def __init__(
self, file_service: FileService, device: str,
pretrained_representations_options: PretrainedRepresentationsOptions
):
super().__init__()
self._device = device
self.do_not_save: bool = (
not pretrained_representations_options.fine_tune_pretrained and
not pretrained_representations_options.fine_tune_after_convergence)
self._include_pretrained = pretrained_representations_options.include_pretrained_model
self._pretrained_model_size = pretrained_representations_options.pretrained_model_size
self._pretrained_weights = pretrained_representations_options.pretrained_weights
self._pretrained_max_length = pretrained_representations_options.pretrained_max_length
self._pretrained_model: PreTrainedModel = None
self._fine_tune_pretrained = pretrained_representations_options.fine_tune_pretrained
self._fine_tune_after_convergence = pretrained_representations_options.fine_tune_after_convergence
self._include_fasttext_model = pretrained_representations_options.include_fasttext_model
if self._include_pretrained and self._pretrained_model_size and self._pretrained_weights:
if pretrained_representations_options.pretrained_model == PretrainedModel.BERT:
self._pretrained_model = BertModel.from_pretrained(
pretrained_representations_options.pretrained_weights)
elif pretrained_representations_options.pretrained_model == PretrainedModel.CamemBERT:
self._pretrained_model = CamembertModel.from_pretrained(
pretrained_representations_options.pretrained_weights)
if pretrained_representations_options.fine_tune_pretrained:
self._pretrained_model.train()
else:
self._pretrained_model.eval()
if self._include_fasttext_model:
assert pretrained_representations_options.fasttext_model is not None, 'fast text model is not supplied when include-fasttext-model is set to true'
data_path = file_service.get_initial_data_path()
fasttext_path = os.path.join(
data_path, 'fasttext',
pretrained_representations_options.fasttext_model)
assert os.path.exists(
fasttext_path), f'fast text model not found in {fasttext_path}'
self._fasttext_dimension = pretrained_representations_options.fasttext_model_size
self._fasttext_model = fasttext.load_model(fasttext_path)
