File size: 5,277 Bytes
b09211c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# coding=utf-8
# Copyright 2023 The CheXagent Authors and 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.

from typing import List, Optional, Union

import torch
from transformers.image_utils import ImageInput
from transformers.processing_utils import ProcessorMixin
from transformers.tokenization_utils_base import BatchEncoding, PaddingStrategy, PreTokenizedInput, TextInput
from transformers.tokenization_utils_base import TruncationStrategy
from transformers.utils import TensorType


class CheXagentProcessor(ProcessorMixin):
    attributes = ["image_processor", "tokenizer"]
    image_processor_class = "BlipImageProcessor"
    tokenizer_class = "AutoTokenizer"

    def __init__(self, image_processor, tokenizer):
        tokenizer.return_token_type_ids = False
        super().__init__(image_processor, tokenizer)
        self.current_processor = self.image_processor

    def __call__(
            self,
            images: ImageInput = None,
            text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
            add_special_tokens: bool = True,
            padding: Union[bool, str, PaddingStrategy] = False,
            truncation: Union[bool, str, TruncationStrategy] = None,
            max_length: Optional[int] = None,
            stride: int = 0,
            pad_to_multiple_of: Optional[int] = None,
            return_attention_mask: Optional[bool] = None,
            return_overflowing_tokens: bool = False,
            return_special_tokens_mask: bool = False,
            return_offsets_mapping: bool = False,
            return_token_type_ids: bool = False,
            return_length: bool = False,
            verbose: bool = True,
            return_tensors: Optional[Union[str, TensorType]] = None,
            **kwargs,
    ) -> BatchEncoding:
        if images is None and text is None:
            raise ValueError("You have to specify either images or text.")

        # Get only text
        if images is None:
            self.current_processor = self.tokenizer
            text_encoding = self.tokenizer(
                text=text,
                add_special_tokens=add_special_tokens,
                padding=padding,
                truncation=truncation,
                max_length=max_length,
                stride=stride,
                pad_to_multiple_of=pad_to_multiple_of,
                return_attention_mask=return_attention_mask,
                return_overflowing_tokens=return_overflowing_tokens,
                return_special_tokens_mask=return_special_tokens_mask,
                return_offsets_mapping=return_offsets_mapping,
                return_token_type_ids=return_token_type_ids,
                return_length=return_length,
                verbose=verbose,
                return_tensors=return_tensors,
                **kwargs,
            )
            return text_encoding

        # add pixel_values
        if images is not None:
            encoding_image_processor = self.image_processor(images, return_tensors=return_tensors)
            encoding_image_processor["pixel_values"] = torch.stack(
                [torch.tensor(pixel_values) for pixel_values in encoding_image_processor["pixel_values"]]
            ).unsqueeze(0)

        if text is not None:
            text_encoding = self.tokenizer(
                text=text,
                add_special_tokens=add_special_tokens,
                padding=padding,
                truncation=truncation,
                max_length=max_length,
                stride=stride,
                pad_to_multiple_of=pad_to_multiple_of,
                return_attention_mask=return_attention_mask,
                return_overflowing_tokens=return_overflowing_tokens,
                return_special_tokens_mask=return_special_tokens_mask,
                return_offsets_mapping=return_offsets_mapping,
                return_token_type_ids=return_token_type_ids,
                return_length=return_length,
                verbose=verbose,
                return_tensors=return_tensors,
                **kwargs,
            )
        else:
            text_encoding = None

        if text_encoding is not None:
            encoding_image_processor.update(text_encoding)

        return encoding_image_processor

    def batch_decode(self, *args, **kwargs):
        return self.tokenizer.batch_decode(*args, **kwargs)

    def decode(self, *args, **kwargs):
        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))