o
Zh @ s& U d Z ddlZddlZddlZddlZddlmZ ddlmZm Z m
Z
m Z m Z ddl
mZ ddlmZmZ ddlmZ dd lmZ dd
lmZmZmZmZmZm Z m Z m Z dd l m Z d d
l!m"Z" d dl#m$Z$m%Z%m&Z&m'Z' e (e)Z*ere Z+ee,e e
e, e
e, f f e-d< neg dZ+e+. D ]%\Z/Z0e0^Z1Z2e sdZ1e2re2d du se sdZ2ne2d Z2e1e2fe+e/< qe"e$e+Z3de,fddZ4 d&de e,ej5f de
e e,ej5f de6de
e6 de
e e,e,f de
e e6e,f de
e, d e6fd d Z7d d Z8e d!d"G d#d$ d$Z9d%d$gZ:dS )'zAutoImageProcessor class. N) OrderedDict)
TYPE_CHECKINGDictOptionalTupleUnion )PretrainedConfig) get_class_from_dynamic_moduleresolve_trust_remote_code)ImageProcessingMixin)BaseImageProcessorFast) CONFIG_NAMEIMAGE_PROCESSOR_NAME cached_fileis_timm_config_dictis_timm_local_checkpointis_torchvision_availableis_vision_availablelogging)requires )_LazyAutoMapping)CONFIG_MAPPING_NAMES
AutoConfigmodel_type_to_module_name!replace_list_option_in_docstrings IMAGE_PROCESSOR_MAPPING_NAMES)s)alignZEfficientNetImageProcessorZ EfficientNetImageProcessorFast)ZariaZAriaImageProcessor)ZbeitZBeitImageProcessorZBeitImageProcessorFast)bitZBitImageProcessorZBitImageProcessorFast)ZblipZBlipImageProcessorZBlipImageProcessorFast)zblip-2r# )Z bridgetower)ZBridgeTowerImageProcessorZ BridgeTowerImageProcessorFast)Z chameleon)ZChameleonImageProcessor)Z chinese_clip)ZChineseCLIPImageProcessorZ ChineseCLIPImageProcessorFast)ZclipZCLIPImageProcessorZCLIPImageProcessorFast)ZclipsegZViTImageProcessorZViTImageProcessorFast)Zconditional_detr)Z ConditionalDetrImageProcessorZ!ConditionalDetrImageProcessorFast)ZconvnextZConvNextImageProcessorZConvNextImageProcessorFast)Z
convnextv2r& )cvtr& )zdata2vec-visionr )Zdeformable_detr)Z DeformableDetrImageProcessorZ DeformableDetrImageProcessorFast)Zdeit)ZDeiTImageProcessorZDeiTImageProcessorFast)Zdepth_anythingZDPTImageProcessor)Z depth_pro)ZDepthProImageProcessorZDepthProImageProcessorFast)Zdeta)ZDetaImageProcessor)Zdetr)DetrImageProcessorZDetrImageProcessorFast)Zdinatr% )Zdinov2r" )z
donut-swin)ZDonutImageProcessorZDonutImageProcessorFast)Zdptr( )Zefficientformer)Z EfficientFormerImageProcessor)Z efficientnetr )Zflava)ZFlavaImageProcessorZFlavaImageProcessorFast)Zfocalnetr" )Zfuyu)ZFuyuImageProcessor)Zgemma3ZGemma3ImageProcessorZGemma3ImageProcessorFast)gitr$ )Zglpn)ZGLPNImageProcessor)Zgot_ocr2)ZGotOcr2ImageProcessorZGotOcr2ImageProcessorFast)zgrounding-dino)ZGroundingDinoImageProcessorZ GroundingDinoImageProcessorFast)Zgroupvitr$ )Zhierar" )Zidefics)ZIdeficsImageProcessor)Zidefics2)ZIdefics2ImageProcessor)Zidefics3)ZIdefics3ImageProcessor)Zijepar% )Zimagegpt)ZImageGPTImageProcessor)Z instructblipr# )Zinstructblipvideo)Z InstructBlipVideoImageProcessor)ZjanusZJanusImageProcessor)zkosmos-2r$ )Z
layoutlmv2)ZLayoutLMv2ImageProcessorZ LayoutLMv2ImageProcessorFast)Z
layoutlmv3ZLayoutLMv3ImageProcessorZ LayoutLMv3ImageProcessorFast)Zlevit)ZLevitImageProcessorZLevitImageProcessorFast)Zllama4)ZLlama4ImageProcessorZLlama4ImageProcessorFast)Zllava)ZLlavaImageProcessorZLlavaImageProcessorFast)Z
llava_next)ZLlavaNextImageProcessorZLlavaNextImageProcessorFast)Zllava_next_video)Z LlavaNextVideoImageProcessor)Zllava_onevision)Z LlavaOnevisionImageProcessorZ LlavaOnevisionImageProcessorFast)Z mask2former)ZMask2FormerImageProcessor)Z
maskformer)ZMaskFormerImageProcessor)zmgp-strr% )Zmistral3ZPixtralImageProcessorZPixtralImageProcessorFast)Zmlcdr$ )Zmllama)ZMllamaImageProcessor)Z mobilenet_v1)ZMobileNetV1ImageProcessorZ MobileNetV1ImageProcessorFast)Z mobilenet_v2)ZMobileNetV2ImageProcessorZ MobileNetV2ImageProcessorFast)Z mobilevitZMobileViTImageProcessor)Z mobilevitv2r. )Znatr% )Znougat)ZNougatImageProcessor)Z oneformer)ZOneFormerImageProcessor)Zowlv2)ZOwlv2ImageProcessor)Zowlvit)ZOwlViTImageProcessorZOwlViTImageProcessorFast)Z paligemmaZSiglipImageProcessorZSiglipImageProcessorFast)Z perceiver)ZPerceiverImageProcessorZPerceiverImageProcessorFast)Zphi4_multimodal)Z Phi4MultimodalImageProcessorFast)Z
pix2struct)ZPix2StructImageProcessor)Zpixtralr- )Z
poolformer)ZPoolFormerImageProcessorZ PoolFormerImageProcessorFast)Zprompt_depth_anything)Z!PromptDepthAnythingImageProcessor)ZpvtZPvtImageProcessorZPvtImageProcessorFast)Zpvt_v2r0 )Z
qwen2_5_vlZQwen2VLImageProcessorZQwen2VLImageProcessorFast)Zqwen2_vlr1 )Zregnetr& )Zresnetr& )Zrt_detr)ZRTDetrImageProcessorZRTDetrImageProcessorFast)ZsamZSamImageProcessor)Zsam_hqr2 )Z segformerZSegformerImageProcessor)Zseggpt)ZSegGptImageProcessor)Z shieldgemma2r* )Zsiglipr/ )Zsiglip2)ZSiglip2ImageProcessorZSiglip2ImageProcessorFast)Z superglue)ZSuperGlueImageProcessor)Z swiftformerr% )Zswinr% )Zswin2sr)ZSwin2SRImageProcessorZSwin2SRImageProcessorFast)Zswinv2r% )ztable-transformer)r) )Z timesformerZVideoMAEImageProcessor)Z timm_wrapper)ZTimmWrapperImageProcessor)Ztvlt)ZTvltImageProcessor)Ztvp)ZTvpImageProcessor)Zudopr, )Zupernetr3 )Zvanr& )Zvideomaer4 )Zvilt)ZViltImageProcessorZViltImageProcessorFast)Zvipllavar$ )Zvitr% )Z
vit_hybrid)ZViTHybridImageProcessor)Zvit_maer% )Zvit_msnr% )Zvitmatte)ZVitMatteImageProcessorZVitMatteImageProcessorFast)Zxclipr$ )Zyolos)ZYolosImageProcessorZYolosImageProcessorFast)Zzoedepth)ZZoeDepthImageProcessor
class_namec C s | dkrt S t D ]'\}}| |v r1t|}td| d}zt|| W S ty0 Y q
w q
tj D ]\}}|D ]}t|dd | krM| S q=q7td}t
|| r^t|| S d S )Nr
.ztransformers.models__name__Z transformers) r
r itemsr importlib
import_modulegetattrAttributeErrorIMAGE_PROCESSOR_MAPPING_extra_contenthasattr)r5 module_nameZ
extractorsmodule_Z extractorZ main_module rC ]/var/www/auris/lib/python3.10/site-packages/transformers/models/auto/image_processing_auto.py#get_image_processor_class_from_name s,
rE F pretrained_model_name_or_path cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_onlyc K s | dd} | durtdt |durtd| }t| t|||||||dddd }
|
du r5td i S t |
dd
} t
| W d S 1 sKw Y dS )
a
Loads the image processor configuration from a pretrained model image processor configuration.
Args:
pretrained_model_name_or_path (`str` or `os.PathLike`):
This can be either:
- a string, the *model id* of a pretrained model configuration hosted inside a model repo on
huggingface.co.
- a path to a *directory* containing a configuration file saved using the
[`~PreTrainedTokenizer.save_pretrained`] method, e.g., `./my_model_directory/`.
cache_dir (`str` or `os.PathLike`, *optional*):
Path to a directory in which a downloaded pretrained model configuration 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 configuration files and override the cached versions if they
exist.
resume_download:
Deprecated and ignored. All downloads are now resumed by default when possible.
Will be removed in v5 of Transformers.
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`, 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.
local_files_only (`bool`, *optional*, defaults to `False`):
If `True`, will only try to load the image processor configuration from local files.
Passing `token=True` is required when you want to use a private model.
Returns:
`Dict`: The configuration of the image processor.
Examples:
```python
# Download configuration from huggingface.co and cache.
image_processor_config = get_image_processor_config("google-bert/bert-base-uncased")
# This model does not have a image processor config so the result will be an empty dict.
image_processor_config = get_image_processor_config("FacebookAI/xlm-roberta-base")
# Save a pretrained image processor locally and you can reload its config
from transformers import AutoTokenizer
image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k")
image_processor.save_pretrained("image-processor-test")
image_processor_config = get_image_processor_config("image-processor-test")
```use_auth_tokenNrThe `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.V`token` and `use_auth_token` are both specified. Please set only the argument `token`.F)
rG rH rI rJ rK rL rM Z _raise_exceptions_for_gated_repoZ%_raise_exceptions_for_missing_entriesZ'_raise_exceptions_for_connection_errorszbCould not locate the image processor configuration file, will try to use the model config instead.zutf-8)encoding) popwarningswarn
FutureWarning
ValueErrorr r loggerinfoopenjsonload) rF rG rH rI rJ rK rL rM kwargsrN Zresolved_config_filereaderrC rC rD get_image_processor_config s> E$r^ c C s t d| d d S )NzFast image processor class zz is available for this model. Using slow image processor class. To use the fast image processor class set `use_fast=True`.)rW warning)Z
fast_classrC rC rD '_warning_fast_image_processor_availableD s
r` )Zvision)backendsc @ sB e Zd ZdZdd Zeeedd Ze d
dd Z
dS ) AutoImageProcessora%
This is a generic image processor class that will be instantiated as one of the image processor classes of the
library when created with the [`AutoImageProcessor.from_pretrained`] class method.
This class cannot be instantiated directly using `__init__()` (throws an error).
c C s t d)NzAutoImageProcessor is designed to be instantiated using the `AutoImageProcessor.from_pretrained(pretrained_model_name_or_path)` method.)EnvironmentError)selfrC rC rD __init__T s zAutoImageProcessor.__init__c O s | dd}|dur tdt |dddur td||d< | dd}| dd}| dd}d |d
< d |v r@| d }n t|rGt}nt}zt j
|fd |i|\} }
W n1 t y } z%zt j
|fd ti|\} }
W n t yx | w t | s| W Y d} ~ nd} ~ ww | d d} d}
d
| di v r| d d
}
| du r|
du r| dd}|dur|
dd} d| di v r| d d }|
dd}
| du r|
du rt|tstj|fd|i|}t|d d} t|drd
|jv r|jd
}
d}| durb|du r| d}|std |r t s td d}|rP| ds-| d7 } t D ] \}
}| |v r< nq1| dd } d}td t| }n| dr\| dd n| } t| }|
du}|duppt |t v }t ||||}|
durt|
t s|
df}
|r|r|s|
d durt |
d |r|
d dur|
d }n|
d }t!||fi |}| dd}
t"j#$|r|% |j&| fi |S |dur|j&| fi |S t |t v r*t t | }|\}}|s|durt | |r|s |du r|j|g|R i |S |dur&|j|g|R i |S td td | d t d t d t d!d"'d#d$ t( D
)%aQ
Instantiate one of the image processor classes of the library from a pretrained model vocabulary.
The image processor class to instantiate is selected based on the `model_type` property of the config object
(either passed as an argument or loaded from `pretrained_model_name_or_path` if possible), or when it's
missing, by falling back to using pattern matching on `pretrained_model_name_or_path`:
List options
Params:
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.
- 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:
Deprecated and ignored. All downloads are now resumed by default when possible.
Will be removed in v5 of Transformers.
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`, 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.
use_fast (`bool`, *optional*, defaults to `False`):
Use a fast torchvision-base image processor if it is supported for a given model.
If a fast image processor is not available for a given model, a normal numpy-based image processor
is returned instead.
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.
trust_remote_code (`bool`, *optional*, defaults to `False`):
Whether or not to allow for custom models defined on the Hub in their own modeling files. This option
should only be set to `True` for repositories you trust and in which you have read the code, as it will
execute code present on the Hub on your local machine.
image_processor_filename (`str`, *optional*, defaults to `"config.json"`):
The name of the file in the model directory to use for the image processor config.
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.
Passing `token=True` is required when you want to use a private model.
Examples:
```python
>>> from transformers import AutoImageProcessor
>>> # Download image processor from huggingface.co and cache.
>>> image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k")
>>> # If image processor files are in a directory (e.g. image processor was saved using *save_pretrained('./test/saved_model/')*)
>>> # image_processor = AutoImageProcessor.from_pretrained("./test/saved_model/")
```rN NrO rK rP configuse_fasttrust_remote_codeTZ
_from_autoimage_processor_filenameimage_processor_typerb auto_mapZfeature_extractor_typeZFeatureExtractorZImageProcessorZAutoFeatureExtractorZFastaC Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.zcUsing `use_fast=True` but `torchvision` is not available. Falling back to the slow image processor.Fzz`use_fast` is set to `True` but the image processor class does not have a fast version. Falling back to the slow version.r r Z
code_revisionzZThis image processor cannot be instantiated. Please make sure you have `Pillow` installed.z Unrecognized image processor in z2. Should have a `image_processor_type` key in its z of z3, or one of the following `model_type` keys in its z: z, c s s | ]}|V qd S )NrC ).0crC rC rD K s z5AutoImageProcessor.from_pretrained..))rR rS rT rU getrV r r r r Zget_image_processor_dict Exceptionr replace
isinstancer r from_pretrainedr; r? rk endswithrW Z warning_oncer r r8 rE typer= r tupler` r
ospathisdirZregister_for_auto_class from_dictjoinkeys)clsrF Zinputsr\ rN rf rg rh ri Z config_dictrB Zinitial_exceptionrj Zimage_processor_auto_mapZfeature_extractor_classZfeature_extractor_auto_mapimage_processor_classimage_processorsZhas_remote_codeZhas_local_codeZ class_refZimage_processor_tupleZimage_processor_class_pyZimage_processor_class_fastrC rC rD rt Z s O
z"AutoImageProcessor.from_pretrainedNFc C s |dur|dur t dtdt |}|du r |du r t d|dur-t|tr-t d|dur:t|ts:t d|durX|durXt|trX|j|krXt d|j d| d | tjv rot| \}}|du ri|}|du ro|}tj | ||f|d
dS ) a)
Register a new image processor for this class.
Args:
config_class ([`PretrainedConfig`]):
The configuration corresponding to the model to register.
image_processor_class ([`ImageProcessingMixin`]): The image processor to register.
NzHCannot specify both image_processor_class and slow_image_processor_classzThe image_processor_class argument is deprecated and will be removed in v4.42. Please use `slow_image_processor_class`, or `fast_image_processor_class` insteadzSYou need to specify either slow_image_processor_class or fast_image_processor_classzIYou passed a fast image processor in as the `slow_image_processor_class`.zNThe `fast_image_processor_class` should inherit from `BaseImageProcessorFast`.zThe fast processor class you are passing has a `slow_image_processor_class` attribute that is not consistent with the slow processor class you passed (fast tokenizer has z and you passed z!. Fix one of those so they match!)exist_ok)
rV rS rT rU
issubclassr
slow_image_processor_classr= r> register)Z config_classr r fast_image_processor_classr Z
existing_slowZ
existing_fastrC rC rD r N sJ
zAutoImageProcessor.register)NNNF) r7
__module__ __qualname____doc__re classmethodr r rt staticmethodr rC rC rC rD rb K s srb r= )NFNNNNF);r r9 rZ rx rS collectionsr typingr r r r r Zconfiguration_utilsr Zdynamic_module_utilsr
r Zimage_processing_utilsr Zimage_processing_utils_fastr
utilsr r r r r r r r Zutils.import_utilsr Z auto_factoryr Zconfiguration_autor r r r Z
get_loggerr7 rW r str__annotations__r8 Z
model_typer r r r= rE PathLikeboolr^ r` rb __all__rC rC rC rD sz (
(x
g @