|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
""" |
|
Processor class for VELD |
|
""" |
|
|
|
from transformers.processing_utils import ProcessorMixin |
|
from transformers.tokenization_utils_base import BatchEncoding |
|
|
|
|
|
class VELDProcessor(ProcessorMixin): |
|
r""" |
|
Constructs a VELD processor which wraps a vision feature extractor and a tokenizer into a single |
|
processor. |
|
[`VELDProcessor`] offers all the functionalities of [`AutoImageProcessor`] and |
|
[`AutoTokenizer`]. See the [`~VELDProcessor.__call__`] and |
|
[`~VELDProcessor.decode`] for more information. |
|
Args: |
|
feature_extractor ([`AutoImageProcessor`]): |
|
The feature extractor is a required input. |
|
tokenizer ([`PreTrainedTokenizer`]): |
|
The tokenizer is a required input. |
|
""" |
|
feature_extractor_class = "AutoImageProcessor" |
|
tokenizer_class = "AutoTokenizer" |
|
|
|
def __init__(self, feature_extractor, tokenizer): |
|
super().__init__(feature_extractor, tokenizer) |
|
self.current_processor = self.feature_extractor |
|
|
|
def __call__(self, text=None, images=None, return_tensors=None, **kwargs): |
|
""" |
|
Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` |
|
and `kwargs` arguments to VisionTextDualEncoderTokenizer's [`~PreTrainedTokenizer.__call__`] if `text` is not |
|
`None` to encode the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to |
|
AutoImageProcessor's [`~AutoImageProcessor.__call__`] if `images` is not `None`. Please refer to the |
|
doctsring of the above two methods for more information. |
|
Args: |
|
text (`str`, `List[str]`, `List[List[str]]`): |
|
The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings |
|
(pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set |
|
`is_split_into_words=True` (to lift the ambiguity with a batch of sequences). |
|
images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`): |
|
The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch |
|
tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a |
|
number of channels, H and W are image height and width. |
|
return_tensors (`str` or [`~utils.TensorType`], *optional*): |
|
If set, will return tensors of a particular framework. Acceptable values are: |
|
- `'tf'`: Return TensorFlow `tf.constant` objects. |
|
- `'pt'`: Return PyTorch `torch.Tensor` objects. |
|
- `'np'`: Return NumPy `np.ndarray` objects. |
|
- `'jax'`: Return JAX `jnp.ndarray` objects. |
|
Returns: |
|
[`BatchEncoding`]: A [`BatchEncoding`] with the following fields: |
|
- **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. |
|
- **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when |
|
`return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not |
|
`None`). |
|
- **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. |
|
""" |
|
|
|
if text is None and images is None: |
|
raise ValueError("You have to specify either text or images. Both cannot be none.") |
|
|
|
if text is not None: |
|
encoding = self.tokenizer(text, return_tensors=return_tensors, **kwargs) |
|
|
|
if images is not None: |
|
image_features = self.feature_extractor(images, return_tensors=return_tensors, **kwargs) |
|
|
|
if text is not None and images is not None: |
|
encoding["pixel_values"] = image_features.pixel_values |
|
return encoding |
|
elif text is not None: |
|
return encoding |
|
else: |
|
return BatchEncoding(data=dict(**image_features), tensor_type=return_tensors) |
|
|
|
def batch_decode(self, *args, **kwargs): |
|
""" |
|
This method forwards all its arguments to VELDProcessor's |
|
[`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. |
|
""" |
|
return self.tokenizer.batch_decode(*args, **kwargs) |
|
|
|
def decode(self, *args, **kwargs): |
|
""" |
|
This method forwards all its arguments to VELDProcessor's [`~PreTrainedTokenizer.decode`]. |
|
Please refer to the docstring of this method for more information. |
|
""" |
|
return self.tokenizer.decode(*args, **kwargs) |
