(*args, **kwargs)[source]#

Bases: TorchtextClassificationDataModule

Data module for the WikiText103 dataset.

inputs_dim = (20,)#
outputs_dim = 28782#
targets_dim = 20#
available_transforms: List[str]#
available_test_augmentations: List[str]#
test_augmentations: List[str]#
class yamle.data.text.TorchtextClassificationModelIMDB(*args, **kwargs)[source]#

Bases: TorchtextClassificationDataModule

Data module for the IMDB dataset.

inputs_dim = (20,)#
outputs_dim = 28782#
targets_dim = 20#
available_transforms: List[str]#
available_test_augmentations: List[str]#
test_augmentations: List[str]#
class yamle.data.text.Shakespeare(*args, **kwargs)[source]#

Bases: TorchtextClassificationDataModule

Data module for the Shakespeare dataset.

inputs_dim = (20,)#
outputs_dim = 28782#
targets_dim = 20#
available_transforms: List[str]#
available_test_augmentations: List[str]#
test_augmentations: List[str]#