bCiK % S r SSKrSSKrSSKrSSKrSSKJr SSKJrJ r J
r
SSK J r SSK
JrJr SSKJrJrJrJrJr SS KJr SS
KJr S S KJr S S
K J r J r J r J r \RB " \"5 r#\( a \" 5 r$\\%\&\ \% \ \% 4 4 \'S' O
\" / SQ5 r$\$RQ 5 H u r)r*\*r+\" 5 ( d Sr+\+\$\)' M \" \ \$5 r,S\%4S jr- S S\
\%\R\ 4 S\ \
\%\R\ 4 S\/S\ \/ S\ \0\%\%4 S\ \
\/\%4 S\ \% S\/4S jjr1\" SS 9 " S S 5 5 r2S S /r3g)!zAutoVideoProcessor class. N) OrderedDict)
TYPE_CHECKINGOptionalUnion )PretrainedConfig) get_class_from_dynamic_moduleresolve_trust_remote_code) CONFIG_NAMEVIDEO_PROCESSOR_NAME cached_fileis_torchvision_availablelogging)requires)BaseVideoProcessor )_LazyAutoMapping)CONFIG_MAPPING_NAMES
AutoConfigmodel_type_to_module_name!replace_list_option_in_docstrings VIDEO_PROCESSOR_MAPPING_NAMES))glm4vGlm4vVideoProcessor) instructblip InstructBlipVideoVideoProcessor)instructblipvideor )internvlInternVLVideoProcessor)llava_next_video LlavaNextVideoVideoProcessor)llava_onevision LlavaOnevisionVideoProcessor)
perception_lmPerceptionLMVideoProcessor) qwen2_5_omniQwen2VLVideoProcessor)
qwen2_5_vlr' )qwen2_vlr' )qwen3_omni_moer' )qwen3_vlQwen3VLVideoProcessor) qwen3_vl_moer, )
sam2_videoSam2VideoVideoProcessor)smolvlmSmolVLMVideoProcessor) video_llavaVideoLlavaVideoProcessor)vjepa2VJEPA2VideoProcessor
class_namec [ R 5 H= u pX; d M [ U5 n[ R " SU 3S5 n [ X05 s $ [ R R 5 H n[ USS 5 U :X d M Us $ [ R " S5 n[ XP5 ( a [ XP5 $ g ! [ a M f = f)N.ztransformers.models__name__ transformers) r itemsr importlib
import_modulegetattrAttributeErrorVIDEO_PROCESSOR_MAPPING_extra_contentvalueshasattr)r6 module_name
extractorsmodule extractor main_modules h/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/auto/video_processing_auto.py video_processor_class_from_namerJ Q s #@#F#F#H #3K@K ,,q
->@UVF
v22
$I -;;BBD 9j$ /: = E )).9K{''{// "
s
C
CC pretrained_model_name_or_path cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_onlyc V UR SS5 n U b+ [ R " S[ 5 Ub [ S5 eU n[ U [ UUUUUUUS9 n
U
c [ R S5 0 $ [ U
SS9 n [ R " U 5 sSSS5 $ ! , ( d f g= f) a
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
[`~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 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")
```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`.)rL rM rN rO rP rQ rR zbCould not locate the video processor configuration file, will try to use the model config instead.zutf-8)encoding) popwarningswarn
FutureWarning
ValueErrorr
r loggerinfoopenjsonload) rK rL rM rN rO rP rQ rR kwargsrT resolved_config_filereaders rI get_video_processor_configre i s J ZZ 0$7N!
A
uv v &% %')
# p
"W 5yy
6 5 5s :B
B()vision torchvision)backendsc Z \ rS rSrSrS r\\" \5 S 5 5 r \
SS j5 r Sr g) AutoVideoProcessor a
This is a generic video processor class that will be instantiated as one of the video processor classes of the
library when created with the [`AutoVideoProcessor.from_pretrained`] class method.
This class cannot be instantiated directly using `__init__()` (throws an error).
c [ S5 e)NzAutoVideoProcessor is designed to be instantiated using the `AutoVideoProcessor.from_pretrained(pretrained_model_name_or_path)` method.)OSError)selfs rI __init__AutoVideoProcessor.__init__ s
d
c UR SS5 nUb< [ R " S[ 5 UR S5 b [ S5 eXCS' UR SS5 nUR SS5 nSUS ' [ R " U40 UD6u pxUR S
S5 n Sn
S UR S 0 5 ; a US S n
U ct U
cq UR S
S5 n U b, U R SS5 n U [ R 5 ; a U n SUR S 0 5 ; a US S n
U
R SS5 n
U cn U
ck [ U[ 5 ( d [ R " U4SU0UD6n[ US
S5 n [! US 5 ( a S UR" ; a UR" S n
U b [% U 5 n U
SLnU SL=( d [' U5 [( ; n[+ XaX5 nU( aK U( aD U
n[- UU40 UD6n UR SS5 nU R/ 5 U R0 " U40 UD6$ U b U R0 " U40 UD6$ [' U5 [( ; a6 [( [' U5 n U b U R " U/UQ70 UD6$ [ S5 e[ SU S[2 S[4 S[4 SSR7 S [ 5 5 3
5 e)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 or url 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.
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.
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/")
```rT NrU rP rV configtrust_remote_codeT
_from_autovideo_processor_typerj auto_mapimage_processor_typeImageProcessorVideoProcessorAutoImageProcessor
code_revisionz_This video processor cannot be instantiated. Please make sure you have `torchvision` installed.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 $ # U H ov M g 7f)N ).0cs rI 5AutoVideoProcessor.from_pretrained..t s @jLiqLis ) rX rY rZ r[ getr\ r get_video_processor_dictreplacer rB
isinstancer r from_pretrainedr> rC rw rJ typer@ r
r register_for_auto_class from_dictr r join)clsrK inputsrb rT rs rt config_dict_video_processor_classvideo_processor_auto_mapimage_processor_class video_processor_class_inferredimage_processor_auto_maphas_remote_codehas_local_code class_refs rI r "AutoVideoProcessor.from_pretrained s: R $4d; % MM E
zz'". l -7OHd+ "JJ':D A #| +DDEbmflm +0F M #' ;??:r#B B'2:'>?S'T $ ! (-E-M$/OO4JD$Q !$01F1N1NO_aq1r. 25R5Y5Y5[[,J)#{z2'FF+6z+BCW+X(+C+K+KL\^n+o( ! (-E-M f&677#331EVZ` %,F4JD$Q !vz**/Cv/V+1??;O+P( ,$CDY$Z !2$>.d:ed6lNe>e 5 n
00I$A)Mj$unt$u !
?D1A ! 9 9 ;(22;I&I I
"
.(22;I&I I
&\ 4
4$;DL$I !$0,<<=Zn]cngmnn u ./L.M N11E0Fd;- X((3}Btyy@jLi@j7j6k
m
rq c , [ R XUS9 g)z
Register a new video processor for this class.
Args:
config_class ([`PretrainedConfig`]):
The configuration corresponding to the model to register.
video_processor_class ([`BaseVideoProcessor`]):
The video processor to register.
)exist_okN)r@ register) config_classr r s rI r AutoVideoProcessor.registerw s (( W_(`rq r~ N)F)
r9
__module__ __qualname____firstlineno____doc__ro classmethodr r r staticmethodr __static_attributes__r~ rq rI rj rj sM
&'DEW
F W
r a arq rj r@ )NFNNNNF)4r r< r` osrY collectionsr typingr r r configuration_utilsr dynamic_module_utilsr r
utilsr r r
r r utils.import_utilsr video_processing_utilsr auto_factoryr configuration_autor r r r
get_loggerr9 r] r strtuple__annotations__r;
model_typevideo_processorsfast_video_processor_classr@ rJ PathLikebooldictre rj __all__r~ rq rI r s # 1 1 4 \ f f * 8 *
H % \g[h!;sE(3-RU :V4W/W#Xh$/
%!, %B$G$G$I J !1 $ % %%)"0J!*- %J ++?A^_ 4 48 &*(,(, " "a!#(bkk)9#:a!c2;; ./0a! a! d^ a!
d38n
% a! E$)$ %
a! sma! a!H
,-xa xa .xav %&:
;rq