rh{J | 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 ejB e" Z#er e Z$ee%e&e e% e e% f f e'd< n
eg d Z$e$jQ D ] \ Z)Z*e*Z+ e sdZ+e+e$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 gZ3y)!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) qwen2_5_omniQwen2VLVideoProcessor)
qwen2_5_vlr% )qwen2_vlr% )smolvlmSmolVLMVideoProcessor) video_llavaVideoLlavaVideoProcessor)vjepa2VJEPA2VideoProcessor
class_namec t j D ]< \ }}| |v s t | }t j d| d } t || c S t j j D ] }t |dd | k( s|c S t j d }t || r t || S y # t $ r Y w xY w)N.ztransformers.models__name__ transformers) r itemsr importlib
import_modulegetattrAttributeErrorVIDEO_PROCESSOR_MAPPING_extra_contentvalueshasattr)r. module_name
extractorsmodule extractor main_modules /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/auto/video_processing_auto.py video_processor_class_from_namerB L s #@#F#F#H Z #3K@K ,,q
->@UVF
vz22
-;;BBD 9j$ /: = )).9K{J'{J// "
s B99 CC 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 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`.)rD rE rF rG rH rI rJ zbCould not locate the video processor configuration file, will try to use the model config instead.zutf-8)encoding) popwarningswarn
FutureWarning
ValueErrorr
r loggerinfoopenjsonload) rC rD rE rF rG rH rI rJ kwargsrL resolved_config_filereaders rA get_video_processor_configr] d s J ZZ 0$7N!
A
uv v &% %')
# p
"W 5 !yy ! ! !s <BB$)vision torchvision)backendsc P e Zd ZdZd Ze ee d Ze dd Z
y)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 rA __init__zAutoVideoProcessor.__init__ s
d
c Z |j dd }|;t j dt |j d t d ||d< |j dd }|j dd }d|d < t
j |fi |\ }}|j d
d } d}
d |j d i v r|d d }
| n|
l|j d
d } | *| j dd } | t j v r| } d|j d i v r|d d }
|
j dd }
| `|
^t |t st j |fd|i|}t |d
d } t! |d r d |j" v r|j" d }
| t% | } |
du}| duxs t' | t( v }t+ |||| }|rF|rD|
}t- ||fi |} |j dd }| j/ | j0 |fi |S | | j0 |fi |S t' | t( v r5t( t' | } | | j |g|i |S t d t d| dt2 dt4 dt4 ddj7 d t D
)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/")
```rL NrM rH rN configtrust_remote_codeT
_from_autovideo_processor_typerb 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 | ] }| y w)N ).0cs rA z5AutoVideoProcessor.from_pretrained..o s @jq@js ) rP rQ rR rS getrT r get_video_processor_dictreplacer r:
isinstancer r from_pretrainedr6 r; rm rB typer8 r
r register_for_auto_class from_dictr r join)clsrC inputsrZ rL ri rj config_dict_video_processor_classvideo_processor_auto_mapimage_processor_class video_processor_class_inferredimage_processor_auto_maphas_remote_codehas_local_code class_refs rA r| z"AutoVideoProcessor.from_pretrained sF R $4d; % MM E
zz'". l -F7OHd+ "JJ':D A #| +DDEbmflm Q +0F M #' ;??:r#B B'2:'>?S'T $ ! (-E-M$/OO4JD$Q !$01F1N1NO_aq1r. 25R5Y5Y5[[,J)#{z2'FF+6z+BCW+X(+C+K+KL\^n+o( ! (-E-M f&67#331EVZ` %,F4JD$Q !vz*/Cv/V+1??;O+P( ,$CDY$Z !2$>.d:ed6lNe>e 5 r s # 1 1 4 \ f f * 8 *
H % \g[h!;sE(3-RU :V4W/W#Xh$/
%!" %B$G$G$I K J !1 $ %%)"0J!*-K ++?A^_ 4 48 &*(,(, " "a!#(bkk)9#:a!c2;; ./0a! a! d^ a!
d38n
% a! E$)$ %
a! sma! a!H
,-xa xa .xav %&:
;rg