`iK U d Z ddlZddlZddlZddlZddlmZ ddlmZm Z m
Z
ddl m Z ddl
mZmZ ddlmZmZmZmZmZ dd lmZ dd
lmZ d d lmZ d d
l m Z m Z m Z m Z ej! e" Z#er, e Z$ee%e&e e% e e% f f e'd< n
eg d Z$e$( D ]\ Z)Z*e*Z+ e sdZ+e+e$e)< ee e$ Z,de%fdZ- d!de
e%ej. f de e
e%ej. f de/de e/ de e0e%e%f de e
e/e%f de e% de/fdZ1 ed G d d Z2d d gZ3dS )"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 t D ]S\ }}| |v rJt | }t j d| d } t || c S # t $ r Y Ow xY wTt j D ]}t |dd | k r|c S t j d }t || rt || S d S )N.ztransformers.models__name__ transformers) r itemsr importlib
import_modulegetattrAttributeErrorVIDEO_PROCESSOR_MAPPING_extra_contentvalueshasattr)r6 module_name
extractorsmodule extractor main_modules /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/auto/video_processing_auto.py video_processor_class_from_namerJ Q s #@#F#F#H#H Z # #3K@@K ,->->->@UVVF
vz22222!
$ -;BBDD 9j$ / /: = = >
).99K{J'' 0{J/// 4s A
A*)A*F pretrained_model_name_or_path cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_onlyc | dd } | -t j dt |t d | }t | t ||||||| }
|
t d i S t |
d 5 } t j | cddd S # 1 swxY w Y dS ) 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 s2 J ZZ 0$77N!
A
uvv v &% %')
# p
"W 5 5 5 !y ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! !s B33B7:B7)vision torchvision)backendsc j e Zd ZdZd Ze ee d Ze dd Z
dS )AutoVideoProcessora%
This is a generic video processor class that will be instantiated as one of the video processor classes of the
library when created with the [`AutoVideoProcessor.from_pretrained`] class method.
This class cannot be instantiated directly using `__init__()` (throws an error).
c t d )NzAutoVideoProcessor is designed to be instantiated using the `AutoVideoProcessor.from_pretrained(pretrained_model_name_or_path)` method.)OSError)selfs rI __init__zAutoVideoProcessor.__init__ s
d
c | dd }|Ct j dt | d t d ||d< | dd }| dd }d|d < t
j |fi |\ }}| d
d } d}
d | d i v r|d d }
| |
| d
d } | 3| dd } | t
v r| } d| d i v r$|d d }
|
dd }
| b|
`t |t st j |fd|i|}t |d
d } t! |d rd |j v r
|j d }
| t% | } |
du}| dupt' | t( v }t+ |||| }|rJ|rH|
}t- ||fi |} | dd }| | j |fi |S | | j |fi |S t' | t( v r
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 K | ]}|V d S )N ).0cs rI z5AutoVideoProcessor.from_pretrained..t s" @j@jq@j@j@j@j@j@jro ) rX rY rZ r[ getr\ r get_video_processor_dictreplacer rB
isinstancer r from_pretrainedr> rC ru rJ typer@ r
r register_for_auto_class from_dictr r join)clsrK inputsrb rT rq rr 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 z"AutoVideoProcessor.from_pretrained s R $4d;; % M E
zz'"". l -F7OHd++ "JJ':D A A #| +DEbmmflmm Q +0F M M #' ;??:r#B#B B B'2:'>?S'T $ ! (-E-M$/OO4JD$Q$Q !$01F1N1NO_aq1r1r. 25R5Y5Y5[5[[[,J)#{z2'F'FFF+6z+BCW+X(+C+K+KL\^n+o+o( ! (-E-M f&677
#31 EVZ` %,F4JD$Q$Q !vz**
Q/Cv/V/V+1?;O+P( ,$CDY$Z$Z !2$>.d:ed6llNe>e 5 r s^ # # # # # # 1 1 1 1 1 1 1 1 1 1 4 3 3 3 3 3 \ \ \ \ \ \ \ \ f f f f f f f f f f f f f f * * * * * * 8 8 8 8 8 8 * * * * * *
H % % \g[f[h[h!;sE(3-RU :V4W/W#Xhhhh$/K
% %!, %B$G$G$I$I K K J !1 $ # % % *%)"0J!*--**+?A^__ 4 48 &*(,(, " "a! a!#(bk)9#:a!c2; ./0a! a! d^ a!
d38n
% a! E$)$ %
a! sma! a! a! a! a!H
,---xa xa xa xa xa xa xa .-xav %&:
;ro