GiTZ d dl Z d dlZd dlZd dlmZmZ d dlZd dlm Z m
Z
ddl m Z ddl
mZ ddlmZmZ ddlmZmZmZmZmZmZ dd lmZ ed
d Z ej: e Z G d
de Z G d d e Z ee jB e _! e jB jD 8e jB jD jG ddd e jB _" yy) N)AnyTypeVar) create_repois_offline_mode )custom_object_save) BatchFeature)is_valid_image
load_image)IMAGE_PROCESSOR_NAMEPROCESSOR_NAMEPushToHubMixin copy_funcloggingsafe_load_json_file) cached_fileImageProcessorTypeImageProcessingMixin)boundc e Zd ZdZy)r a
Holds the output of the image processor specific `__call__` methods.
This class is derived from a python dictionary and can be used as a dictionary.
Args:
data (`dict`):
Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.).
tensor_type (`Union[None, str, TensorType]`, *optional*):
You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at
initialization.
N)__name__
__module__ __qualname____doc__ d/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/transformers/image_processing_base.pyr r - s r r c e Zd ZdZdZd Ze d dee de e
j z de e
j z dz de de d e e z dz d
e d efd Z
d d
e e
j z de fdZede e
j z d eee ef ee ef f fd Zedee ef fd Zd ee ef fdZede e
j z fd Zd e fdZde e
j z fdZd Zed d Zde ee z eee z fd Zy) r z
This is an image processor mixin used to provide saving/loading functionality for sequential and image feature
extractors.
Nc
|j dd |j dd |j D ] \ }} t | || y# t $ r%}t j d| d| d| |d}~ww xY w)z'Set elements of `kwargs` as attributes.feature_extractor_typeNprocessor_classz
Can't set z with value z for )popitemssetattrAttributeErrorloggererror)selfkwargskeyvalueerrs r __init__z ImageProcessingMixin.__init__E s
+T2
$d+ ,,. JC
c5) "
z#l5'tf MN
s
A A: A55A:cls pretrained_model_name_or_path cache_dirforce_downloadlocal_files_onlytokenrevisionreturnc ||d< ||d< ||d< ||d< |||d< | j |fi |\ }} | j |fi |S )a
Instantiate a type of [`~image_processing_utils.ImageProcessingMixin`] from an image processor.
Args:
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 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.
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`, or not specified, 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.
To test a pull request you made on the Hub, you can pass `revision="refs/pr/"`.
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.
subfolder (`str`, *optional*, defaults to `""`):
In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
specify the folder name here.
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.
Returns:
A image processor of type [`~image_processing_utils.ImageProcessingMixin`].
Examples:
```python
# We can't instantiate directly the base class *ImageProcessingMixin* so let's show the examples on a
# derived class: *CLIPImageProcessor*
image_processor = CLIPImageProcessor.from_pretrained(
"openai/clip-vit-base-patch32"
) # Download image_processing_config from huggingface.co and cache.
image_processor = CLIPImageProcessor.from_pretrained(
"./test/saved_model/"
) # E.g. image processor (or model) was saved using *save_pretrained('./test/saved_model/')*
image_processor = CLIPImageProcessor.from_pretrained("./test/saved_model/preprocessor_config.json")
image_processor = CLIPImageProcessor.from_pretrained(
"openai/clip-vit-base-patch32", do_normalize=False, foo=False
)
assert image_processor.do_normalize is False
image_processor, unused_kwargs = CLIPImageProcessor.from_pretrained(
"openai/clip-vit-base-patch32", do_normalize=False, foo=False, return_unused_kwargs=True
)
assert image_processor.do_normalize is False
assert unused_kwargs == {"foo": False}
```r0 r1 r2 r4 r3 )get_image_processor_dict from_dict) r. r/ r0 r1 r2 r3 r4 r) image_processor_dicts r from_pretrainedz$ImageProcessingMixin.from_pretrainedT st n ({#1 %5!" %z #F7O'Cs'C'CDa'lek'l$ f s}} 1 )configzImage processor saved in r3 )r? r3 )ospathisfileAssertionErrormakedirsr" splitsepr r@ _get_files_timestamps _auto_classr joinr to_json_filer& info_upload_modified_filesget)r( r; r< r) r? r@ files_timestampsoutput_image_processor_files r save_pretrainedz$ImageProcessingMixin.save_pretrained s/ 77>>. ) ?>2BBe!fg g
NT2 #ZZ(8$ ?N jjN,@,@,Mb,QRG!'CDCFCKKG # 9 9. I ' t^D A ')ggll>CW&X# 56 /0K/LMN ' ' - jj)
(
,,,r c
|j dd }|j dd }|j dd }|j dd }|j dd }|j dd }|j d d
} |j d t }
|j d d } |j d
d } d| d}
| | |
d< t r|st j d d}t | }t j j | }t j j | r t j j ||
}t j j | r|}d}d}n3|
} t |t ||||||
|| d }t ||||||||
|| d }d}|t | }d|v r|d }|
| t | }|t d| d| d|
d |r t j d| ||fS t j d d| ||fS # t $ r t $ r t d| d| d|
d w xY w)a
From a `pretrained_model_name_or_path`, resolve to a dictionary of parameters, to be used for instantiating a
image processor of type [`~image_processor_utils.ImageProcessingMixin`] using `from_dict`.
Parameters:
pretrained_model_name_or_path (`str` or `os.PathLike`):
The identifier of the pre-trained checkpoint from which we want the dictionary of parameters.
subfolder (`str`, *optional*, defaults to `""`):
In case the relevant files are located inside a subfolder of the model repo on huggingface.co, you can
specify the folder name here.
image_processor_filename (`str`, *optional*, defaults to `"config.json"`):
The name of the file in the model directory to use for the image processor config.
Returns:
`tuple[Dict, Dict]`: The dictionary(ies) that will be used to instantiate the image processor object.
r0 Nr1 Fproxiesr3 r2 r4 subfolder image_processor_filename_from_pipeline
_from_autoimage processor) file_typefrom_auto_classusing_pipelinez+Offline mode: forcing local_files_only=TrueT)
filenamer0 r1 rU r2 r3
user_agentr4 rV %_raise_exceptions_for_missing_entriesz Can't load image processor for 'z'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'z2' is the correct path to a directory containing a z fileimage_processorzloading configuration file z from cache at )r" r r r& rN strrC rD isdirrL rE r r
OSError Exceptionr )r. r/ r) r0 r1 rU r3 r2 r4 rV rX
from_pipeliner] r` is_localimage_processor_file resolved_image_processor_fileresolved_processor_filer9 processor_dicts r r7 z-ImageProcessingMixin.get_image_processor_dict s ( JJ{D1 $4e<**Y-
7D)!::&8%@::j$/JJ{B/ #)::.HJ^#_
#3T:
**\59#4 Y
$+8J' ( %5 KKE F # (+,I(J%77==!>?
77==6 7#%77<<0MOg#h
77>>7 8,I )&* #H#; &
*51 + '#1 #%5 ) % ':? +' 1<1 1 '#1 #%5 ) % ':? 1-: $ " . 01H IN N2'56G'H$ ( 49M9U#67T#U '23P2Q R55R4S T++C*DEK
KK56S5TU V $V++
KK-.B-C?SpRqr
$V++Q
67T6U V99V8W X//G.HO
s :0H% %(I
r9 c |j }|j dd }|j |j D ci c]! \ }}|| j j
v s ||# c}} | di |}g }t
t |j D ]V }t || s|| j j
vs)t |||j |d |j | X |r&t j d| j d| d t j d| |r||fS |S c c}}w )a
Instantiates a type of [`~image_processing_utils.ImageProcessingMixin`] from a Python dictionary of parameters.
Args:
image_processor_dict (`dict[str, Any]`):
Dictionary that will be used to instantiate the image processor object. Such a dictionary can be
retrieved from a pretrained checkpoint by leveraging the
[`~image_processing_utils.ImageProcessingMixin.to_dict`] method.
kwargs (`dict[str, Any]`):
Additional parameters from which to initialize the image processor object.
Returns:
[`~image_processing_utils.ImageProcessingMixin`]: The image processor object instantiated from those
parameters.
return_unused_kwargsFNzImage processor z : kwargs z were applied for backward compatibility. To avoid this warning, add them to valid_kwargs: create a custom TypedDict extending ImagesKwargs with these keys and set it as the `valid_kwargs` class attribute.r )copyr" updater# valid_kwargs__annotations__reversedlistkeyshasattrr$ appendr& warning_oncer rN ) r. r9 r) rn kvrb
extra_keysr* s r r8 z ImageProcessingMixin.from_dict^ s7 " 4 8 8 : %zz*@% H ##flln$ndaSM]M]MmMmHmQT$no 5 45
D /0 'C,Cr s 8 4 F 3 # 19OP
H %
# jw> jwZ
$--A-M-M#N ##++7/C/O/O/W/W/^/^ /CRh 0_ 0$$, 8r