478 lines
22 KiB
Python
478 lines
22 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
# adapted from https://github.com/ManaEstras/transformers/blob/v4.57.1.hyvl/src/transformers/models/hunyuan_vl/image_processing_hunyuan_vl.py
|
|
"""Image processor class for HunYuanVL."""
|
|
|
|
# isort conflicts with ruff for transformers imports
|
|
# 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 HunYuanVLImageProcessor(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}
|
|
# 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
|
|
|
|
# hard-code
|
|
|
|
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,
|
|
):
|
|
"""
|
|
Preprocess an image or batch of images. Copy of the `preprocess` method from `CLIPImageProcessor`.
|
|
|
|
Args:
|
|
images (`ImageInput`):
|
|
Image or batch of images to preprocess. Expects pixel values ranging from 0 to 255. If pixel values range from 0 to 1, set `do_rescale=False`.
|
|
do_resize (`bool`, *optional*, defaults to `self.do_resize`):
|
|
Whether to resize the image.
|
|
size (`dict[str, int]`, *optional*, defaults to `self.size`):
|
|
Size of the image after resizing. `shortest_edge` and `longest_edge` keys must be present.
|
|
resample (`PILImageResampling`, *optional*, defaults to `self.resample`):
|
|
Resampling filter to use if resizing the image. This can be one of the `PILImageResampling` enums.
|
|
do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
|
|
Whether to rescale the image.
|
|
rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
|
|
Scale factor to use if rescaling the image.
|
|
do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
|
|
Whether to normalize the image.
|
|
image_mean (`float` or `list[float]`, *optional*, defaults to `self.image_mean`):
|
|
Mean to use if normalizing the image. Can be a float or a list of floats corresponding to the number of channels in the image.
|
|
image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`):
|
|
Standard deviation to use if normalizing the image. Can be a float or a list of floats corresponding to the number of channels in the image.
|
|
patch_size (`int`, *optional*, defaults to `self.patch_size`):
|
|
The spatial patch size of the vision encoder.
|
|
temporal_patch_size (`int`, *optional*, defaults to `self.temporal_patch_size`):
|
|
The temporal patch size of the vision encoder.
|
|
merge_size (`int`, *optional*, defaults to `self.merge_size`):
|
|
The merge size of the vision encoder to llm encoder.
|
|
do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`):
|
|
Whether to convert the image to RGB.
|
|
data_format (`ChannelDimension`, *optional*, defaults to `ChannelDimension.FIRST`):
|
|
The channel dimension format for the output image. Can be one of:
|
|
- `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
|
|
- `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
|
|
- Unset: Use the channel dimension format of the input image.
|
|
input_data_format (`ChannelDimension` or `str`, *optional*):
|
|
The channel dimension format for the input image. Can be one of:
|
|
- `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
|
|
- `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
|
|
- `"none"` or `ChannelDimension.NONE`: image in (height, width) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
|
|
""" # noqa: E501
|
|
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,
|
|
):
|
|
"""
|
|
Args:
|
|
images (`ImageInput`):
|
|
Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If
|
|
passing in images with pixel values between 0 and 1, set `do_rescale=False`.
|
|
videos (`VideoInput`):
|
|
Video to preprocess. Expects a single or batch of videos with pixel values ranging from 0 to 255. If
|
|
passing in videos with pixel values between 0 and 1, set `do_rescale=False`.
|
|
do_resize (`bool`, *optional*, defaults to `self.do_resize`):
|
|
Whether to resize the image.
|
|
size (`dict[str, int]`, *optional*, defaults to `self.size`):
|
|
Size of the image after resizing. Shortest edge of the image is resized to size["shortest_edge"], with
|
|
the longest edge resized to keep the input aspect ratio.
|
|
resample (`int`, *optional*, defaults to `self.resample`):
|
|
Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`. Only
|
|
has an effect if `do_resize` is set to `True`.
|
|
do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
|
|
Whether to rescale the image.
|
|
rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
|
|
Rescale factor to rescale the image by if `do_rescale` is set to `True`.
|
|
do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
|
|
Whether to normalize the image.
|
|
image_mean (`float` or `list[float]`, *optional*, defaults to `self.image_mean`):
|
|
Image mean to use for normalization. Only has an effect if `do_normalize` is set to `True`.
|
|
image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`):
|
|
Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to
|
|
`True`.
|
|
min_pixels (`int`, *optional*, defaults to `self.min_pixels`):
|
|
The min pixels of the image to resize the image.
|
|
max_pixels (`int`, *optional*, defaults to `self.max_pixels`):
|
|
The max pixels of the image to resize the image.
|
|
patch_size (`int`, *optional*, defaults to `self.patch_size`):
|
|
The spatial patch size of the vision encoder.
|
|
temporal_patch_size (`int`, *optional*, defaults to `self.temporal_patch_size`):
|
|
The temporal patch size of the vision encoder.
|
|
merge_size (`int`, *optional*, defaults to `self.merge_size`):
|
|
The merge size of the vision encoder to llm encoder.
|
|
do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`):
|
|
Whether to convert the image to RGB.
|
|
return_tensors (`str` or `TensorType`, *optional*):
|
|
The type of tensors to return. Can be one of:
|
|
- Unset: Return a list of `np.ndarray`.
|
|
- `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`.
|
|
- `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
|
|
- `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`.
|
|
- `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`.
|
|
data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`):
|
|
The channel dimension format for the output image. Can be one of:
|
|
- `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
|
|
- `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
|
|
- Unset: Use the channel dimension format of the input image.
|
|
input_data_format (`ChannelDimension` or `str`, *optional*):
|
|
The channel dimension format for the input image. If unset, the channel dimension format is inferred
|
|
from the input image. Can be one of:
|
|
- `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
|
|
- `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
|
|
- `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
|
|
|
|
""" # noqa: E501
|
|
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:
|
|
# backward compatibility: override size with min_pixels and max_pixels
|
|
# if they are provided.
|
|
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}
|
|
)
|
|
|
|
# kept for BC only and should be removed after v5.0
|
|
if videos is not None:
|
|
logger.warning(
|
|
"`HunYuanVLV1ImageProcessor` works only with image inputs "
|
|
"and doesn't process videos anymore. "
|
|
"This is a deprecated behavior and will be removed in v5.0. "
|
|
"Your videos should be forwarded to `HunYuanVLV1VideoProcessor`. "
|
|
)
|
|
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):
|
|
"""
|
|
A utility that returns number of image patches for a given image size.
|
|
|
|
Args:
|
|
height (`int`):
|
|
Height of the input image.
|
|
width (`int`):
|
|
Width of the input image.
|
|
images_kwargs (`dict`, *optional*):
|
|
Any kwargs to override defaults of the image processor.
|
|
Returns:
|
|
`int`: Number of image patches per image.
|
|
"""
|
|
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("HunYuanVLImageProcessor", HunYuanVLImageProcessor)
|