sgp U d Z ddlZddlZddlZddlZddlmZ ddlmZm Z m
Z
m Z m Z ddl
mZ ddlmZmZ ddlmZmZ dd lmZ dd
lmZmZmZmZm Z m Z d d l m Z d d
l m!Z!m"Z"m#Z#m$Z$ e jJ e& Z'er e Z(ee)e e
e) e
e) f f e*d< n
eg d Z(e(jW D ]/ \ Z,Z-e-^Z.Z/ e sdZ.e/r e/d e sdZ/ne/d Z/e.e/fe(e,< 1 e e!e( Z0de)fdZ1 d de e)ejd f de
e e)ejd f de3de
e3 de
e e)e)f de
e e3e)f de
e) de3fdZ4d Z5 G d d Z6y) zAutoImageProcessor class. N) OrderedDict)
TYPE_CHECKINGDictOptionalTupleUnion )PretrainedConfig) get_class_from_dynamic_moduleresolve_trust_remote_code)BaseImageProcessorImageProcessingMixin)BaseImageProcessorFast) CONFIG_NAMEIMAGE_PROCESSOR_NAMEget_file_from_repois_torchvision_availableis_vision_availablelogging )_LazyAutoMapping)CONFIG_MAPPING_NAMES
AutoConfigmodel_type_to_module_name!replace_list_option_in_docstrings IMAGE_PROCESSOR_MAPPING_NAMES)c)alignEfficientNetImageProcessor)beitBeitImageProcessor)bitBitImageProcessor)blipBlipImageProcessor)zblip-2r' ) bridgetower)BridgeTowerImageProcessor) chameleon)ChameleonImageProcessor) chinese_clip)ChineseCLIPImageProcessor)clipCLIPImageProcessor)clipsegViTImageProcessorViTImageProcessorFast)conditional_detr) ConditionalDetrImageProcessor)convnextConvNextImageProcessor)
convnextv2r9 )cvtr9 )zdata2vec-visionr! )deformable_detr) DeformableDetrImageProcessor DeformableDetrImageProcessorFast)deit)DeiTImageProcessor)depth_anythingDPTImageProcessor)deta)DetaImageProcessor)detr)DetrImageProcessorDetrImageProcessorFast)dinatr3 )dinov2r$ )z
donut-swin)DonutImageProcessor)dptrC )efficientformer) EfficientFormerImageProcessor) efficientnetr )flava)FlavaImageProcessor)focalnetr$ )fuyu)FuyuImageProcessor)gitr0 )glpn)GLPNImageProcessor)zgrounding-dino)GroundingDinoImageProcessor)groupvitr0 )hierar$ )idefics)IdeficsImageProcessor)idefics2)Idefics2ImageProcessor)idefics3)Idefics3ImageProcessor)ijepar3 )imagegpt)ImageGPTImageProcessor) instructblipr' )instructblipvideo) InstructBlipVideoImageProcessor)zkosmos-2r0 )
layoutlmv2)LayoutLMv2ImageProcessor)
layoutlmv3LayoutLMv3ImageProcessor)levit)LevitImageProcessor)llavar0 )
llava_next)LlavaNextImageProcessor)llava_next_video) LlavaNextVideoImageProcessor)llava_onevision) LlavaOnevisionImageProcessor) mask2former)Mask2FormerImageProcessor)
maskformer)MaskFormerImageProcessor)zmgp-strr3 )mllama)MllamaImageProcessor) mobilenet_v1)MobileNetV1ImageProcessor) mobilenet_v2)MobileNetV2ImageProcessor) mobilevitMobileViTImageProcessor) mobilevitv2r )natr3 )nougat)NougatImageProcessor) oneformer)OneFormerImageProcessor)owlv2)Owlv2ImageProcessor)owlvit)OwlViTImageProcessor) paligemmaSiglipImageProcessor) perceiver)PerceiverImageProcessor)
pix2struct)Pix2StructImageProcessor)pixtral)PixtralImageProcessorPixtralImageProcessorFast)
poolformer)PoolFormerImageProcessor)pvtPvtImageProcessor)pvt_v2r )qwen2_vl)Qwen2VLImageProcessor)regnetr9 )resnetr9 )rt_detr)RTDetrImageProcessorRTDetrImageProcessorFast)sam)SamImageProcessor) segformerSegformerImageProcessor)seggpt)SegGptImageProcessor)siglipr ) swiftformerr3 )swinr3 )swin2sr)Swin2SRImageProcessor)swinv2r3 )ztable-transformer)rH ) timesformerVideoMAEImageProcessor)tvlt)TvltImageProcessor)tvp)TvpImageProcessor)udoprk )upernetr )vanr9 )videomaer )vilt)ViltImageProcessor)vipllavar0 )vitr3 )
vit_hybrid)ViTHybridImageProcessor)vit_maer3 )vit_msnr3 )vitmatte)VitMatteImageProcessor)xclipr0 )yolos)YolosImageProcessor)zoedepth)ZoeDepthImageProcessor
class_namec | dk( rt S t j D ]< \ }}| |v s t | }t j
d| d } t
|| c S t j j D ]" \ }}|D ] }t
|dd | k( s|c c S $ t j
d }t || r t
|| S y # t $ r Y w xY w)Nr .ztransformers.models__name__ transformers) r r itemsr importlib
import_modulegetattrAttributeErrorIMAGE_PROCESSOR_MAPPING_extra_contenthasattr)r module_name
extractorsmodule_ extractor main_modules a/var/www/html/venv/lib/python3.12/site-packages/transformers/models/auto/image_processing_auto.py image_processor_class_from_namer s --%%#@#F#F#H Z #3K@K ,,q
->@UVF
vz22
1??EEG !
:# !Iy*d3zA !! )).9K{J'{J// "
s C C C pretrained_model_name_or_path cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_onlyc N |j dd } | )t j dt | t d | }t | t ||||||| }
|
t j d i S t |
d 5 } t j | cddd S # 1 sw Y yxY w) 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`.)r r r r r r r zbCould not locate the image processor configuration file, will try to use the model config instead.zutf-8)encoding) popwarningswarn
FutureWarning
ValueErrorr r loggerinfoopenjsonload) r r r r r r r r kwargsr resolved_config_filereaders r get_image_processor_configr s J ZZ 0$7N!
A
uv v -% %')
# p
"W 5 !yy ! ! !s <BB$c 6 t j d| d y )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 r '_warning_fast_image_processor_availabler . s!
NN
%j\ 2g g c V e Zd ZdZd Ze ee d Ze dd Z
y)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.)EnvironmentError)selfs r __init__zAutoImageProcessor.__init__= s
d
r c |j dd }||1|r|
j! d s|
dz
}
n|s|
j! d r|
dd }
t# |
}
| du}|
duxs t% | t& v }t) |||| }| t | t* s| df} |r|r|s| d t- | d |r | d | d }n| d }t/ ||fi |}
|j dd } t0 j2 j5 | r|
j7 |
j8 |fi |S |
|
j8 |fi |S t% | t& v ret& t% | }|\ }}|s
| t- | |r|s| |j |g|i |S | |j |g|i |S t d t d| dt: dt< dt< d d j? d t@ jC D
) a
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 tokenizer 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.
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/")
```r Nr r r configuse_fasttrust_remote_codeT
_from_autoimage_processor_typer auto_mapfeature_extractor_typeFeatureExtractorImageProcessorAutoFeatureExtractorFastr r
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 | ] }| y w)N ).0cs r z5AutoImageProcessor.from_pretrained.. s @qq@qs )"r r r r getr r get_image_processor_dictreplace
isinstancer
r from_pretrainedr r r endswithr typer r tupler r ospathisdirregister_for_auto_class from_dictr r joinr keys)clsr inputsr r r r r config_dictr image_processor_classimage_processor_auto_mapfeature_extractor_classfeature_extractor_auto_maphas_remote_codehas_local_code class_refimage_processor_tupleimage_processor_class_pyimage_processor_class_fasts r r z"AutoImageProcessor.from_pretrainedC s; Z $4d; % MM E
zz'4(4 l -F7OHd+::j$/ "JJ':D A #| -FFGdohno Q +0F M #' ;??:r#B B'2:'>?S'T $ ! (-E-M&1oo6NPT&U #&2(?(G(GHZ\l(m%% R)HH-8-DE[-\*+E+M+MN`br+s( ! (-E-M f&67#331&7 %,F4JD$Q !vz*/Cv/V+1??;O+P( ,#$9$B$B6$J)V3)!&;&D&DV&L,A#2,F)$CDY$Z !2$>.d:ed6lNe>e 5 rS s # > > 4 \ N A +
H % \g[h!;sE(3-RU :V4W/W#Xh$/d
f%!P %B$G$G$I i J >N; !; %)" &)CA)F)NVnVp%)"%?%B"1KMg0h!*- i ++?A^_ < 48 &*(,(, " "a!#(bkk)9#:a!c2;; ./0a! a! d^ a!
d38n
% a! E$)$ %
a! sma! a!H{
{
r