PyTorch
English
Tevatron
phi3_v
vidore
custom_code
MrLight commited on
Commit
10329fa
1 Parent(s): 9ecf6de

Create processing_phi3_v.py

Browse files
Files changed (1) hide show
  1. processing_phi3_v.py +233 -0
processing_phi3_v.py ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # coding=utf-8
2
+ # Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
3
+ #
4
+ # Licensed under the Apache License, Version 2.0 (the "License");
5
+ # you may not use this file except in compliance with the License.
6
+ # You may obtain a copy of the License at
7
+ #
8
+ # http://www.apache.org/licenses/LICENSE-2.0
9
+ #
10
+ # Unless required by applicable law or agreed to in writing, software
11
+ # distributed under the License is distributed on an "AS IS" BASIS,
12
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
+ # See the License for the specific language governing permissions and
14
+ # limitations under the License.
15
+
16
+ """
17
+ Processor class for Phi3-V.
18
+ """
19
+ import re
20
+ from typing import List, Optional, Union
21
+
22
+ import torch
23
+
24
+ import transformers
25
+ from transformers.feature_extraction_utils import BatchFeature
26
+ from transformers.image_utils import ImageInput
27
+ from transformers.processing_utils import ProcessorMixin
28
+ from transformers.tokenization_utils_base import PaddingStrategy, TextInput, TruncationStrategy
29
+ from transformers.utils import TensorType
30
+ from .image_processing_phi3_v import Phi3VImageProcessor
31
+ transformers.Phi3VImageProcessor = Phi3VImageProcessor
32
+
33
+ class Phi3VProcessor(ProcessorMixin):
34
+ r"""
35
+ Constructs a Phi3-V processor which wraps a Phi3-V image processor and a LLaMa tokenizer into a single processor.
36
+
37
+ [`Phi3VProcessor`] offers all the functionalities of [`Phi3VImageProcessor`] and [`LlamaTokenizerFast`]. See the
38
+ [`~Phi3VProcessor.__call__`] and [`~Phi3VProcessor.decode`] for more information.
39
+
40
+ Args:
41
+ image_processor ([`Phi3VImageProcessor`], *optional*):
42
+ The image processor is a required input.
43
+ tokenizer ([`LlamaTokenizerFast`], *optional*):
44
+ The tokenizer is a required input.
45
+ """
46
+
47
+ attributes = ["image_processor", "tokenizer"]
48
+ image_processor_class = "Phi3VImageProcessor"
49
+ tokenizer_class = ("LlamaTokenizer", "LlamaTokenizerFast")
50
+ special_image_token = "<|image|>"
51
+
52
+ def __init__(self, image_processor, tokenizer):
53
+ self.image_processor = image_processor
54
+ self.tokenizer = tokenizer
55
+ self.num_img_tokens = image_processor.num_img_tokens
56
+ self.img_tokens = [f"<|image_{i+1}|>" for i in range(1000000)]
57
+
58
+ def __call__(
59
+ self,
60
+ text: Union[TextInput, List[TextInput]],
61
+ images: ImageInput = None,
62
+ padding: Union[bool, str, PaddingStrategy] = False,
63
+ truncation: Union[bool, str, TruncationStrategy] = None,
64
+ max_length=None,
65
+ return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
66
+ ) -> BatchFeature:
67
+ """
68
+ Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
69
+ and `kwargs` arguments to LlamaTokenizerFast's [`~LlamaTokenizerFast.__call__`] if `text` is not `None` to encode
70
+ the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to
71
+ Phi3ImageProcessor's [`~Phi3ImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring
72
+ of the above two methods for more information.
73
+
74
+ Args:
75
+ text (`str`, `List[str]`, `List[List[str]]`):
76
+ The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
77
+ (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
78
+ `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
79
+ images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
80
+ The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
81
+ tensor. Both channels-first and channels-last formats are supported.
82
+ padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
83
+ Select a strategy to pad the returned sequences (according to the model's padding side and padding
84
+ index) among:
85
+ - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
86
+ sequence if provided).
87
+ - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
88
+ acceptable input length for the model if that argument is not provided.
89
+ - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
90
+ lengths).
91
+ max_length (`int`, *optional*):
92
+ Maximum length of the returned list and optionally padding length (see above).
93
+ truncation (`bool`, *optional*):
94
+ Activates truncation to cut input sequences longer than `max_length` to `max_length`.
95
+ return_tensors (`str` or [`~utils.TensorType`], *optional*):
96
+ If set, will return tensors of a particular framework. Acceptable values are:
97
+
98
+ - `'tf'`: Return TensorFlow `tf.constant` objects.
99
+ - `'pt'`: Return PyTorch `torch.Tensor` objects.
100
+ - `'np'`: Return NumPy `np.ndarray` objects.
101
+ - `'jax'`: Return JAX `jnp.ndarray` objects.
102
+
103
+ Returns:
104
+ [`BatchFeature`]: A [`BatchFeature`] with the following fields:
105
+
106
+ - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
107
+ - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
108
+ `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
109
+ `None`).
110
+ - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
111
+ """
112
+ if images is not None:
113
+ image_inputs = self.image_processor(images, return_tensors=return_tensors)
114
+ else:
115
+ image_inputs = {}
116
+ inputs = self._convert_images_texts_to_inputs(image_inputs, text, padding=padding, truncation=truncation, max_length=max_length, return_tensors=return_tensors)
117
+ return inputs
118
+
119
+ def calc_num_image_tokens(self, images: ImageInput):
120
+ """ Calculate the number of image tokens for each image.
121
+ Args:
122
+ images (`ImageInput`):
123
+ Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If
124
+ passing in images with pixel values between 0 and 1, set `do_rescale=False`.
125
+ """
126
+ return self.image_processor.calc_num_image_tokens(images)
127
+
128
+ def calc_num_image_tokens_from_image_size(self, width, height):
129
+ """ Calculate the number of image token for an image with given width and height.
130
+ Args:
131
+ width (`int`):
132
+ Width of the image.
133
+ height (`int`):
134
+ Height of the image.
135
+ """
136
+ return self.image_processor.calc_num_image_tokens_from_image_size(width, height)
137
+
138
+
139
+ @property
140
+ def special_image_token_id(self):
141
+ return self.tokenizer.convert_tokens_to_ids(self.special_image_token)
142
+
143
+ def get_special_image_token_id(self):
144
+ return self.tokenizer.convert_tokens_to_ids(self.special_image_token)
145
+
146
+ def _convert_images_texts_to_inputs(self, images, texts, padding=False, truncation=None, max_length=None, return_tensors=None):
147
+
148
+ if not len(images):
149
+ model_inputs = self.tokenizer(texts, return_tensors=return_tensors, padding=padding, truncation=truncation, max_length=max_length)
150
+ return BatchFeature(data={**model_inputs})
151
+
152
+ pattern = r"<\|image_\d+\|>"
153
+ if isinstance(texts, str):
154
+ texts = [texts]
155
+
156
+ prompt_chunks = []
157
+ image_tags = []
158
+ for text in texts:
159
+ prompt_chunks.append([self.tokenizer(chunk).input_ids for chunk in re.split(pattern, text)])
160
+ image_tags.append(re.findall(pattern, text))
161
+
162
+ if 'num_img_tokens' in images:
163
+ num_img_tokens = images['num_img_tokens']
164
+ else:
165
+ assert 'num_crops' in images, 'num_crops must be provided in images if num_img_tokens is not provided'
166
+ num_crops = images['num_crops']
167
+ num_img_tokens = [_num_crops * self.num_img_tokens for _num_crops in num_crops]
168
+
169
+ images, image_sizes = images['pixel_values'], images['image_sizes']
170
+
171
+ # image_tags needs to start from 1 to n
172
+ # image_tags = re.findall(pattern, texts)
173
+ # image_ids = [int(s.split("|")[1].split("_")[-1]) * -1 for s in image_tags]
174
+ # image_ids_pad = [[iid]*num_img_tokens[i] for i, iid in enumerate(image_ids)]
175
+ image_ids = [[int(s.split("|")[1].split("_")[-1]) for s in tags] for tags in image_tags]
176
+ unique_image_ids = sorted(list(set([iid for ids in image_ids for iid in ids])))
177
+ # image_ids must start from 1, and must be continuous int, e.g. [1, 2, 3], cannot be [1, 4, 5]
178
+ # check the condition
179
+ assert unique_image_ids == list(range(1, len(unique_image_ids)+1)), f"image_ids must start from 1, and must be continuous int, e.g. [1, 2, 3], cannot be {unique_image_ids}"
180
+ # total images must be the same as the number of image tags
181
+ assert len(unique_image_ids) == len(images), f"total images must be the same as the number of image tags, got {len(unique_image_ids)} image tags and {len(images)} images"
182
+
183
+ image_ids_pad = [[[-iid]*num_img_tokens[iid-1] for iid in ids] for ids in image_ids]
184
+
185
+ def insert_separator(X, sep_list):
186
+ if len(X) > len(sep_list):
187
+ sep_list.append([])
188
+ return [ele for sublist in zip(X, sep_list) for ele in sublist]
189
+ input_ids = []
190
+ for sub_prompt_chunks, sub_image_ids_pad in zip(prompt_chunks, image_ids_pad):
191
+ input_ids.append([])
192
+ offset = 0
193
+ for x in insert_separator(sub_prompt_chunks, sub_image_ids_pad):
194
+ input_ids[-1].extend(x[offset:])
195
+
196
+ max_length = max(len(ids) for ids in input_ids)
197
+ for i in range(len(input_ids)):
198
+ while len(input_ids[i]) < max_length:
199
+ input_ids[i] = [self.tokenizer.pad_token_id]+input_ids[i]
200
+
201
+
202
+ input_ids = torch.tensor(input_ids, dtype=torch.long).unsqueeze(0)
203
+ attention_mask = (input_ids > -1000000).to(torch.long)
204
+ attention_mask[input_ids == self.tokenizer.pad_token_id] = 0
205
+
206
+ return BatchFeature(data={"input_ids": input_ids,
207
+ "attention_mask": attention_mask,
208
+ "pixel_values": images,
209
+ "image_sizes": image_sizes})
210
+
211
+
212
+ # Copied from transformers.models.clip.processing_clip.CLIPProcessor.batch_decode with CLIP->Llama
213
+ def batch_decode(self, *args, **kwargs):
214
+ """
215
+ This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
216
+ refer to the docstring of this method for more information.
217
+ """
218
+ return self.tokenizer.batch_decode(*args, **kwargs)
219
+
220
+ # Copied from transformers.models.clip.processing_clip.CLIPProcessor.decode with CLIP->Llama
221
+ def decode(self, *args, **kwargs):
222
+ """
223
+ This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
224
+ the docstring of this method for more information.
225
+ """
226
+ return self.tokenizer.decode(*args, **kwargs)
227
+
228
+ @property
229
+ # Copied from transformers.models.clip.processing_clip.CLIPProcessor.model_input_names
230
+ def model_input_names(self):
231
+ tokenizer_input_names = self.tokenizer.model_input_names
232
+ image_processor_input_names = self.image_processor.model_input_names
233
+ return list(dict.fromkeys(tokenizer_input_names + image_processor_input_names))