`i $ U d Z ddlZddlZddlZddlZddlmZ ddlmZm Z m
Z
ddl m Z ddl
mZmZ ddlmZ dd lmZ dd
lmZmZmZmZmZmZmZm Z dd l m Z d d
l m Z d dl!m"Z"m#Z#m$Z$m%Z% e j& e' Z(dgZ)er, e Z*ee+e,e e+ e e+ f f e-d< n
eg d Z*e*. D ]'\ Z/\ Z0Z1 e sdZ0 e sdZ1e0e1fe*e/< ( e e"e* Z2de+fdZ3 d$de
e+ej4 f de e
e+ej4 f de5de e5 de e6e+e+f de e
e5e+f de e+ d e5fd Z7d Z8 e d G d! d" Z9d#d"gZ:dS )%zAutoImageProcessor class. N) OrderedDict)
TYPE_CHECKINGOptionalUnion )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_docstringsQwen2VLImageProcessor IMAGE_PROCESSOR_MAPPING_NAMES))aimv2CLIPImageProcessorCLIPImageProcessorFast)aimv2_vision_modelr )alignEfficientNetImageProcessor EfficientNetImageProcessorFast)aria)AriaImageProcessorN)beitBeitImageProcessorBeitImageProcessorFast)bitBitImageProcessorBitImageProcessorFast)blipBlipImageProcessorBlipImageProcessorFast)zblip-2r2 ) bridgetower)BridgeTowerImageProcessor BridgeTowerImageProcessorFast) chameleon)ChameleonImageProcessorChameleonImageProcessorFast) chinese_clip)ChineseCLIPImageProcessor ChineseCLIPImageProcessorFast)clipr )clipsegViTImageProcessorViTImageProcessorFast)cohere2_vision)N Cohere2VisionImageProcessorFast)conditional_detr) ConditionalDetrImageProcessor!ConditionalDetrImageProcessorFast)convnextConvNextImageProcessorConvNextImageProcessorFast)
convnextv2rI )cvtrI )zdata2vec-visionr* ) deepseek_vl)DeepseekVLImageProcessor DeepseekVLImageProcessorFast)deepseek_vl_hybrid) DeepseekVLHybridImageProcessor"DeepseekVLHybridImageProcessorFast)deformable_detr) DeformableDetrImageProcessor DeformableDetrImageProcessorFast)deit)DeiTImageProcessorDeiTImageProcessorFast)depth_anythingDPTImageProcessorDPTImageProcessorFast) depth_pro)DepthProImageProcessorDepthProImageProcessorFast)deta)DetaImageProcessorN)detrDetrImageProcessorDetrImageProcessorFast)dinatr@ )dinov2r. )
dinov3_vit)NDINOv3ViTImageProcessorFast)z
donut-swin)DonutImageProcessorDonutImageProcessorFast)dptr[ )edgetamNSam2ImageProcessorFast)efficientformer) EfficientFormerImageProcessorN)efficientloftr) EfficientLoFTRImageProcessor EfficientLoFTRImageProcessorFast) efficientnetr$ )eomt)EomtImageProcessorEomtImageProcessorFast)flava)FlavaImageProcessorFlavaImageProcessorFast)focalnetr. )fuyu)FuyuImageProcessorN)gemma3Gemma3ImageProcessorGemma3ImageProcessorFast)gemma3nSiglipImageProcessorSiglipImageProcessorFast)gitr )glm4v)Glm4vImageProcessorGlm4vImageProcessorFast)glpn)GLPNImageProcessorN)got_ocr2)GotOcr2ImageProcessorGotOcr2ImageProcessorFast)zgrounding-dinoGroundingDinoImageProcessor GroundingDinoImageProcessorFast)groupvitr )hierar. )idefics)IdeficsImageProcessorN)idefics2)Idefics2ImageProcessorIdefics2ImageProcessorFast)idefics3)Idefics3ImageProcessorIdefics3ImageProcessorFast)ijepar@ )imagegpt)ImageGPTImageProcessorImageGPTImageProcessorFast) instructblipr2 )instructblipvideo) InstructBlipVideoImageProcessorN)janus)JanusImageProcessorJanusImageProcessorFast)zkosmos-2r )z
kosmos-2.5)Kosmos2_5ImageProcessorKosmos2_5ImageProcessorFast)
layoutlmv2)LayoutLMv2ImageProcessor LayoutLMv2ImageProcessorFast)
layoutlmv3LayoutLMv3ImageProcessor LayoutLMv3ImageProcessorFast)levit)LevitImageProcessorLevitImageProcessorFast)lfm2_vl)NLfm2VlImageProcessorFast) lightglue)LightGlueImageProcessorN)llama4)Llama4ImageProcessorLlama4ImageProcessorFast)llava)LlavaImageProcessorLlavaImageProcessorFast)
llava_next)LlavaNextImageProcessorLlavaNextImageProcessorFast)llava_next_video) LlavaNextVideoImageProcessorN)llava_onevision) LlavaOnevisionImageProcessor LlavaOnevisionImageProcessorFast) mask2former)Mask2FormerImageProcessor Mask2FormerImageProcessorFast)
maskformer)MaskFormerImageProcessor MaskFormerImageProcessorFast)
metaclip_2r )zmgp-strr@ )mistral3PixtralImageProcessorPixtralImageProcessorFast)mlcdr )mllama)MllamaImageProcessorN)zmm-grounding-dinor ) mobilenet_v1)MobileNetV1ImageProcessor MobileNetV1ImageProcessorFast) mobilenet_v2)MobileNetV2ImageProcessor MobileNetV2ImageProcessorFast) mobilevitMobileViTImageProcessorMobileViTImageProcessorFast) mobilevitv2r )natr@ )nougat)NougatImageProcessorNougatImageProcessorFast) oneformer)OneFormerImageProcessorOneFormerImageProcessorFast)ovis2)Ovis2ImageProcessorOvis2ImageProcessorFast)owlv2)Owlv2ImageProcessorOwlv2ImageProcessorFast)owlvit)OwlViTImageProcessorOwlViTImageProcessorFast) paligemmar ) perceiver)PerceiverImageProcessorPerceiverImageProcessorFast)
perception_lm)N PerceptionLMImageProcessorFast)phi4_multimodal)N Phi4MultimodalImageProcessorFast)
pix2struct)Pix2StructImageProcessorN)pixtralr )
poolformer)PoolFormerImageProcessor PoolFormerImageProcessorFast)prompt_depth_anything)!PromptDepthAnythingImageProcessor%PromptDepthAnythingImageProcessorFast)pvtPvtImageProcessorPvtImageProcessorFast)pvt_v2r )
qwen2_5_vlr Qwen2VLImageProcessorFast)qwen2_vlr )qwen3_vlr )regnetrI )resnetrI )rt_detr)RTDetrImageProcessorRTDetrImageProcessorFast)samSamImageProcessorSamImageProcessorFast)sam2ro )sam_hqr ) segformerSegformerImageProcessorSegformerImageProcessorFast)seggpt)SegGptImageProcessorN) shieldgemma2r )siglipr )siglip2)Siglip2ImageProcessorSiglip2ImageProcessorFast)smolvlm)SmolVLMImageProcessorSmolVLMImageProcessorFast) superglue)SuperGlueImageProcessorN)
superpoint)SuperPointImageProcessor SuperPointImageProcessorFast) swiftformerr@ )swinr@ )swin2sr)Swin2SRImageProcessorSwin2SRImageProcessorFast)swinv2r@ )ztable-transformerrd )textnet)TextNetImageProcessorTextNetImageProcessorFast) timesformerVideoMAEImageProcessorN) timm_wrapper)TimmWrapperImageProcessorN)tvlt)TvltImageProcessorN)tvp)TvpImageProcessorTvpImageProcessorFast)udopr )upernetr )vanrI )videomaer2 )vilt)ViltImageProcessorViltImageProcessorFast)vipllavar )vitr@ )
vit_hybrid)ViTHybridImageProcessorN)vit_maer@ )vit_msnr@ )vitmatte)VitMatteImageProcessorVitMatteImageProcessorFast)xclipr )yolos)YolosImageProcessorYolosImageProcessorFast)zoedepth)ZoeDepthImageProcessorZoeDepthImageProcessorFast
class_namec | dk rt S t D ]S\ }}| |v rJt | }t j d| d } t
|| c S # t $ r Y Ow xY wTt j
D ]"}|D ] }t
|dd | k r|c c S #t j d }t || rt
|| S d S )Nr .ztransformers.models__name__ transformers) r r itemsr importlib
import_modulegetattrAttributeErrorIMAGE_PROCESSOR_MAPPING_extra_contentvalueshasattr)rR module_name
extractorsmodule extractor main_modules /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/auto/image_processing_auto.py#get_image_processor_class_from_namerf sD ---%%#@#F#F#H#H Z # #3K@@K ,->->->@UVVF
vz22222!
$ .<CCEE ! !
# ! !Iy*d33zAA B ! ).99K{J'' 0{J/// 4s A**
A76A7F pretrained_model_name_or_path cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_onlyc | dd } | -t j dt |t d | }t | t |||||||ddd }
|
t d i S t |
d 5 } t j | cddd S # 1 swxY w 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 `hf auth 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)
rh ri rj rk rl rm rn _raise_exceptions_for_gated_repo%_raise_exceptions_for_missing_entries'_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) rg rh ri rj rk rl rm rn kwargsrp resolved_config_filereaders re get_image_processor_configr s; J ZZ 0$77N!
A
uvv v &% %'))..305
# p
"W 5 5 5 !y ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! !s B66B:=B:c B 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`.)r| warning)
fast_classs re '_warning_fast_image_processor_availabler Z s<
NN gj g g g )vision)backendsc p e Zd ZdZd Ze ee d Ze 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 t d )NzAutoImageProcessor is designed to be instantiated using the `AutoImageProcessor.from_pretrained(pretrained_model_name_or_path)` method.)OSError)selfs re __init__zAutoImageProcessor.__init__j s
d
r c v | dd }|Ct j dt | d t d ||d< | dd }| dd }| dd }d |d
< d |v r| d }n t
| rt }nt } t j
|fd |i|\ } }
nV# t $ rI} t j
|fd t i|\ } }
n# t $ r | w xY wt | s| Y d} ~ nd} ~ ww xY w| d d } d}
d
| di v r| d d
}
| l|
j| dd }||
dd } d| di v r$| d d }|
dd }
| b|
`t |t st! j |fd|i|}t% |d d } t' |d rd
|j v r
|j d
}
d}| |j| d }|s7| t, v r.t/ r d }t0 d| d |st0 d |r| d s| dz
} |rVt/ sHt5 | dd }|t d| d t0 d d}|rXt6 D ]}| |v r n' | dd } d}t0 d t5 | }nN| d }t5 | }|(| d rt d| d |
du}|dupt= | t> v }|rk|
t |
t@ s|
df}
|r|
d |
d }n|
d }d |v r |! d d }nd}tE ||||| }|rg|re|s |
d tG |
d tI ||fi |}| d!d }
|% |j& | fi |S | |j& | fi |S t= | t> v rkt> t= | }|\ }}|s|tG | |r|s| |j |g|R i |S | |j |g|R i |S t d" t d#| d$t d%t d&t d'd(' d) t6 D
)*aI
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 `hf auth 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/")
```rp Nrq rl rr configuse_fasttrust_remote_codeT
_from_autoimage_processor_filenameimage_processor_typer auto_mapfeature_extractor_typeFeatureExtractorImageProcessorAutoFeatureExtractorFastz The image processor of type `aS ` is now loaded as a fast processor by default, even if the model checkpoint was saved with a slow processor. This is a breaking change and may produce slightly different outputs. To continue using the slow processor, instantiate this class with `use_fast=False`. Note that this behavior will be extended to all models in a future release.aC 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`.`zU` requires `torchvision` to be installed. Please install `torchvision` and try again.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.z\` does not have a slow version. Please set `use_fast=True` when instantiating the processor.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 3 K | ]}|V d S )N ).0cs re z5AutoImageProcessor.from_pretrained..q s" @j@jq@j@j@j@j@j@jr )(rw rx ry rz getr{ r r
r r get_image_processor_dict Exceptionr replace
isinstancer r from_pretrainedrZ r_ r endswithFORCE_FAST_IMAGE_PROCESSORr r| warning_oncerf r r^ removesuffixtyper\ tuplesplitr
r r register_for_auto_class from_dictjoin)clsrg inputsr rp r r r r config_dict_initial_exceptionr image_processor_auto_mapfeature_extractor_classfeature_extractor_auto_mapimage_processor_classimage_processorsimage_processor_type_slowhas_remote_codehas_local_code class_ref
upstream_repoimage_processor_tupleimage_processor_class_pyimage_processor_class_fasts re r z"AutoImageProcessor.from_pretrainedp s= ^ $4d;; % M E
zz'"". l -F7OHd++::j$// "JJ':D A A #| & / /'-zz2L'M'M $ $
%&C
D
D <'2 $ $'; $ ( 1 J- H` dj NK ( ( (
(!5!N1" "LW"[a" " QQ
(
(
(''
(
'{33
(''
(
(
(
(
( (" +/Et L L #' ;??:r#B#B B B'2:'>?S'T $ ',D,L&1oo6NPT&U&U #&2'>'F'FGY[k'l'l$% R)H)HHH-8-DE[-\*+E+M+MN`br+s+s( ',D,L f&677
#31 &7 $+63I4#P#P vz**
Q/Cv/V/V+1?;O+P( $ + /88@@ $8.d:ed6llNe>e '3JG_af;
;
1 mnn n
' 2*657MNN 7*EIccc !-H! !Zt! ! !
2A A A+B<+P (M=)1-:*)1-:* (( 57QR]e )
r )NNNF) rU
__module__ __qualname____doc__r classmethodr r r staticmethodr r r re r r a s
&&'DEE@
@
FE [@
D ##'#' 8
8
8
\8
8
8
r r r\ )NFNNNNF);r rX r osrx collectionsr typingr r r configuration_utilsr dynamic_module_utilsr r
image_processing_utilsr image_processing_utils_fastr utilsr
r r r r r r r utils.import_utilsr auto_factoryr configuration_autor r r r
get_loggerrU r| r r strr __annotations__rW
model_type
slow_classr r\ rf PathLikebooldictr r r __all__r r re r s # # # # # # 1 1 1 1 1 1 1 1 1 1 4 3 3 3 3 3 \ \ \ \ \ \ \ \ : : : : : : A A A A A A + * * * * * * * * * * *
H % % 6 6 R \g[f[h[h!;sE(3-RU :V4W/W#Xhhhh$/KK
K
K
M% M%!` -J,O,O,Q,Q I I(J(Z
# # % %
1;Z0H!*--**+?A^__ C < 48 &*(,(, " "d! d!#(bk)9#:d!c2; ./0d! d! d^ d!
d38n
% d! E$)$ %
d! smd! d! d! d! d!N
; K
K
K
K
K
K
K
K
\
%&:
;r