# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/paddleocr_vl/modular_paddleocr_vl.py. # Do NOT edit this file manually as any edits will be overwritten by the generation of # the file from the modular. If any change should be done, please apply the change to the # modular_paddleocr_vl.py file directly. One of our CI enforces this. # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # Copyright 2025 The PaddlePaddle Team and The HuggingFace Inc. team. All rights reserved. # # This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX # and OPT implementations in this library. It has been modified from its # original forms to accommodate minor architectural differences compared # to GPT-NeoX and OPT used by the Meta AI team that trained the model. # # 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. import math from typing import Optional import torch import torch.nn.functional as F from ...image_processing_utils import BatchFeature from ...image_processing_utils_fast import BaseImageProcessorFast, group_images_by_shape, reorder_images from ...image_utils import OPENAI_CLIP_MEAN, OPENAI_CLIP_STD, PILImageResampling, SizeDict from ...utils import TensorType def smart_resize( height: int, width: int, factor: int = 28, min_pixels: int = 384 * 384, max_pixels: int = 1536 * 1536, ): if height < factor: width = round((width * factor) / height) height = factor if width < factor: height = round((height * factor) / width) width = factor if max(height, width) / min(height, width) > 200: raise ValueError( f"absolute aspect ratio must be smaller than 200, got {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 = math.floor(height / beta / factor) * factor w_bar = 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 PaddleOCRVLImageProcessorFast(BaseImageProcessorFast): 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 = 384 * 384, max_pixels: int = 1536 * 1536, patch_size: int = 14, temporal_patch_size: int = 1, 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": 384 * 384, "longest_edge": 1536 * 1536} # backward compatibility: override size with min_pixels and max_pixels if they are provided 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: list["torch.Tensor"], do_resize: bool, size: SizeDict, interpolation: Optional["F.InterpolationMode"], do_rescale: bool, rescale_factor: float, do_normalize: bool, image_mean: float | list[float] | None, image_std: float | list[float] | None, disable_grouping: bool | None, return_tensors: str | TensorType | None, patch_size: int | None = None, temporal_patch_size: int | None = None, merge_size: int | None = None, **kwargs, ): 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 grouped_images, grouped_images_index = group_images_by_shape(images, disable_grouping=disable_grouping) resized_images_grouped = {} for shape, stacked_images in grouped_images.items(): height, width = stacked_images.shape[-2:] if do_resize: resized_height, resized_width = smart_resize( height, width, factor=patch_size * merge_size, min_pixels=size["shortest_edge"], max_pixels=size["longest_edge"], ) stacked_images = self.resize( image=stacked_images, size=SizeDict(height=resized_height, width=resized_width), interpolation=interpolation, ) resized_images_grouped[shape] = stacked_images resized_images = reorder_images(resized_images_grouped, grouped_images_index) # Group images by size for further processing # Needed in case do_resize is False, or resize returns images with different sizes grouped_images, grouped_images_index = group_images_by_shape(resized_images, disable_grouping=disable_grouping) processed_images_grouped = {} processed_grids = {} for shape, stacked_images in grouped_images.items(): resized_height, resized_width = stacked_images.shape[-2:] # Fused rescale and normalize patches = self.rescale_and_normalize( stacked_images, do_rescale, rescale_factor, do_normalize, image_mean, image_std ) if patches.ndim == 4: # add a temporal dimension if we have images patches = patches.unsqueeze(1) if patches.shape[1] % temporal_patch_size != 0: repeats = patches[:, -1:].repeat(1, temporal_patch_size - 1, 1, 1, 1) patches = torch.cat([patches, repeats], dim=1) batch_size, grid_t, channel = patches.shape[:3] grid_t = grid_t // temporal_patch_size grid_h, grid_w = ( resized_height // patch_size, resized_width // patch_size, ) patches = patches.view( batch_size, grid_t, temporal_patch_size, channel, grid_h, patch_size, grid_w, patch_size, ) patches = patches.permute(0, 1, 4, 6, 3, 2, 5, 7) flatten_patches = patches.reshape(batch_size, grid_t * grid_h * grid_w, channel, patch_size, patch_size) processed_images_grouped[shape] = flatten_patches processed_grids[shape] = [[grid_t, grid_h, grid_w]] * batch_size processed_images = reorder_images(processed_images_grouped, grouped_images_index) processed_grids = reorder_images(processed_grids, grouped_images_index) pixel_values = torch.cat(processed_images, dim=0) image_grid_thw = torch.tensor(processed_grids) return BatchFeature( data={"pixel_values": pixel_values, "image_grid_thw": image_grid_thw}, tensor_type=return_tensors ) __all__ = ["PaddleOCRVLImageProcessorFast"]