/usr/local/lib/python3.6/site-packages/transformers/models/auto
Edit: /usr/local/lib/python3.6/site-packages/transformers/models/auto/feature_extraction_auto.py (16303B)
# coding=utf-8
# Copyright 2021 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" AutoFeatureExtractor class."""
import importlib
import json
import os
from collections import OrderedDict
from typing import Dict, Optional, Union
# Build the list of all feature extractors
from ...configuration_utils import PretrainedConfig
from ...dynamic_module_utils import get_class_from_dynamic_module
from ...feature_extraction_utils import FeatureExtractionMixin
from ...utils import CONFIG_NAME, FEATURE_EXTRACTOR_NAME, get_file_from_repo, logging
from .auto_factory import _LazyAutoMapping
from .configuration_auto import (
CONFIG_MAPPING_NAMES,
AutoConfig,
model_type_to_module_name,
replace_list_option_in_docstrings,
)
logger = logging.get_logger(__name__)
FEATURE_EXTRACTOR_MAPPING_NAMES = OrderedDict(
[
("beit", "BeitFeatureExtractor"),
("detr", "DetrFeatureExtractor"),
("deit", "DeiTFeatureExtractor"),
("hubert", "Wav2Vec2FeatureExtractor"),
("speech_to_text", "Speech2TextFeatureExtractor"),
("vit", "ViTFeatureExtractor"),
("wav2vec2", "Wav2Vec2FeatureExtractor"),
("detr", "DetrFeatureExtractor"),
("layoutlmv2", "LayoutLMv2FeatureExtractor"),
("clip", "CLIPFeatureExtractor"),
("perceiver", "PerceiverFeatureExtractor"),
("swin", "ViTFeatureExtractor"),
("vit_mae", "ViTFeatureExtractor"),
("segformer", "SegformerFeatureExtractor"),
("convnext", "ConvNextFeatureExtractor"),
("van", "ConvNextFeatureExtractor"),
("resnet", "ConvNextFeatureExtractor"),
("poolformer", "PoolFormerFeatureExtractor"),
("maskformer", "MaskFormerFeatureExtractor"),
]
)
FEATURE_EXTRACTOR_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, FEATURE_EXTRACTOR_MAPPING_NAMES)
def feature_extractor_class_from_name(class_name: str):
for module_name, extractors in FEATURE_EXTRACTOR_MAPPING_NAMES.items():
if class_name in extractors:
module_name = model_type_to_module_name(module_name)
module = importlib.import_module(f".{module_name}", "transformers.models")
return getattr(module, class_name)
break
for config, extractor in FEATURE_EXTRACTOR_MAPPING._extra_content.items():
if getattr(extractor, "__name__", None) == class_name:
return extractor
return None
def get_feature_extractor_config(
pretrained_model_name_or_path: Union[str, os.PathLike],
cache_dir: Optional[Union[str, os.PathLike]] = None,
force_download: bool = False,
resume_download: bool = False,
proxies: Optional[Dict[str, str]] = None,
use_auth_token: Optional[Union[bool, str]] = None,
revision: Optional[str] = None,
local_files_only: bool = False,
**kwargs,
):
"""
Loads the tokenizer configuration from a pretrained model tokenizer 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. Valid model ids can be located at the root-level, like `bert-base-uncased`, or namespaced
under a user or organization name, like `dbmdz/bert-base-german-cased`.
- 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 (`bool`, *optional*, defaults to `False`):
Whether or not to delete incompletely received file. Attempts to resume the download if such a file exists.
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.
use_auth_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 `transformers-cli 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 tokenizer configuration from local files.
Passing `use_auth_token=True` is required when you want to use a private model.
Returns:
`Dict`: The configuration of the tokenizer.
Examples:
```python
# Download configuration from huggingface.co and cache.
tokenizer_config = get_tokenizer_config("bert-base-uncased")
# This model does not have a tokenizer config so the result will be an empty dict.
tokenizer_config = get_tokenizer_config("xlm-roberta-base")
# Save a pretrained tokenizer locally and you can reload its config
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
tokenizer.save_pretrained("tokenizer-test")
tokenizer_config = get_tokenizer_config("tokenizer-test")
```"""
resolved_config_file = get_file_from_repo(
pretrained_model_name_or_path,
FEATURE_EXTRACTOR_NAME,
cache_dir=cache_dir,
force_download=force_download,
resume_download=resume_download,
proxies=proxies,
use_auth_token=use_auth_token,
revision=revision,
local_files_only=local_files_only,
)
if resolved_config_file is None:
logger.info(
"Could not locate the feature extractor configuration file, will try to use the model config instead."
)
return {}
with open(resolved_config_file, encoding="utf-8") as reader:
return json.load(reader)
class AutoFeatureExtractor:
r"""
This is a generic feature extractor class that will be instantiated as one of the feature extractor classes of the
library when created with the [`AutoFeatureExtractor.from_pretrained`] class method.
This class cannot be instantiated directly using `__init__()` (throws an error).
"""
def __init__(self):
raise EnvironmentError(
"AutoFeatureExtractor is designed to be instantiated "
"using the `AutoFeatureExtractor.from_pretrained(pretrained_model_name_or_path)` method."
)
@classmethod
@replace_list_option_in_docstrings(FEATURE_EXTRACTOR_MAPPING_NAMES)
def from_pretrained(cls, pretrained_model_name_or_path, **kwargs):
r"""
Instantiate one of the feature extractor classes of the library from a pretrained model vocabulary.
The feature extractor 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 feature_extractor hosted inside a model repo on
huggingface.co. Valid model ids can be located at the root-level, like `bert-base-uncased`, or
namespaced under a user or organization name, like `dbmdz/bert-base-german-cased`.
- a path to a *directory* containing a feature extractor file saved using the
[`~feature_extraction_utils.FeatureExtractionMixin.save_pretrained`] method, e.g.,
`./my_model_directory/`.
- a path or url to a saved feature extractor 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 feature extractor 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 feature extractor files and override the cached versions
if they exist.
resume_download (`bool`, *optional*, defaults to `False`):
Whether or not to delete incompletely received file. Attempts to resume the download if such a file
exists.
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.
use_auth_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 `transformers-cli 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 feature extractor object. If `True`, then this
functions returns a `Tuple(feature_extractor, unused_kwargs)` where *unused_kwargs* is a dictionary
consisting of the key/value pairs whose keys are not feature extractor attributes: i.e., the part of
`kwargs` which has not been used to update `feature_extractor` 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 feature extractor attributes will be used to override the
loaded values. Behavior concerning key/value pairs whose keys are *not* feature extractor attributes is
controlled by the `return_unused_kwargs` keyword parameter.
Passing `use_auth_token=True` is required when you want to use a private model.
Examples:
```python
>>> from transformers import AutoFeatureExtractor
>>> # Download feature extractor from huggingface.co and cache.
>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/wav2vec2-base-960h")
>>> # If feature extractor files are in a directory (e.g. feature extractor was saved using *save_pretrained('./test/saved_model/')*)
>>> feature_extractor = AutoFeatureExtractor.from_pretrained("./test/saved_model/")
```"""
config = kwargs.pop("config", None)
trust_remote_code = kwargs.pop("trust_remote_code", False)
kwargs["_from_auto"] = True
config_dict, _ = FeatureExtractionMixin.get_feature_extractor_dict(pretrained_model_name_or_path, **kwargs)
feature_extractor_class = config_dict.get("feature_extractor_type", None)
feature_extractor_auto_map = None
if "AutoFeatureExtractor" in config_dict.get("auto_map", {}):
feature_extractor_auto_map = config_dict["auto_map"]["AutoFeatureExtractor"]
# If we don't find the feature extractor class in the feature extractor config, let's try the model config.
if feature_extractor_class is None and feature_extractor_auto_map is None:
if not isinstance(config, PretrainedConfig):
config = AutoConfig.from_pretrained(pretrained_model_name_or_path, **kwargs)
# It could be in `config.feature_extractor_type``
feature_extractor_class = getattr(config, "feature_extractor_type", None)
if hasattr(config, "auto_map") and "AutoFeatureExtractor" in config.auto_map:
feature_extractor_auto_map = config.auto_map["AutoFeatureExtractor"]
if feature_extractor_class is not None:
# If we have custom code for a feature extractor, we get the proper class.
if feature_extractor_auto_map is not None:
if not trust_remote_code:
raise ValueError(
f"Loading {pretrained_model_name_or_path} requires you to execute the feature extractor file "
"in that repo on your local machine. Make sure you have read the code there to avoid "
"malicious use, then set the option `trust_remote_code=True` to remove this error."
)
if kwargs.get("revision", None) is None:
logger.warning(
"Explicitly passing a `revision` is encouraged when loading a feature extractor with custom "
"code to ensure no malicious code has been contributed in a newer revision."
)
module_file, class_name = feature_extractor_auto_map.split(".")
feature_extractor_class = get_class_from_dynamic_module(
pretrained_model_name_or_path, module_file + ".py", class_name, **kwargs
)
else:
feature_extractor_class = feature_extractor_class_from_name(feature_extractor_class)
return feature_extractor_class.from_dict(config_dict, **kwargs)
# Last try: we use the FEATURE_EXTRACTOR_MAPPING.
elif type(config) in FEATURE_EXTRACTOR_MAPPING:
feature_extractor_class = FEATURE_EXTRACTOR_MAPPING[type(config)]
return feature_extractor_class.from_dict(config_dict, **kwargs)
raise ValueError(
f"Unrecognized feature extractor in {pretrained_model_name_or_path}. Should have a "
f"`feature_extractor_type` key in its {FEATURE_EXTRACTOR_NAME} of {CONFIG_NAME}, or one of the following "
"`model_type` keys in its {CONFIG_NAME}: {', '.join(c for c in FEATURE_EXTRACTOR_MAPPING_NAMES.keys())}"
)
@staticmethod
def register(config_class, feature_extractor_class):
"""
Register a new feature extractor for this class.
Args:
config_class ([`PretrainedConfig`]):
The configuration corresponding to the model to register.
feature_extractor_class ([`FeatureExtractorMixin`]): The feature extractor to register.
"""
FEATURE_EXTRACTOR_MAPPING.register(config_class, feature_extractor_class)