master
/ transformers / pipelines / feature_extraction.py

feature_extraction.py @3c11360 

69624d8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
from typing import Dict

from .base import GenericTensor, Pipeline


# Can't use @add_end_docstrings(PIPELINE_INIT_ARGS) here because this one does not accept `binary_output`
class FeatureExtractionPipeline(Pipeline):
    """
    Feature extraction pipeline using no model head. This pipeline extracts the hidden states from the base
    transformer, which can be used as features in downstream tasks.

    This feature extraction pipeline can currently be loaded from [`pipeline`] using the task
    identifier: `"feature-extraction"`.

    All models may be used for this pipeline. See a list of all models, including community-contributed models on
    [huggingface.co/models](https://huggingface.co/models).

    Arguments:
        model ([`PreTrainedModel`] or [`TFPreTrainedModel`]):
            The model that will be used by the pipeline to make predictions. This needs to be a model inheriting from
            [`PreTrainedModel`] for PyTorch and [`TFPreTrainedModel`] for
            TensorFlow.
        tokenizer ([`PreTrainedTokenizer`]):
            The tokenizer that will be used by the pipeline to encode data for the model. This object inherits from
            [`PreTrainedTokenizer`].
        modelcard (`str` or [`ModelCard`], *optional*):
            Model card attributed to the model for this pipeline.
        framework (`str`, *optional*):
            The framework to use, either `"pt"` for PyTorch or `"tf"` for TensorFlow. The specified framework
            must be installed.

            If no framework is specified, will default to the one currently installed. If no framework is specified and
            both frameworks are installed, will default to the framework of the `model`, or to PyTorch if no model
            is provided.
        task (`str`, defaults to `""`):
            A task-identifier for the pipeline.
        args_parser ([`~pipelines.ArgumentHandler`], *optional*):
            Reference to the object in charge of parsing supplied pipeline parameters.
        device (`int`, *optional*, defaults to -1):
            Device ordinal for CPU/GPU supports. Setting this to -1 will leverage CPU, a positive will run the model on
            the associated CUDA device id.
    """

    def _sanitize_parameters(self, truncation=None, **kwargs):
        preprocess_params = {}
        if truncation is not None:
            preprocess_params["truncation"] = truncation
        return preprocess_params, {}, {}

    def preprocess(self, inputs, truncation=None) -> Dict[str, GenericTensor]:
        return_tensors = self.framework
        if truncation is None:
            kwargs = {}
        else:
            kwargs = {"truncation": truncation}
        model_inputs = self.tokenizer(inputs, return_tensors=return_tensors, **kwargs)
        return model_inputs

    def _forward(self, model_inputs):
        model_outputs = self.model(**model_inputs)
        return model_outputs

    def postprocess(self, model_outputs):
        # [0] is the first available tensor, logits or last_hidden_state.
        if self.framework == "pt":
            return model_outputs[0].tolist()
        elif self.framework == "tf":
            return model_outputs[0].numpy().tolist()

    def __call__(self, *args, **kwargs):
        """
        Extract the features of the input(s).

        Args:
            args (`str` or `List[str]`): One or several texts (or one list of texts) to get the features of.

        Return:
            A nested list of `float`: The features computed by the model.
        """
        return super().__call__(*args, **kwargs)