+
jP a R t10 t R t^ RIt^ RIt^ RIHt ^ RIHt ^RIH t ^RI
H t H t ^RI
HtHtHtHtHtHtHtHt ^RIHt ^RIHt ^R IHt ^R
I H t ^R I H t H t H!t!H"t" ]PF ! ]$4 t%]' d
]! 4 t ] ^ k M ]! . RO4 t&] PN ! ]&4 ] PP ! 4 F w t)t*]*t+]! 4 ' g Rt+]+] ])& K ]! ] ] 4 t,R R
lt-RR R llt.]! RR7 ! R R4 4 t/RR.t0R# )zAutoVideoProcessor class.N) OrderedDict)
TYPE_CHECKING)PreTrainedConfig) get_class_from_dynamic_moduleresolve_trust_remote_code) CONFIG_NAMEIMAGE_PROCESSOR_NAMEPROCESSOR_NAMEVIDEO_PROCESSOR_NAME cached_fileis_torchvision_availableloggingsafe_load_json_file)requires)BaseVideoProcessor)_LazyAutoMapping) VIDEO_PROCESSOR_MAPPING_NAMES)CONFIG_MAPPING_NAMES
AutoConfigmodel_type_to_module_name!replace_list_option_in_docstringsc $ V ^8 d QhR\ /# )
class_name)str)formats "o/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/auto/video_processing_auto.py __annotate__r U s c \ P ! 4 F> w rW8X g K
\ V4 p\ P ! R V 2R4 p \ W04 u # \ P P 4 F p\ VRR4 V 8X g K Vu # \ P ! R4 p\ W@4 ' d \ W@4 # R# \ d K i ; i).ztransformers.models__name__N transformers) r itemsr importlib
import_modulegetattrAttributeErrorVIDEO_PROCESSOR_MAPPING_extra_contentvalueshasattr)r module_name extractormodule main_modules & r video_processor_class_from_namer0 U s "?"E"E"G "3K@K ,,q
->@UVF
v22
#H -;;BBD 9j$ /: = E )).9K{''{// "
s
C CCc 0 V ^8 d QhR\ \ P , R\ \ P , R, R\ R\ \ \ 3, R, R\ \ , R, R\ R, R\ /# ) r pretrained_model_name_or_path cache_dirNforce_downloadproxiestokenrevisionlocal_files_only)r osPathLikebooldict)r s "r r r m s u& u&#u&R[[ 4'u& u& #s(^d
" u&
#: u& Dj
u& u&r c \ V \ VVVVVVRRR7
p\ \ 3 U u. uF# p \ V V VVVVVVRRRR7 ;p
f K! V
NK% p p V ' d
V ^ , MRp V ' g V' g \ P R4 / # Rp
Ve \
V4 pRV9 d
VR, p
V e V
f \
V 4 p
T
;' g / # u up i )aR
Loads the video processor configuration from a pretrained model video 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
[`~BaseVideoProcessor.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.
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 video processor configuration from local files.
Passing `token=True` is required when you want to use a private model.
Returns:
`Dict`: The configuration of the video processor.
Examples:
```python
# Download configuration from huggingface.co and cache.
video_processor_config = get_video_processor_config("llava-hf/llava-onevision-qwen2-0.5b-ov-hf")
# This model does not have a video processor config so the result will be an empty dict.
video_processor_config = get_video_processor_config("FacebookAI/xlm-roberta-base")
# Save a pretrained video processor locally and you can reload its config
from transformers import AutoVideoProcessor
video_processor = AutoVideoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-0.5b-ov-hf")
video_processor.save_pretrained("video-processor-test")
video_processor = get_video_processor_config("video-processor-test")
```F) filenamer3 r4 r5 r6 r7 r8 _raise_exceptions_for_gated_repo%_raise_exceptions_for_missing_entries)
r> r3 r4 r5 r6 r7 r8 r? r@ '_raise_exceptions_for_connection_errorsNz8Could not locate the video processor configuration file.video_processor)r r r
r loggerinfor )r2 r3 r4 r5 r6 r7 r8 kwargsresolved_processor_filer>
resolved_file resolved_video_processor_files resolved_video_processor_filevideo_processor_dictprocessor_dicts &&&&&&&, r get_video_processor_configrL m s D *% %))..3 ./CD&DH (-!# - !!1166;8=
M
D # &( Jh$B1$Emq! )1H NO
*,-DE .#12C#D $05I5Q 23P Q % %2%O&s C
C
)backendsc d a ] tR t^t o RtR t]]! ]4 R 4 4 t ]
RR l4 t Rt V t
R# )AutoVideoProcessora
This is a generic video processor class that will be instantiated as one of the video processor classes of the
library when created with the [`AutoVideoProcessor.from_pretrained`] class method.
This class cannot be instantiated directly using `__init__()` (throws an error).
c \ R 4 h)zAutoVideoProcessor is designed to be instantiated using the `AutoVideoProcessor.from_pretrained(pretrained_model_name_or_path)` method.)OSError)selfs &r __init__AutoVideoProcessor.__init__ s
d
r c VP RR4 pVP RR4 pRVR& \ P ! V3/ VB w rgVP RR4 pRp RVP R/ 4 9 d VR, R, p Vfu V fq VP R R4 p
V
e" V
P R
R 4 p \ V 4 e T pR VP R/ 4 9 d# VR, R , p V P R
R 4 p Vft \
V\ 4 ' g \ P ! V3RV/VB p\ VRR4 p\ VR4 ' d% RVP 9 d VP R, p Ve \ V4 pV RJp
VRJ;' g \ V4 \ 9 pR
pV
' d V' dM T;' g \ \ V4 , pVRJ;' d! VP P# R4 ' * pRV 9 d V P% R4 ^ , pMRp\' WQWV4 pV
' dX V' dP V' gH T p\) VV3/ VB pVP RR4 pVP+ 4 VP ! V.VO5/ VB # Ve VP ! V.VO5/ VB # \ V4 \ 9 d1 \ \ V4 , pVe VP ! V.VO5/ VB # \- 4 ' g \ V R24 h\ RV R\. R\0 R\0 RRP3 R \4 4 4 2
4 h \ d ELi ; i)a
Instantiate one of the video processor classes of the library from a pretrained model vocabulary.
The video 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 video_processor hosted inside a model repo on
huggingface.co.
- a path to a *directory* containing a video processor file saved using the
[`~video_processing_utils.BaseVideoProcessor.save_pretrained`] method, e.g.,
`./my_model_directory/`.
- a path to a saved video 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 video 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 video processor files and override the cached versions if
they exist.
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.
return_unused_kwargs (`bool`, *optional*, defaults to `False`):
If `False`, then this function returns just the final video processor object. If `True`, then this
functions returns a `Tuple(video_processor, unused_kwargs)` where *unused_kwargs* is a dictionary
consisting of the key/value pairs whose keys are not video processor attributes: i.e., the part of
`kwargs` which has not been used to update `video_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 video processor attributes will be used to override the
loaded values. Behavior concerning key/value pairs whose keys are *not* video 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 AutoVideoProcessor
>>> # Download video processor from huggingface.co and cache.
>>> video_processor = AutoVideoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-0.5b-ov-hf")
>>> # If video processor files are in a directory (e.g. video processor was saved using *save_pretrained('./test/saved_model/')*)
>>> # video_processor = AutoVideoProcessor.from_pretrained("./test/saved_model/")
```configNtrust_remote_codeT
_from_autovideo_processor_typerO auto_mapimage_processor_typeImageProcessorVideoProcessorAutoImageProcessorFz
transformers.z--
code_revisionzT requires `torchvision` to be installed. Please install `torchvision` and try again.z Unrecognized video processor in z2. Should have a `video_processor_type` key in its z of z3, or one of the following `model_type` keys in its z: z, c 3 $ " T F qx K R # 5i)N ).0cs & r 5AutoVideoProcessor.from_pretrained.. s @jLiqLis )popr get_video_processor_dictgetreplacer0
isinstancer r from_pretrainedr& r+ rZ
ValueErrortyper(
__module__
startswithsplitr r register_for_auto_classr r
r joinr )clsr2 inputsrE rV rW config_dict_video_processor_classvideo_processor_auto_mapimage_processor_class video_processor_class_inferredimage_processor_auto_maphas_remote_codehas_local_codeexplicit_local_codelocal_video_processor_class
upstream_repo class_refs &&*, r rk "AutoVideoProcessor.from_pretrained s L Hd+ "JJ':D A #| +DDEbmflm +0F M #' ;??:r#B B'2:'>?S'T $ ! (-E-M$/OO4JD$Q !$01F1N1NO_aq1r. 33QR^,J)#{z2'FF+6z+BCW+X(+C+K+KL\^n+o( ! (
!&*:;; ' 7 75 IZ ^d F
)08NPT(U%6:..3G6??3Z/5?S/T, ! ,$CDY$Z !2$>.d:eed6lNe>e # .C.l.lG^_cdj_kGl+/t; _ _ 7 B B M Mo ^^ $ // 8 > >t DQ G
$
9!.cp! 09L0I$A)Mj$unt$u !
?D1A ! 9 9 ;(889VjY_jcij j
"
.(889VjY_jcij j
&\ 4
4$;DL$I !$0,<<=Zn]cngmnn ()) 01 2F G
./L.M N11E0Fd;- X((3}Btyy@jLi@j7j6k
m
]
s ;A2M MMc 4 \ P WVR7 R# )z
Register a new video processor for this class.
Args:
config_class ([`PreTrainedConfig`]):
The configuration corresponding to the model to register.
video_processor_class ([`BaseVideoProcessor`]):
The video processor to register.
)exist_okN)r( register) config_classrw r s &&&r r AutoVideoProcessor.register s (( W_(`r ra N)F)r! rn __qualname____firstlineno____doc__rS classmethodr r rk staticmethodr __static_attributes____classdictcell__)
__classdict__s @r rO rO sK
&'DE[
F [
z a ar rO r( c V ^8 d Qh/ ^ \ 9 d: \ \ \ \ R, \ R, 3, 3, ;R& # )r Nr )__conditional_annotations__r r tuple)r s "r r r s9 L cb;sE#*cDj:P4Q/Q#RbM r ) ) cosmos3_omniQwen3VLVideoProcessor) exaone4_5Qwen2VLVideoProcessor) instructblip InstructBlipVideoVideoProcessor)pe_audio_videoPeVideoVideoProcessor) qwen2_5_omnir )
qwen2_5_vlr )qwen3_5r ) qwen3_5_moer )qwen3_omni_moer ) qwen3_vl_moer ) qwen4_expr )
videoprism LlavaOnevisionVideoProcessor)NFNNNF)vision torchvision)2r r r$ r9 collectionsr typingr configuration_utilsr dynamic_module_utilsr r utilsr r r r
r r r
r utils.import_utilsr video_processing_utilsr auto_factoryr
auto_mappingsr configuration_autor r r r
get_loggerr! rC %MISSING_VIDEO_PROCESSOR_MAPPING_NAMESupdater#
model_typevideo_processorsfast_video_processor_classr( r0 rL rO __all__r )r s @r r s # 4 \ + 8 * 8
H % VaUb!b -8
-) "(()NO$A$G$G$I J !1 $ % %%)"0J!*- %J ++?A^_ 0u&p
,-|a |a .|a~ %&:
;r