File size: 7,214 Bytes
d1ceb73
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
# coding=utf-8
# Copyright 2023 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
Image/Text processor class for ALIGN
"""

from typing import List, Union


try:
    from typing import Unpack
except ImportError:
    from typing_extensions import Unpack

from ...image_utils import ImageInput
from ...processing_utils import (
    ProcessingKwargs,
    ProcessorMixin,
)
from ...tokenization_utils_base import BatchEncoding, PreTokenizedInput, TextInput


class AlignProcessorKwargs(ProcessingKwargs, total=False):
    # see processing_utils.ProcessingKwargs documentation for usage.
    _defaults = {
        "text_kwargs": {
            "padding": "max_length",
            "max_length": 64,
        },
    }


class AlignProcessor(ProcessorMixin):
    r"""
    Constructs an ALIGN processor which wraps [`EfficientNetImageProcessor`] and
    [`BertTokenizer`]/[`BertTokenizerFast`] into a single processor that interits both the image processor and
    tokenizer functionalities. See the [`~AlignProcessor.__call__`] and [`~OwlViTProcessor.decode`] for more
    information.
    The preferred way of passing kwargs is as a dictionary per modality, see usage example below.
        ```python
        from transformers import AlignProcessor
        from PIL import Image
        model_id = "kakaobrain/align-base"
        processor = AlignProcessor.from_pretrained(model_id)

        processor(
            images=your_pil_image,
            text=["What is that?"],
            images_kwargs = {"crop_size": {"height": 224, "width": 224}},
            text_kwargs = {"padding": "do_not_pad"},
            common_kwargs = {"return_tensors": "pt"},
        )
        ```

    Args:
        image_processor ([`EfficientNetImageProcessor`]):
            The image processor is a required input.
        tokenizer ([`BertTokenizer`, `BertTokenizerFast`]):
            The tokenizer is a required input.

    """

    attributes = ["image_processor", "tokenizer"]
    image_processor_class = "EfficientNetImageProcessor"
    tokenizer_class = ("BertTokenizer", "BertTokenizerFast")

    def __init__(self, image_processor, tokenizer):
        super().__init__(image_processor, tokenizer)

    def __call__(
        self,
        text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
        images: ImageInput = None,
        audio=None,
        videos=None,
        **kwargs: Unpack[AlignProcessorKwargs],
    ) -> BatchEncoding:
        """
        Main method to prepare text(s) and image(s) to be fed as input to the model. This method forwards the `text`
        arguments to BertTokenizerFast's [`~BertTokenizerFast.__call__`] if `text` is not `None` to encode
        the text. To prepare the image(s), this method forwards the `images` arguments to
        EfficientNetImageProcessor's [`~EfficientNetImageProcessor.__call__`] if `images` is not `None`. Please refer
        to the doctsring of the above two methods for more information.

        Args:
            text (`str`, `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. Both channels-first and channels-last formats are supported.
            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 must specify either text or images.")
        output_kwargs = self._merge_kwargs(
            AlignProcessorKwargs,
            tokenizer_init_kwargs=self.tokenizer.init_kwargs,
            **kwargs,
        )
        # then, we can pass correct kwargs to each processor
        if text is not None:
            encoding = self.tokenizer(text, **output_kwargs["text_kwargs"])

        if images is not None:
            image_features = self.image_processor(images, **output_kwargs["images_kwargs"])

        # BC for explicit return_tensors
        if "return_tensors" in output_kwargs["common_kwargs"]:
            return_tensors = output_kwargs["common_kwargs"].pop("return_tensors", None)

        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 BertTokenizerFast'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 BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
        the docstring of this method for more information.
        """
        return self.tokenizer.decode(*args, **kwargs)

    @property
    def model_input_names(self):
        tokenizer_input_names = self.tokenizer.model_input_names
        image_processor_input_names = self.image_processor.model_input_names
        return list(dict.fromkeys(tokenizer_input_names + image_processor_input_names))