/usr/local/lib/python3.6/site-packages/transformers/utils
NameSizeModeActions
__pycache__/-0755rm
doc.py388360644editdlrm
dummy_detectron2_objects.py3910644editdlrm
dummy_flax_objects.py248550644editdlrm
dummy_pt_objects.py1114430644editdlrm
dummy_pytorch_quantization_and_torch_objects.py24760644editdlrm
dummy_scatter_objects.py11380644editdlrm
dummy_sentencepiece_and_speech_objects.py3420644editdlrm
dummy_sentencepiece_and_tokenizers_objects.py3010644editdlrm
dummy_sentencepiece_objects.py43710644editdlrm
dummy_speech_objects.py3150644editdlrm
dummy_tf_objects.py504560644editdlrm
dummy_timm_and_vision_objects.py9030644editdlrm
dummy_timm_objects.py8050644editdlrm
dummy_tokenizers_objects.py81730644editdlrm
dummy_vision_objects.py34860644editdlrm
fx.py231860644editdlrm
fx_transformations.py121780644editdlrm
generic.py98200644editdlrm
hp_naming.py49710644editdlrm
hub.py429320644editdlrm
import_utils.py292880644editdlrm
logging.py95160644editdlrm
model_parallel_utils.py22760644editdlrm
notebook.py145240644editdlrm
sentencepiece_model_pb2.py396070644editdlrm
versions.py43780644editdlrm
__init__.py50550644editdlrm
Edit: /usr/local/lib/python3.6/site-packages/transformers/utils/generic.py (9820B)
# Copyright 2022 The HuggingFace Team. All rights reserved. # # 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. """ Generic utilities """ import inspect from collections import OrderedDict, UserDict from contextlib import ExitStack from dataclasses import fields from enum import Enum from typing import Any, ContextManager, List, Tuple import numpy as np from .import_utils import is_flax_available, is_tf_available, is_torch_available, is_torch_fx_proxy class cached_property(property): """ Descriptor that mimics @property but caches output in member variable. From tensorflow_datasets Built-in in functools from Python 3.8. """ def __get__(self, obj, objtype=None): # See docs.python.org/3/howto/descriptor.html#properties if obj is None: return self if self.fget is None: raise AttributeError("unreadable attribute") attr = "__cached_" + self.fget.__name__ cached = getattr(obj, attr, None) if cached is None: cached = self.fget(obj) setattr(obj, attr, cached) return cached def is_tensor(x): """ Tests if `x` is a `torch.Tensor`, `tf.Tensor`, `jaxlib.xla_extension.DeviceArray` or `np.ndarray`. """ if is_torch_fx_proxy(x): return True if is_torch_available(): import torch if isinstance(x, torch.Tensor): return True if is_tf_available(): import tensorflow as tf if isinstance(x, tf.Tensor): return True if is_flax_available(): import jax.numpy as jnp from jax.core import Tracer if isinstance(x, (jnp.ndarray, Tracer)): return True return isinstance(x, np.ndarray) def _is_numpy(x): return isinstance(x, np.ndarray) def _is_torch(x): import torch return isinstance(x, torch.Tensor) def _is_torch_device(x): import torch return isinstance(x, torch.device) def _is_tensorflow(x): import tensorflow as tf return isinstance(x, tf.Tensor) def _is_jax(x): import jax.numpy as jnp # noqa: F811 return isinstance(x, jnp.ndarray) def to_py_obj(obj): """ Convert a TensorFlow tensor, PyTorch tensor, Numpy array or python list to a python list. """ if isinstance(obj, (dict, UserDict)): return {k: to_py_obj(v) for k, v in obj.items()} elif isinstance(obj, (list, tuple)): return [to_py_obj(o) for o in obj] elif is_tf_available() and _is_tensorflow(obj): return obj.numpy().tolist() elif is_torch_available() and _is_torch(obj): return obj.detach().cpu().tolist() elif is_flax_available() and _is_jax(obj): return np.asarray(obj).tolist() elif isinstance(obj, (np.ndarray, np.number)): # tolist also works on 0d np arrays return obj.tolist() else: return obj def to_numpy(obj): """ Convert a TensorFlow tensor, PyTorch tensor, Numpy array or python list to a Numpy array. """ if isinstance(obj, (dict, UserDict)): return {k: to_numpy(v) for k, v in obj.items()} elif isinstance(obj, (list, tuple)): return np.array(obj) elif is_tf_available() and _is_tensorflow(obj): return obj.numpy() elif is_torch_available() and _is_torch(obj): return obj.detach().cpu().numpy() elif is_flax_available() and _is_jax(obj): return np.asarray(obj) else: return obj class ModelOutput(OrderedDict): """ Base class for all model outputs as dataclass. Has a `__getitem__` that allows indexing by integer or slice (like a tuple) or strings (like a dictionary) that will ignore the `None` attributes. Otherwise behaves like a regular python dictionary. You can't unpack a `ModelOutput` directly. Use the [`~utils.ModelOutput.to_tuple`] method to convert it to a tuple before. """ def __post_init__(self): class_fields = fields(self) # Safety and consistency checks if not len(class_fields): raise ValueError(f"{self.__class__.__name__} has no fields.") if not all(field.default is None for field in class_fields[1:]): raise ValueError(f"{self.__class__.__name__} should not have more than one required field.") first_field = getattr(self, class_fields[0].name) other_fields_are_none = all(getattr(self, field.name) is None for field in class_fields[1:]) if other_fields_are_none and not is_tensor(first_field): if isinstance(first_field, dict): iterator = first_field.items() first_field_iterator = True else: try: iterator = iter(first_field) first_field_iterator = True except TypeError: first_field_iterator = False # if we provided an iterator as first field and the iterator is a (key, value) iterator # set the associated fields if first_field_iterator: for element in iterator: if ( not isinstance(element, (list, tuple)) or not len(element) == 2 or not isinstance(element[0], str) ): break setattr(self, element[0], element[1]) if element[1] is not None: self[element[0]] = element[1] elif first_field is not None: self[class_fields[0].name] = first_field else: for field in class_fields: v = getattr(self, field.name) if v is not None: self[field.name] = v def __delitem__(self, *args, **kwargs): raise Exception(f"You cannot use ``__delitem__`` on a {self.__class__.__name__} instance.") def setdefault(self, *args, **kwargs): raise Exception(f"You cannot use ``setdefault`` on a {self.__class__.__name__} instance.") def pop(self, *args, **kwargs): raise Exception(f"You cannot use ``pop`` on a {self.__class__.__name__} instance.") def update(self, *args, **kwargs): raise Exception(f"You cannot use ``update`` on a {self.__class__.__name__} instance.") def __getitem__(self, k): if isinstance(k, str): inner_dict = {k: v for (k, v) in self.items()} return inner_dict[k] else: return self.to_tuple()[k] def __setattr__(self, name, value): if name in self.keys() and value is not None: # Don't call self.__setitem__ to avoid recursion errors super().__setitem__(name, value) super().__setattr__(name, value) def __setitem__(self, key, value): # Will raise a KeyException if needed super().__setitem__(key, value) # Don't call self.__setattr__ to avoid recursion errors super().__setattr__(key, value) def to_tuple(self) -> Tuple[Any]: """ Convert self to a tuple containing all the attributes/keys that are not `None`. """ return tuple(self[k] for k in self.keys()) class ExplicitEnum(Enum): """ Enum with more explicit error message for missing values. """ @classmethod def _missing_(cls, value): raise ValueError( f"{value} is not a valid {cls.__name__}, please select one of {list(cls._value2member_map_.keys())}" ) class PaddingStrategy(ExplicitEnum): """ Possible values for the `padding` argument in [`PreTrainedTokenizerBase.__call__`]. Useful for tab-completion in an IDE. """ LONGEST = "longest" MAX_LENGTH = "max_length" DO_NOT_PAD = "do_not_pad" class TensorType(ExplicitEnum): """ Possible values for the `return_tensors` argument in [`PreTrainedTokenizerBase.__call__`]. Useful for tab-completion in an IDE. """ PYTORCH = "pt" TENSORFLOW = "tf" NUMPY = "np" JAX = "jax" class ContextManagers: """ Wrapper for `contextlib.ExitStack` which enters a collection of context managers. Adaptation of `ContextManagers` in the `fastcore` library. """ def __init__(self, context_managers: List[ContextManager]): self.context_managers = context_managers self.stack = ExitStack() def __enter__(self): for context_manager in self.context_managers: self.stack.enter_context(context_manager) def __exit__(self, *args, **kwargs): self.stack.__exit__(*args, **kwargs) def find_labels(model_class): """ Find the labels used by a given model. Args: model_class (`type`): The class of the model. """ model_name = model_class.__name__ if model_name.startswith("TF"): signature = inspect.signature(model_class.call) elif model_name.startswith("Flax"): signature = inspect.signature(model_class.__call__) else: signature = inspect.signature(model_class.forward) if "QuestionAnswering" in model_name: return [p for p in signature.parameters if "label" in p or p in ("start_positions", "end_positions")] else: return [p for p in signature.parameters if "label" in p]