Spaces:
Runtime error
Runtime error
File size: 34,533 Bytes
f8f5cdf |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 |
# coding=utf-8
# Copyright 2022 The HuggingFace Inc. team.
#
# 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 copy
import json
import os
import warnings
from io import BytesIO
from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
import numpy as np
import requests
from .dynamic_module_utils import custom_object_save
from .feature_extraction_utils import BatchFeature as BaseBatchFeature
from .image_transforms import center_crop, normalize, rescale
from .image_utils import ChannelDimension
from .utils import (
IMAGE_PROCESSOR_NAME,
PushToHubMixin,
add_model_info_to_auto_map,
cached_file,
copy_func,
download_url,
is_offline_mode,
is_remote_url,
is_vision_available,
logging,
)
if is_vision_available():
from PIL import Image
logger = logging.get_logger(__name__)
# TODO: Move BatchFeature to be imported by both image_processing_utils and image_processing_utils
# We override the class string here, but logic is the same.
class BatchFeature(BaseBatchFeature):
r"""
Holds the output of the image processor specific `__call__` methods.
This class is derived from a python dictionary and can be used as a dictionary.
Args:
data (`dict`):
Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.).
tensor_type (`Union[None, str, TensorType]`, *optional*):
You can give a tensor_type here to convert the lists of integers in PyTorch/TensorFlow/Numpy Tensors at
initialization.
"""
# TODO: (Amy) - factor out the common parts of this and the feature extractor
class ImageProcessingMixin(PushToHubMixin):
"""
This is an image processor mixin used to provide saving/loading functionality for sequential and image feature
extractors.
"""
_auto_class = None
def __init__(self, **kwargs):
"""Set elements of `kwargs` as attributes."""
# Pop "processor_class" as it should be saved as private attribute
self._processor_class = kwargs.pop("processor_class", None)
# Additional attributes without default values
for key, value in kwargs.items():
try:
setattr(self, key, value)
except AttributeError as err:
logger.error(f"Can't set {key} with value {value} for {self}")
raise err
def _set_processor_class(self, processor_class: str):
"""Sets processor class as an attribute."""
self._processor_class = processor_class
@classmethod
def from_pretrained(
cls,
pretrained_model_name_or_path: Union[str, os.PathLike],
cache_dir: Optional[Union[str, os.PathLike]] = None,
force_download: bool = False,
local_files_only: bool = False,
token: Optional[Union[str, bool]] = None,
revision: str = "main",
**kwargs,
):
r"""
Instantiate a type of [`~image_processing_utils.ImageProcessingMixin`] from an image processor.
Args:
pretrained_model_name_or_path (`str` or `os.PathLike`):
This can be either:
- a string, the *model id* of a pretrained image_processor hosted inside a model repo on
huggingface.co. Valid model ids can be located at the root-level, like `bert-base-uncased`, or
namespaced under a user or organization name, like `dbmdz/bert-base-german-cased`.
- a path to a *directory* containing a image processor file saved using the
[`~image_processing_utils.ImageProcessingMixin.save_pretrained`] method, e.g.,
`./my_model_directory/`.
- a path or url to a saved image processor JSON *file*, e.g.,
`./my_model_directory/preprocessor_config.json`.
cache_dir (`str` or `os.PathLike`, *optional*):
Path to a directory in which a downloaded pretrained model image processor should be cached if the
standard cache should not be used.
force_download (`bool`, *optional*, defaults to `False`):
Whether or not to force to (re-)download the image processor files and override the cached versions if
they exist.
resume_download (`bool`, *optional*, defaults to `False`):
Whether or not to delete incompletely received file. Attempts to resume the download if such a file
exists.
proxies (`Dict[str, str]`, *optional*):
A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
token (`str` or `bool`, *optional*):
The token to use as HTTP bearer authorization for remote files. If `True`, or not specified, will use
the token generated when running `huggingface-cli login` (stored in `~/.huggingface`).
revision (`str`, *optional*, defaults to `"main"`):
The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
identifier allowed by git.
<Tip>
To test a pull request you made on the Hub, you can pass `revision="refs/pr/<pr_number>".
</Tip>
return_unused_kwargs (`bool`, *optional*, defaults to `False`):
If `False`, then this function returns just the final image processor object. If `True`, then this
functions returns a `Tuple(image_processor, unused_kwargs)` where *unused_kwargs* is a dictionary
consisting of the key/value pairs whose keys are not image processor attributes: i.e., the part of
`kwargs` which has not been used to update `image_processor` and is otherwise ignored.
subfolder (`str`, *optional*, defaults to `""`):
In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
specify the folder name here.
kwargs (`Dict[str, Any]`, *optional*):
The values in kwargs of any keys which are image processor attributes will be used to override the
loaded values. Behavior concerning key/value pairs whose keys are *not* image processor attributes is
controlled by the `return_unused_kwargs` keyword parameter.
Returns:
A image processor of type [`~image_processing_utils.ImageProcessingMixin`].
Examples:
```python
# We can't instantiate directly the base class *ImageProcessingMixin* so let's show the examples on a
# derived class: *CLIPImageProcessor*
image_processor = CLIPImageProcessor.from_pretrained(
"openai/clip-vit-base-patch32"
) # Download image_processing_config from huggingface.co and cache.
image_processor = CLIPImageProcessor.from_pretrained(
"./test/saved_model/"
) # E.g. image processor (or model) was saved using *save_pretrained('./test/saved_model/')*
image_processor = CLIPImageProcessor.from_pretrained("./test/saved_model/preprocessor_config.json")
image_processor = CLIPImageProcessor.from_pretrained(
"openai/clip-vit-base-patch32", do_normalize=False, foo=False
)
assert image_processor.do_normalize is False
image_processor, unused_kwargs = CLIPImageProcessor.from_pretrained(
"openai/clip-vit-base-patch32", do_normalize=False, foo=False, return_unused_kwargs=True
)
assert image_processor.do_normalize is False
assert unused_kwargs == {"foo": False}
```"""
kwargs["cache_dir"] = cache_dir
kwargs["force_download"] = force_download
kwargs["local_files_only"] = local_files_only
kwargs["revision"] = revision
use_auth_token = kwargs.pop("use_auth_token", None)
if use_auth_token is not None:
warnings.warn(
"The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.", FutureWarning
)
if token is not None:
raise ValueError(
"`token` and `use_auth_token` are both specified. Please set only the argument `token`."
)
token = use_auth_token
if token is not None:
kwargs["token"] = token
image_processor_dict, kwargs = cls.get_image_processor_dict(pretrained_model_name_or_path, **kwargs)
return cls.from_dict(image_processor_dict, **kwargs)
def save_pretrained(self, save_directory: Union[str, os.PathLike], push_to_hub: bool = False, **kwargs):
"""
Save an image processor object to the directory `save_directory`, so that it can be re-loaded using the
[`~image_processing_utils.ImageProcessingMixin.from_pretrained`] class method.
Args:
save_directory (`str` or `os.PathLike`):
Directory where the image processor JSON file will be saved (will be created if it does not exist).
push_to_hub (`bool`, *optional*, defaults to `False`):
Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
namespace).
kwargs (`Dict[str, Any]`, *optional*):
Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
"""
use_auth_token = kwargs.pop("use_auth_token", None)
if use_auth_token is not None:
warnings.warn(
"The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.", FutureWarning
)
if kwargs.get("token", None) is not None:
raise ValueError(
"`token` and `use_auth_token` are both specified. Please set only the argument `token`."
)
kwargs["token"] = use_auth_token
if os.path.isfile(save_directory):
raise AssertionError(f"Provided path ({save_directory}) should be a directory, not a file")
os.makedirs(save_directory, exist_ok=True)
if push_to_hub:
commit_message = kwargs.pop("commit_message", None)
repo_id = kwargs.pop("repo_id", save_directory.split(os.path.sep)[-1])
repo_id = self._create_repo(repo_id, **kwargs)
files_timestamps = self._get_files_timestamps(save_directory)
# If we have a custom config, we copy the file defining it in the folder and set the attributes so it can be
# loaded from the Hub.
if self._auto_class is not None:
custom_object_save(self, save_directory, config=self)
# If we save using the predefined names, we can load using `from_pretrained`
output_image_processor_file = os.path.join(save_directory, IMAGE_PROCESSOR_NAME)
self.to_json_file(output_image_processor_file)
logger.info(f"Image processor saved in {output_image_processor_file}")
if push_to_hub:
self._upload_modified_files(
save_directory,
repo_id,
files_timestamps,
commit_message=commit_message,
token=kwargs.get("token"),
)
return [output_image_processor_file]
@classmethod
def get_image_processor_dict(
cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs
) -> Tuple[Dict[str, Any], Dict[str, Any]]:
"""
From a `pretrained_model_name_or_path`, resolve to a dictionary of parameters, to be used for instantiating a
image processor of type [`~image_processor_utils.ImageProcessingMixin`] using `from_dict`.
Parameters:
pretrained_model_name_or_path (`str` or `os.PathLike`):
The identifier of the pre-trained checkpoint from which we want the dictionary of parameters.
subfolder (`str`, *optional*, defaults to `""`):
In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
specify the folder name here.
Returns:
`Tuple[Dict, Dict]`: The dictionary(ies) that will be used to instantiate the image processor object.
"""
cache_dir = kwargs.pop("cache_dir", None)
force_download = kwargs.pop("force_download", False)
resume_download = kwargs.pop("resume_download", False)
proxies = kwargs.pop("proxies", None)
token = kwargs.pop("token", None)
use_auth_token = kwargs.pop("use_auth_token", None)
local_files_only = kwargs.pop("local_files_only", False)
revision = kwargs.pop("revision", None)
subfolder = kwargs.pop("subfolder", "")
from_pipeline = kwargs.pop("_from_pipeline", None)
from_auto_class = kwargs.pop("_from_auto", False)
if use_auth_token is not None:
warnings.warn(
"The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.", FutureWarning
)
if token is not None:
raise ValueError(
"`token` and `use_auth_token` are both specified. Please set only the argument `token`."
)
token = use_auth_token
user_agent = {"file_type": "image processor", "from_auto_class": from_auto_class}
if from_pipeline is not None:
user_agent["using_pipeline"] = from_pipeline
if is_offline_mode() and not local_files_only:
logger.info("Offline mode: forcing local_files_only=True")
local_files_only = True
pretrained_model_name_or_path = str(pretrained_model_name_or_path)
is_local = os.path.isdir(pretrained_model_name_or_path)
if os.path.isdir(pretrained_model_name_or_path):
image_processor_file = os.path.join(pretrained_model_name_or_path, IMAGE_PROCESSOR_NAME)
if os.path.isfile(pretrained_model_name_or_path):
resolved_image_processor_file = pretrained_model_name_or_path
is_local = True
elif is_remote_url(pretrained_model_name_or_path):
image_processor_file = pretrained_model_name_or_path
resolved_image_processor_file = download_url(pretrained_model_name_or_path)
else:
image_processor_file = IMAGE_PROCESSOR_NAME
try:
# Load from local folder or from cache or download from model Hub and cache
resolved_image_processor_file = cached_file(
pretrained_model_name_or_path,
image_processor_file,
cache_dir=cache_dir,
force_download=force_download,
proxies=proxies,
resume_download=resume_download,
local_files_only=local_files_only,
token=token,
user_agent=user_agent,
revision=revision,
subfolder=subfolder,
)
except EnvironmentError:
# Raise any environment error raise by `cached_file`. It will have a helpful error message adapted to
# the original exception.
raise
except Exception:
# For any other exception, we throw a generic error.
raise EnvironmentError(
f"Can't load image processor for '{pretrained_model_name_or_path}'. If you were trying to load"
" it from 'https://huggingface.co/models', make sure you don't have a local directory with the"
f" same name. Otherwise, make sure '{pretrained_model_name_or_path}' is the correct path to a"
f" directory containing a {IMAGE_PROCESSOR_NAME} file"
)
try:
# Load image_processor dict
with open(resolved_image_processor_file, "r", encoding="utf-8") as reader:
text = reader.read()
image_processor_dict = json.loads(text)
except json.JSONDecodeError:
raise EnvironmentError(
f"It looks like the config file at '{resolved_image_processor_file}' is not a valid JSON file."
)
if is_local:
logger.info(f"loading configuration file {resolved_image_processor_file}")
else:
logger.info(
f"loading configuration file {image_processor_file} from cache at {resolved_image_processor_file}"
)
if "auto_map" in image_processor_dict and not is_local:
image_processor_dict["auto_map"] = add_model_info_to_auto_map(
image_processor_dict["auto_map"], pretrained_model_name_or_path
)
return image_processor_dict, kwargs
@classmethod
def from_dict(cls, image_processor_dict: Dict[str, Any], **kwargs):
"""
Instantiates a type of [`~image_processing_utils.ImageProcessingMixin`] from a Python dictionary of parameters.
Args:
image_processor_dict (`Dict[str, Any]`):
Dictionary that will be used to instantiate the image processor object. Such a dictionary can be
retrieved from a pretrained checkpoint by leveraging the
[`~image_processing_utils.ImageProcessingMixin.to_dict`] method.
kwargs (`Dict[str, Any]`):
Additional parameters from which to initialize the image processor object.
Returns:
[`~image_processing_utils.ImageProcessingMixin`]: The image processor object instantiated from those
parameters.
"""
image_processor_dict = image_processor_dict.copy()
return_unused_kwargs = kwargs.pop("return_unused_kwargs", False)
# The `size` parameter is a dict and was previously an int or tuple in feature extractors.
# We set `size` here directly to the `image_processor_dict` so that it is converted to the appropriate
# dict within the image processor and isn't overwritten if `size` is passed in as a kwarg.
if "size" in kwargs and "size" in image_processor_dict:
image_processor_dict["size"] = kwargs.pop("size")
if "crop_size" in kwargs and "crop_size" in image_processor_dict:
image_processor_dict["crop_size"] = kwargs.pop("crop_size")
image_processor = cls(**image_processor_dict)
# Update image_processor with kwargs if needed
to_remove = []
for key, value in kwargs.items():
if hasattr(image_processor, key):
setattr(image_processor, key, value)
to_remove.append(key)
for key in to_remove:
kwargs.pop(key, None)
logger.info(f"Image processor {image_processor}")
if return_unused_kwargs:
return image_processor, kwargs
else:
return image_processor
def to_dict(self) -> Dict[str, Any]:
"""
Serializes this instance to a Python dictionary.
Returns:
`Dict[str, Any]`: Dictionary of all the attributes that make up this image processor instance.
"""
output = copy.deepcopy(self.__dict__)
output["image_processor_type"] = self.__class__.__name__
return output
@classmethod
def from_json_file(cls, json_file: Union[str, os.PathLike]):
"""
Instantiates a image processor of type [`~image_processing_utils.ImageProcessingMixin`] from the path to a JSON
file of parameters.
Args:
json_file (`str` or `os.PathLike`):
Path to the JSON file containing the parameters.
Returns:
A image processor of type [`~image_processing_utils.ImageProcessingMixin`]: The image_processor object
instantiated from that JSON file.
"""
with open(json_file, "r", encoding="utf-8") as reader:
text = reader.read()
image_processor_dict = json.loads(text)
return cls(**image_processor_dict)
def to_json_string(self) -> str:
"""
Serializes this instance to a JSON string.
Returns:
`str`: String containing all the attributes that make up this feature_extractor instance in JSON format.
"""
dictionary = self.to_dict()
for key, value in dictionary.items():
if isinstance(value, np.ndarray):
dictionary[key] = value.tolist()
# make sure private name "_processor_class" is correctly
# saved as "processor_class"
_processor_class = dictionary.pop("_processor_class", None)
if _processor_class is not None:
dictionary["processor_class"] = _processor_class
return json.dumps(dictionary, indent=2, sort_keys=True) + "\n"
def to_json_file(self, json_file_path: Union[str, os.PathLike]):
"""
Save this instance to a JSON file.
Args:
json_file_path (`str` or `os.PathLike`):
Path to the JSON file in which this image_processor instance's parameters will be saved.
"""
with open(json_file_path, "w", encoding="utf-8") as writer:
writer.write(self.to_json_string())
def __repr__(self):
return f"{self.__class__.__name__} {self.to_json_string()}"
@classmethod
def register_for_auto_class(cls, auto_class="AutoImageProcessor"):
"""
Register this class with a given auto class. This should only be used for custom image processors as the ones
in the library are already mapped with `AutoImageProcessor `.
<Tip warning={true}>
This API is experimental and may have some slight breaking changes in the next releases.
</Tip>
Args:
auto_class (`str` or `type`, *optional*, defaults to `"AutoImageProcessor "`):
The auto class to register this new image processor with.
"""
if not isinstance(auto_class, str):
auto_class = auto_class.__name__
import transformers.models.auto as auto_module
if not hasattr(auto_module, auto_class):
raise ValueError(f"{auto_class} is not a valid auto class.")
cls._auto_class = auto_class
def fetch_images(self, image_url_or_urls: Union[str, List[str]]):
"""
Convert a single or a list of urls into the corresponding `PIL.Image` objects.
If a single url is passed, the return value will be a single object. If a list is passed a list of objects is
returned.
"""
headers = {
"User-Agent": (
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0"
" Safari/537.36"
)
}
if isinstance(image_url_or_urls, list):
return [self.fetch_images(x) for x in image_url_or_urls]
elif isinstance(image_url_or_urls, str):
response = requests.get(image_url_or_urls, stream=True, headers=headers)
response.raise_for_status()
return Image.open(BytesIO(response.content))
else:
raise ValueError(f"only a single or a list of entries is supported but got type={type(image_url_or_urls)}")
class BaseImageProcessor(ImageProcessingMixin):
def __init__(self, **kwargs):
super().__init__(**kwargs)
def __call__(self, images, **kwargs) -> BatchFeature:
"""Preprocess an image or a batch of images."""
return self.preprocess(images, **kwargs)
def preprocess(self, images, **kwargs) -> BatchFeature:
raise NotImplementedError("Each image processor must implement its own preprocess method")
def rescale(
self,
image: np.ndarray,
scale: float,
data_format: Optional[Union[str, ChannelDimension]] = None,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
) -> np.ndarray:
"""
Rescale an image by a scale factor. image = image * scale.
Args:
image (`np.ndarray`):
Image to rescale.
scale (`float`):
The scaling factor to rescale pixel values by.
data_format (`str` or `ChannelDimension`, *optional*):
The channel dimension format for the output image. If unset, the channel dimension format of the input
image is used. 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.
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.
Returns:
`np.ndarray`: The rescaled image.
"""
return rescale(image, scale=scale, data_format=data_format, input_data_format=input_data_format, **kwargs)
def normalize(
self,
image: np.ndarray,
mean: Union[float, Iterable[float]],
std: Union[float, Iterable[float]],
data_format: Optional[Union[str, ChannelDimension]] = None,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
) -> np.ndarray:
"""
Normalize an image. image = (image - image_mean) / image_std.
Args:
image (`np.ndarray`):
Image to normalize.
mean (`float` or `Iterable[float]`):
Image mean to use for normalization.
std (`float` or `Iterable[float]`):
Image standard deviation to use for normalization.
data_format (`str` or `ChannelDimension`, *optional*):
The channel dimension format for the output image. If unset, the channel dimension format of the input
image is used. 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.
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.
Returns:
`np.ndarray`: The normalized image.
"""
return normalize(
image, mean=mean, std=std, data_format=data_format, input_data_format=input_data_format, **kwargs
)
def center_crop(
self,
image: np.ndarray,
size: Dict[str, int],
data_format: Optional[Union[str, ChannelDimension]] = None,
input_data_format: Optional[Union[str, ChannelDimension]] = None,
**kwargs,
) -> np.ndarray:
"""
Center crop an image to `(size["height"], size["width"])`. If the input size is smaller than `crop_size` along
any edge, the image is padded with 0's and then center cropped.
Args:
image (`np.ndarray`):
Image to center crop.
size (`Dict[str, int]`):
Size of the output image.
data_format (`str` or `ChannelDimension`, *optional*):
The channel dimension format for the output image. If unset, the channel dimension format of the input
image is used. 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.
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.
"""
size = get_size_dict(size)
if "height" not in size or "width" not in size:
raise ValueError(f"The size dictionary must have keys 'height' and 'width'. Got {size.keys()}")
return center_crop(
image,
size=(size["height"], size["width"]),
data_format=data_format,
input_data_format=input_data_format,
**kwargs,
)
VALID_SIZE_DICT_KEYS = ({"height", "width"}, {"shortest_edge"}, {"shortest_edge", "longest_edge"}, {"longest_edge"})
def is_valid_size_dict(size_dict):
if not isinstance(size_dict, dict):
return False
size_dict_keys = set(size_dict.keys())
for allowed_keys in VALID_SIZE_DICT_KEYS:
if size_dict_keys == allowed_keys:
return True
return False
def convert_to_size_dict(
size, max_size: Optional[int] = None, default_to_square: bool = True, height_width_order: bool = True
):
# By default, if size is an int we assume it represents a tuple of (size, size).
if isinstance(size, int) and default_to_square:
if max_size is not None:
raise ValueError("Cannot specify both size as an int, with default_to_square=True and max_size")
return {"height": size, "width": size}
# In other configs, if size is an int and default_to_square is False, size represents the length of
# the shortest edge after resizing.
elif isinstance(size, int) and not default_to_square:
size_dict = {"shortest_edge": size}
if max_size is not None:
size_dict["longest_edge"] = max_size
return size_dict
# Otherwise, if size is a tuple it's either (height, width) or (width, height)
elif isinstance(size, (tuple, list)) and height_width_order:
return {"height": size[0], "width": size[1]}
elif isinstance(size, (tuple, list)) and not height_width_order:
return {"height": size[1], "width": size[0]}
elif size is None and max_size is not None:
if default_to_square:
raise ValueError("Cannot specify both default_to_square=True and max_size")
return {"longest_edge": max_size}
raise ValueError(f"Could not convert size input to size dict: {size}")
def get_size_dict(
size: Union[int, Iterable[int], Dict[str, int]] = None,
max_size: Optional[int] = None,
height_width_order: bool = True,
default_to_square: bool = True,
param_name="size",
) -> dict:
"""
Converts the old size parameter in the config into the new dict expected in the config. This is to ensure backwards
compatibility with the old image processor configs and removes ambiguity over whether the tuple is in (height,
width) or (width, height) format.
- If `size` is tuple, it is converted to `{"height": size[0], "width": size[1]}` or `{"height": size[1], "width":
size[0]}` if `height_width_order` is `False`.
- If `size` is an int, and `default_to_square` is `True`, it is converted to `{"height": size, "width": size}`.
- If `size` is an int and `default_to_square` is False, it is converted to `{"shortest_edge": size}`. If `max_size`
is set, it is added to the dict as `{"longest_edge": max_size}`.
Args:
size (`Union[int, Iterable[int], Dict[str, int]]`, *optional*):
The `size` parameter to be cast into a size dictionary.
max_size (`Optional[int]`, *optional*):
The `max_size` parameter to be cast into a size dictionary.
height_width_order (`bool`, *optional*, defaults to `True`):
If `size` is a tuple, whether it's in (height, width) or (width, height) order.
default_to_square (`bool`, *optional*, defaults to `True`):
If `size` is an int, whether to default to a square image or not.
"""
if not isinstance(size, dict):
size_dict = convert_to_size_dict(size, max_size, default_to_square, height_width_order)
logger.info(
f"{param_name} should be a dictionary on of the following set of keys: {VALID_SIZE_DICT_KEYS}, got {size}."
f" Converted to {size_dict}.",
)
else:
size_dict = size
if not is_valid_size_dict(size_dict):
raise ValueError(
f"{param_name} must have one of the following set of keys: {VALID_SIZE_DICT_KEYS}, got {size_dict.keys()}"
)
return size_dict
ImageProcessingMixin.push_to_hub = copy_func(ImageProcessingMixin.push_to_hub)
if ImageProcessingMixin.push_to_hub.__doc__ is not None:
ImageProcessingMixin.push_to_hub.__doc__ = ImageProcessingMixin.push_to_hub.__doc__.format(
object="image processor", object_class="AutoImageProcessor", object_files="image processor file"
)
|