File size: 13,252 Bytes
30b022c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# Modified from HunyuanVL image processor for BrainOCR.
"""Image processor class for BrainOCR."""

# isort: skip_file
import math

import numpy as np
import torchvision.transforms as transforms
from transformers import AutoImageProcessor
from transformers.image_processing_utils import BaseImageProcessor, BatchFeature
from transformers.image_transforms import (
    convert_to_rgb,
)
from transformers.image_utils import (
    OPENAI_CLIP_MEAN,
    OPENAI_CLIP_STD,
    ChannelDimension,
    ImageInput,
    PILImageResampling,
    make_flat_list_of_images,
    make_list_of_images,
    valid_images,
    validate_preprocess_arguments,
)
from transformers.utils import TensorType, logging
from transformers.video_utils import VideoInput, make_batched_videos

logger = logging.get_logger(__name__)


def smart_resize(
    height: int,
    width: int,
    factor: int = 16,
    min_pixels: int = 512 * 512,
    max_pixels: int = 2048 * 2048,
):
    """Rescales the image so that the following conditions are met:

    1. Both dimensions (height and width) are divisible by 'factor'.

    2. The total number of pixels is within the range ['min_pixels', 'max_pixels'].

    3. The aspect ratio of the image is maintained as closely as possible.

    """
    if max(height, width) / min(height, width) > 200:
        raise ValueError(
            "absolute aspect ratio must be smaller than 200, got "
            f"{max(height, width) / min(height, width)}"
        )
    h_bar = round(height / factor) * factor
    w_bar = round(width / factor) * factor
    if h_bar * w_bar > max_pixels:
        beta = math.sqrt((height * width) / max_pixels)
        h_bar = max(factor, math.floor(height / beta / factor) * factor)
        w_bar = max(factor, math.floor(width / beta / factor) * factor)
    elif h_bar * w_bar < min_pixels:
        beta = math.sqrt(min_pixels / (height * width))
        h_bar = math.ceil(height * beta / factor) * factor
        w_bar = math.ceil(width * beta / factor) * factor
    return h_bar, w_bar


class BrainOCRImageProcessor(BaseImageProcessor):
    model_input_names = [
        "pixel_values",
        "image_grid_thw",
        "pixel_values_videos",
        "video_grid_thw",
    ]

    def __init__(
        self,
        do_resize: bool = True,
        size: dict[str, int] | None = None,
        resample: PILImageResampling = PILImageResampling.BICUBIC,
        do_rescale: bool = True,
        rescale_factor: int | float = 1 / 255,
        do_normalize: bool = True,
        image_mean: float | list[float] | None = None,
        image_std: float | list[float] | None = None,
        do_convert_rgb: bool = True,
        min_pixels: int | None = None,
        max_pixels: int | None = None,
        patch_size: int = 16,
        temporal_patch_size: int = 2,
        merge_size: int = 2,
        **kwargs,
    ) -> None:
        super().__init__(**kwargs)
        if size is not None and (
            "shortest_edge" not in size or "longest_edge" not in size
        ):
            raise ValueError(
                "size must contain 'shortest_edge' and 'longest_edge' keys."
            )
        else:
            size = {"shortest_edge": 512 * 512, "longest_edge": 2048 * 2048}
        if min_pixels is not None:
            size["shortest_edge"] = min_pixels
        if max_pixels is not None:
            size["longest_edge"] = max_pixels
        self.min_pixels = size["shortest_edge"]
        self.max_pixels = size["longest_edge"]
        self.size = size

        self.do_resize = do_resize
        self.resample = resample
        self.do_rescale = do_rescale
        self.rescale_factor = rescale_factor
        self.do_normalize = do_normalize
        self.image_mean = image_mean if image_mean is not None else OPENAI_CLIP_MEAN
        self.image_std = image_std if image_std is not None else OPENAI_CLIP_STD

        self.patch_size = patch_size
        self.temporal_patch_size = temporal_patch_size
        self.merge_size = merge_size
        self.do_convert_rgb = do_convert_rgb

    def _preprocess(
        self,
        images: ImageInput | VideoInput,
        do_resize: bool | None = None,
        size: dict[str, int] | None = None,
        resample: PILImageResampling = None,
        do_rescale: bool | None = None,
        rescale_factor: float | None = None,
        do_normalize: bool | None = None,
        image_mean: float | list[float] | None = None,
        image_std: float | list[float] | None = None,
        patch_size: int = 16,
        temporal_patch_size: int = 2,
        merge_size: int = 2,
        do_convert_rgb: bool | None = None,
        data_format: ChannelDimension | None = ChannelDimension.FIRST,
        input_data_format: str | ChannelDimension | None = None,
    ):
        images = make_list_of_images(images)

        if do_convert_rgb:
            images = [convert_to_rgb(image) for image in images]

        width, height = images[0].width, images[0].height
        resized_width, resized_height = width, height
        processed_images = []
        for image in images:
            if do_resize:
                resized_height, resized_width = smart_resize(
                    height=height,
                    width=width,
                    factor=patch_size * merge_size,
                    min_pixels=self.min_pixels,
                    max_pixels=self.max_pixels,
                )
                image = image.resize((resized_width, resized_height))

            if do_normalize:
                image = transforms.Compose(
                    [
                        transforms.ToTensor(),
                        transforms.Normalize(self.image_mean, self.image_std),
                    ]
                )(image)
            processed_images.append(image)

        patches = np.array(processed_images)
        channel = patches.shape[1]
        grid_t = patches.shape[0] // temporal_patch_size
        grid_h, grid_w = resized_height // patch_size, resized_width // patch_size
        patches = patches.reshape(
            1,
            channel,
            grid_h // merge_size,
            merge_size,
            patch_size,
            grid_w // merge_size,
            merge_size,
            patch_size,
        )
        patches = patches.transpose(0, 2, 3, 5, 6, 1, 4, 7)
        flatten_patches = patches.reshape(
            1 * grid_h * grid_w, channel * patch_size * patch_size
        )

        return flatten_patches, (grid_t, grid_h, grid_w)

    def preprocess(
        self,
        images: ImageInput,
        videos: VideoInput = None,
        do_resize: bool | None = None,
        size: dict[str, int] | None = None,
        min_pixels: int | None = None,
        max_pixels: int | None = None,
        resample: PILImageResampling = None,
        do_rescale: bool | None = None,
        rescale_factor: float | None = None,
        do_normalize: bool | None = None,
        image_mean: float | list[float] | None = None,
        image_std: float | list[float] | None = None,
        patch_size: int | None = None,
        temporal_patch_size: int | None = None,
        merge_size: int | None = None,
        do_convert_rgb: bool | None = None,
        return_tensors: str | TensorType | None = None,
        data_format: ChannelDimension | None = ChannelDimension.FIRST,
        input_data_format: str | ChannelDimension | None = None,
    ):
        min_pixels = min_pixels if min_pixels is not None else self.min_pixels
        max_pixels = max_pixels if max_pixels is not None else self.max_pixels

        if size is not None:
            if "shortest_edge" not in size or "longest_edge" not in size:
                raise ValueError(
                    "size must contain 'shortest_edge' and 'longest_edge' keys."
                )
            min_pixels = size["shortest_edge"]
        elif min_pixels is not None and max_pixels is not None:
            size = {"shortest_edge": min_pixels, "longest_edge": max_pixels}
        else:
            size = {**self.size}

        do_resize = do_resize if do_resize is not None else self.do_resize
        resample = resample if resample is not None else self.resample
        do_rescale = do_rescale if do_rescale is not None else self.do_rescale
        rescale_factor = (
            rescale_factor if rescale_factor is not None else self.rescale_factor
        )
        do_normalize = do_normalize if do_normalize is not None else self.do_normalize
        image_mean = image_mean if image_mean is not None else self.image_mean
        image_std = image_std if image_std is not None else self.image_std
        patch_size = patch_size if patch_size is not None else self.patch_size
        temporal_patch_size = (
            temporal_patch_size
            if temporal_patch_size is not None
            else self.temporal_patch_size
        )
        merge_size = merge_size if merge_size is not None else self.merge_size
        do_convert_rgb = (
            do_convert_rgb if do_convert_rgb is not None else self.do_convert_rgb
        )

        if images is not None:
            images = make_flat_list_of_images(images)

        if images is not None and not valid_images(images):
            raise ValueError(
                "Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
                "torch.Tensor, tf.Tensor or jax.ndarray."
            )

        validate_preprocess_arguments(
            rescale_factor=rescale_factor,
            do_normalize=do_normalize,
            image_mean=image_mean,
            image_std=image_std,
            do_resize=do_resize,
            size=size,
            resample=resample,
        )

        data = {}
        if images is not None:
            pixel_values, vision_grid_thws = [], []
            for image in images:
                patches, image_grid_thw = self._preprocess(
                    image,
                    do_resize=do_resize,
                    size=size,
                    resample=resample,
                    do_rescale=do_rescale,
                    rescale_factor=rescale_factor,
                    do_normalize=do_normalize,
                    image_mean=image_mean,
                    image_std=image_std,
                    patch_size=patch_size,
                    temporal_patch_size=temporal_patch_size,
                    merge_size=merge_size,
                    data_format=data_format,
                    do_convert_rgb=do_convert_rgb,
                    input_data_format=input_data_format,
                )
                pixel_values.extend(patches)
                vision_grid_thws.append(image_grid_thw)
            pixel_values = np.array(pixel_values)
            vision_grid_thws = np.array(vision_grid_thws)
            data.update(
                {"pixel_values": pixel_values, "image_grid_thw": vision_grid_thws}
            )

        if videos is not None:
            videos = make_batched_videos(videos)
            pixel_values_videos, vision_grid_thws_videos = [], []
            for images in videos:
                patches, video_grid_thw = self._preprocess(
                    images,
                    do_resize=do_resize,
                    size=size,
                    resample=resample,
                    do_rescale=do_rescale,
                    rescale_factor=rescale_factor,
                    do_normalize=do_normalize,
                    image_mean=image_mean,
                    image_std=image_std,
                    patch_size=patch_size,
                    temporal_patch_size=temporal_patch_size,
                    merge_size=merge_size,
                    data_format=data_format,
                    do_convert_rgb=do_convert_rgb,
                    input_data_format=input_data_format,
                )
                pixel_values_videos.extend(patches)
                vision_grid_thws_videos.append(video_grid_thw)
            data.update(
                {
                    "pixel_values_videos": np.array(pixel_values_videos),
                    "video_grid_thw": np.array(vision_grid_thws_videos),
                }
            )

        return BatchFeature(data=data, tensor_type=return_tensors)

    def get_number_of_image_patches(self, height: int, width: int, images_kwargs=None):
        min_pixels = (
            images_kwargs["min_pixels"]
            if "min_pixels" in images_kwargs
            else self.size["shortest_edge"]
        )
        max_pixels = (
            images_kwargs["max_pixels"]
            if "max_pixels" in images_kwargs
            else self.size["longest_edge"]
        )
        patch_size = images_kwargs.get("patch_size", self.patch_size)
        merge_size = images_kwargs.get("merge_size", self.merge_size)

        factor = patch_size * merge_size
        resized_height, resized_width = smart_resize(
            height, width, factor, min_pixels=min_pixels, max_pixels=max_pixels
        )
        grid_h, grid_w = resized_height // patch_size, resized_width // patch_size
        return grid_h * (grid_w + 1) + 2


AutoImageProcessor.register("BrainOCRImageProcessor", BrainOCRImageProcessor)