File size: 12,541 Bytes
9140675 |
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 |
# coding=utf-8
# Copyright 2025 The Keye 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.
from typing import List, Union
import numpy as np
from transformers.feature_extraction_utils import BatchFeature
from transformers.processing_utils import (
ProcessingKwargs,
ProcessorMixin,
Unpack,
VideosKwargs,
)
from transformers.tokenization_utils_base import PreTokenizedInput, TextInput
import torch
ImageInput = Union[
"PIL.Image.Image",
np.ndarray,
"torch.Tensor",
List["PIL.Image.Image"],
List[np.ndarray],
List["torch.Tensor"],
] # noqa
VideoInput = Union[
List["PIL.Image.Image"],
"np.ndarray",
"torch.Tensor",
List["np.ndarray"],
List["torch.Tensor"],
List[List["PIL.Image.Image"]],
List[List["np.ndarrray"]],
List[List["torch.Tensor"]],
] # noqa
class KeyeVideosProcessorKwargs(VideosKwargs, total=False):
fps: Union[List[float], float]
class KeyeProcessorKwargs(ProcessingKwargs, total=False):
videos_kwargs: KeyeVideosProcessorKwargs
_defaults = {
"text_kwargs": {
"padding": False,
},
"videos_kwargs": {"fps": 2.0},
}
class KeyeProcessor(ProcessorMixin):
r"""
[`KeyeProcessor`] offers all the functionalities of [`SiglipImageProcessor`] and [`Qwen2TokenizerFast`]. See the
[`~KeyeProcessor.__call__`] and [`~KeyeProcessor.decode`] for more information.
Args:
image_processor ([`SiglipImageProcessor`], *optional*):
The image processor is a required input.
tokenizer ([`Qwen2TokenizerFast`], *optional*):
The tokenizer is a required input.
chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages
in a chat into a tokenizable string.
"""
attributes = ["image_processor", "tokenizer"]
valid_kwargs = [
"chat_template",
"image_std",
"min_pixels",
"image_mean",
"merge_size",
"image_processor_type",
"temporal_patch_size",
"patch_size",
"max_pixels",
]
image_processor_class = "AutoImageProcessor"
tokenizer_class = ("Qwen2Tokenizer", "Qwen2TokenizerFast")
def __init__(
self, image_processor=None, tokenizer=None, chat_template=None, **kwargs
):
self.image_token = (
"<|image_pad|>"
if not hasattr(tokenizer, "image_token")
else tokenizer.image_token
)
self.video_token = (
"<|video_pad|>"
if not hasattr(tokenizer, "video_token")
else tokenizer.video_token
)
super().__init__(image_processor, tokenizer, chat_template=chat_template)
def __call__(
self,
images: ImageInput = None,
text: Union[
TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]
] = None,
videos: VideoInput = None,
**kwargs: Unpack[KeyeProcessorKwargs],
) -> BatchFeature:
"""
Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
and `kwargs` arguments to Qwen2TokenizerFast's [`~Qwen2TokenizerFast.__call__`] if `text` is not `None` to encode
the text. To prepare the vision inputs, this method forwards the `vision_infos` and `kwrags` arguments to
SiglipImageProcessor's [`~SiglipImageProcessor.__call__`] if `vision_infos` is not `None`.
Args:
images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
tensor. Both channels-first and channels-last formats are supported.
text (`str`, `List[str]`, `List[List[str]]`):
The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
(pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
`is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
videos (`np.ndarray`, `torch.Tensor`, `List[np.ndarray]`, `List[torch.Tensor]`):
The image or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch
tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported.
return_tensors (`str` or [`~utils.TensorType`], *optional*):
If set, will return tensors of a particular framework. Acceptable values are:
- `'tf'`: Return TensorFlow `tf.constant` objects.
- `'pt'`: Return PyTorch `torch.Tensor` objects.
- `'np'`: Return NumPy `np.ndarray` objects.
- `'jax'`: Return JAX `jnp.ndarray` objects.
Returns:
[`BatchFeature`]: A [`BatchFeature`] with the following fields:
- **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
- **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
`return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
`None`).
- **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
- **pixel_values_videos** -- Pixel values of videos to be fed to a model. Returned when `videos` is not `None`.
- **image_grid_thw** -- List of image 3D grid in LLM. Returned when `images` is not `None`.
- **video_grid_thw** -- List of video 3D grid in LLM. Returned when `videos` is not `None`.
- **second_per_grid_ts** -- List of video seconds per time grid. Returned when `videos` is not `None`.
"""
output_kwargs = self._merge_kwargs(
KeyeProcessorKwargs,
tokenizer_init_kwargs=self.tokenizer.init_kwargs,
**kwargs,
)
if images is not None:
image_inputs = self.image_processor(images=images, return_tensors="pt")
image_inputs["pixel_values"] = image_inputs["pixel_values"]
image_grid_thw = image_inputs["image_grid_thw"]
else:
image_inputs = {}
image_grid_thw = None
if videos is not None:
# TODO: add video processing
videos_inputs = self.image_processor(
images=None, videos=videos, **output_kwargs["images_kwargs"]
)
video_grid_thw = videos_inputs["video_grid_thw"]
fps = output_kwargs["videos_kwargs"].pop("fps", 2.0)
if isinstance(fps, (int, float)):
second_per_grid_ts = [
self.image_processor.temporal_patch_size / fps
] * len(video_grid_thw)
elif hasattr(fps, "__len__") and len(fps) == len(video_grid_thw):
second_per_grid_ts = [
self.image_processor.temporal_patch_size / tmp for tmp in fps
]
else:
raise ValueError(
f"The length of fps ({len(fps) if hasattr(fps, '__len__') else fps}) must be equal to the length of video_grid_thw ({len(video_grid_thw)}) or fps should be a single number."
)
videos_inputs.update(
{"second_per_grid_ts": torch.tensor(second_per_grid_ts)}
)
else:
videos_inputs = {}
video_grid_thw = None
if not isinstance(text, list):
text = [text]
if image_grid_thw is not None:
index = 0
for i in range(len(text)):
while self.image_token in text[i]:
text[i] = text[i].replace(
self.image_token,
"<|placeholder|>"
* (
image_grid_thw[index].prod()
// self.image_processor.merge_size
// self.image_processor.merge_size
),
1,
)
index += 1
text[i] = text[i].replace("<|placeholder|>", self.image_token)
if video_grid_thw is not None:
index = 0
for i in range(len(text)):
while self.video_token in text[i]:
text[i] = text[i].replace(
self.video_token,
"<|placeholder|>"
* (
video_grid_thw[index].prod()
// self.image_processor.merge_size
// self.image_processor.merge_size
),
1,
)
index += 1
text[i] = text[i].replace("<|placeholder|>", self.video_token)
text_inputs = self.tokenizer(text, **output_kwargs["text_kwargs"])
return BatchFeature(data={**text_inputs, **image_inputs, **videos_inputs})
def batch_decode(self, *args, **kwargs):
"""
This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
refer to the docstring of this method for more information.
"""
return self.tokenizer.batch_decode(*args, **kwargs)
def decode(self, *args, **kwargs):
"""
This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
the docstring of this method for more information.
"""
return self.tokenizer.decode(*args, **kwargs)
def post_process_image_text_to_text(
self,
generated_outputs,
skip_special_tokens=True,
clean_up_tokenization_spaces=False,
**kwargs,
):
"""
Post-process the output of the model to decode the text.
Args:
generated_outputs (`torch.Tensor` or `np.ndarray`):
The output of the model `generate` function. The output is expected to be a tensor of shape `(batch_size, sequence_length)`
or `(sequence_length,)`.
skip_special_tokens (`bool`, *optional*, defaults to `True`):
Whether or not to remove special tokens in the output. Argument passed to the tokenizer's `batch_decode` method.
Clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`):
Whether or not to clean up the tokenization spaces. Argument passed to the tokenizer's `batch_decode` method.
**kwargs:
Additional arguments to be passed to the tokenizer's `batch_decode method`.
Returns:
`List[str]`: The decoded text.
"""
return self.tokenizer.batch_decode(
generated_outputs,
skip_special_tokens=skip_special_tokens,
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
**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
names_from_processor = list(
dict.fromkeys(tokenizer_input_names + image_processor_input_names)
)
return names_from_processor + ["second_per_grid_ts"]
__all__ = ["KeyeProcessor", "KeyeProcessor_moonvit", "KeyeProcessor"]
|