Apply suggestions from code review

src/transformers/__init__.py

@@ -480,11 +480,8 @@
     _import_structure["models.detr"].append("DetrFeatureExtractor")
     _import_structure["models.layoutlmv2"].append("LayoutLMv2FeatureExtractor")
     _import_structure["models.layoutlmv2"].append("LayoutLMv2Processor")
-<<<<<<< HEAD
-    _import_structure["models.segformer"].append("SegformerFeatureExtractor")
-=======
     _import_structure["models.layoutxlm"].append("LayoutXLMProcessor")
->>>>>>> Move LayoutXLM tokenizers and processor to separate folder
+    _import_structure["models.segformer"].append("SegformerFeatureExtractor")
     _import_structure["models.vit"].append("ViTFeatureExtractor")
 else:
     from .utils import dummy_vision_objects
@@ -2359,8 +2356,8 @@
         from .models.deit import DeiTFeatureExtractor
         from .models.detr import DetrFeatureExtractor
         from .models.layoutlmv2 import LayoutLMv2FeatureExtractor, LayoutLMv2Processor
-        from .models.segformer import SegformerFeatureExtractor
         from .models.layoutxlm import LayoutXLMProcessor
+        from .models.segformer import SegformerFeatureExtractor
         from .models.vit import ViTFeatureExtractor
     else:
         from .utils.dummy_vision_objects import *

src/transformers/models/__init__.py

@@ -59,6 +59,7 @@
     ibert,
     layoutlm,
     layoutlmv2,
+    layoutxlm,
     led,
     longformer,
     luke,

src/transformers/models/layoutxlm/tokenization_layoutxlm.py

@@ -474,67 +474,6 @@ def _is_valid_text_input(t):
                 **kwargs,
             )
 
-    @add_end_docstrings(ENCODE_KWARGS_DOCSTRING, LAYOUTLMV2_ENCODE_PLUS_ADDITIONAL_KWARGS_DOCSTRING)
-    def batch_encode_plus(
-        self,
-        batch_text_or_text_pairs: Union[
-            List[TextInput],
-            List[TextInputPair],
-            List[PreTokenizedInput],
-        ],
-        is_pair: bool = None,
-        boxes: Optional[List[List[List[int]]]] = None,
-        word_labels: Optional[Union[List[int], List[List[int]]]] = None,
-        add_special_tokens: bool = True,
-        padding: Union[bool, str, PaddingStrategy] = False,
-        truncation: Union[bool, str, TruncationStrategy] = False,
-        max_length: Optional[int] = None,
-        stride: int = 0,
-        pad_to_multiple_of: Optional[int] = None,
-        return_tensors: Optional[Union[str, TensorType]] = None,
-        return_token_type_ids: Optional[bool] = None,
-        return_attention_mask: Optional[bool] = None,
-        return_overflowing_tokens: bool = False,
-        return_special_tokens_mask: bool = False,
-        return_offsets_mapping: bool = False,
-        return_length: bool = False,
-        verbose: bool = True,
-        **kwargs
-    ) -> BatchEncoding:
-        """ """
-
-        # Backward compatibility for 'truncation_strategy', 'pad_to_max_length'
-        padding_strategy, truncation_strategy, max_length, kwargs = self._get_padding_truncation_strategies(
-            padding=padding,
-            truncation=truncation,
-            max_length=max_length,
-            pad_to_multiple_of=pad_to_multiple_of,
-            verbose=verbose,
-            **kwargs,
-        )
-
-        return self._batch_encode_plus(
-            batch_text_or_text_pairs=batch_text_or_text_pairs,
-            is_pair=is_pair,
-            boxes=boxes,
-            word_labels=word_labels,
-            add_special_tokens=add_special_tokens,
-            padding_strategy=padding_strategy,
-            truncation_strategy=truncation_strategy,
-            max_length=max_length,
-            stride=stride,
-            pad_to_multiple_of=pad_to_multiple_of,
-            return_tensors=return_tensors,
-            return_token_type_ids=return_token_type_ids,
-            return_attention_mask=return_attention_mask,
-            return_overflowing_tokens=return_overflowing_tokens,
-            return_special_tokens_mask=return_special_tokens_mask,
-            return_offsets_mapping=return_offsets_mapping,
-            return_length=return_length,
-            verbose=verbose,
-            **kwargs,
-        )
-
     def _batch_encode_plus(
         self,
         batch_text_or_text_pairs: Union[
@@ -662,123 +601,6 @@ def _batch_prepare_for_model(
 
         return batch_outputs
 
-    @add_end_docstrings(ENCODE_KWARGS_DOCSTRING)
-    def encode(
-        self,
-        text: Union[TextInput, PreTokenizedInput],
-        text_pair: Optional[PreTokenizedInput] = None,
-        boxes: Optional[List[List[int]]] = None,
-        word_labels: Optional[List[int]] = None,
-        add_special_tokens: bool = True,
-        padding: Union[bool, str, PaddingStrategy] = False,
-        truncation: Union[bool, str, TruncationStrategy] = False,
-        max_length: Optional[int] = None,
-        stride: int = 0,
-        pad_to_multiple_of: Optional[int] = None,
-        return_tensors: Optional[Union[str, TensorType]] = None,
-        return_token_type_ids: Optional[bool] = None,
-        return_attention_mask: Optional[bool] = None,
-        return_overflowing_tokens: bool = False,
-        return_special_tokens_mask: bool = False,
-        return_offsets_mapping: bool = False,
-        return_length: bool = False,
-        verbose: bool = True,
-        **kwargs
-    ) -> List[int]:
-        """
-        ...
-        """
-        encoded_inputs = self.encode_plus(
-            text=text,
-            text_pair=text_pair,
-            boxes=boxes,
-            word_labels=word_labels,
-            add_special_tokens=add_special_tokens,
-            padding=padding,
-            truncation=truncation,
-            max_length=max_length,
-            stride=stride,
-            pad_to_multiple_of=pad_to_multiple_of,
-            return_tensors=return_tensors,
-            return_token_type_ids=return_token_type_ids,
-            return_attention_mask=return_attention_mask,
-            return_overflowing_tokens=return_overflowing_tokens,
-            return_special_tokens_mask=return_special_tokens_mask,
-            return_offsets_mapping=return_offsets_mapping,
-            return_length=return_length,
-            verbose=verbose,
-            **kwargs,
-        )
-
-        return encoded_inputs["input_ids"]
-
-    @add_end_docstrings(ENCODE_KWARGS_DOCSTRING, LAYOUTLMV2_ENCODE_PLUS_ADDITIONAL_KWARGS_DOCSTRING)
-    def encode_plus(
-        self,
-        text: Union[TextInput, PreTokenizedInput],
-        text_pair: Optional[PreTokenizedInput] = None,
-        boxes: Optional[List[List[int]]] = None,
-        word_labels: Optional[List[int]] = None,
-        add_special_tokens: bool = True,
-        padding: Union[bool, str, PaddingStrategy] = False,
-        truncation: Union[bool, str, TruncationStrategy] = False,
-        max_length: Optional[int] = None,
-        stride: int = 0,
-        pad_to_multiple_of: Optional[int] = None,
-        return_tensors: Optional[Union[str, TensorType]] = None,
-        return_token_type_ids: Optional[bool] = None,
-        return_attention_mask: Optional[bool] = None,
-        return_overflowing_tokens: bool = False,
-        return_special_tokens_mask: bool = False,
-        return_offsets_mapping: bool = False,
-        return_length: bool = False,
-        verbose: bool = True,
-        **kwargs
-    ) -> BatchEncoding:
-        """
-        Tokenize and prepare for the model a sequence or a pair of sequences. .. warning:: This method is deprecated,
-        ``__call__`` should be used instead.
-
-        Args:
-            text (:obj:`str`, :obj:`List[str]`, :obj:`List[List[str]]`):
-                The first sequence to be encoded. This can be a string, a list of strings or a list of list of strings.
-            text_pair (:obj:`List[str]` or :obj:`List[int]`, `optional`):
-                Optional second sequence to be encoded. This can be a list of strings (words of a single example) or a
-                list of list of strings (words of a batch of examples).
-        """
-
-        # Backward compatibility for 'truncation_strategy', 'pad_to_max_length'
-        padding_strategy, truncation_strategy, max_length, kwargs = self._get_padding_truncation_strategies(
-            padding=padding,
-            truncation=truncation,
-            max_length=max_length,
-            pad_to_multiple_of=pad_to_multiple_of,
-            verbose=verbose,
-            **kwargs,
-        )
-
-        return self._encode_plus(
-            text=text,
-            boxes=boxes,
-            text_pair=text_pair,
-            word_labels=word_labels,
-            add_special_tokens=add_special_tokens,
-            padding_strategy=padding_strategy,
-            truncation_strategy=truncation_strategy,
-            max_length=max_length,
-            stride=stride,
-            pad_to_multiple_of=pad_to_multiple_of,
-            return_tensors=return_tensors,
-            return_token_type_ids=return_token_type_ids,
-            return_attention_mask=return_attention_mask,
-            return_overflowing_tokens=return_overflowing_tokens,
-            return_special_tokens_mask=return_special_tokens_mask,
-            return_offsets_mapping=return_offsets_mapping,
-            return_length=return_length,
-            verbose=verbose,
-            **kwargs,
-        )
-
     def _encode_plus(
         self,
         text: Union[TextInput, PreTokenizedInput],

src/transformers/utils/dummy_vision_objects.py

@@ -50,10 +50,6 @@ def from_pretrained(cls, *args, **kwargs):
         requires_backends(cls, ["vision"])
 
 
-class SegformerFeatureExtractor:
-    def __init__(self, *args, **kwargs):
-        requires_backends(self, ["vision"])
-
 class LayoutXLMProcessor:
     def __init__(self, *args, **kwargs):
         requires_backends(self, ["vision"])
@@ -63,6 +59,11 @@ def from_pretrained(cls, *args, **kwargs):
         requires_backends(cls, ["vision"])
 
 
+class SegformerFeatureExtractor:
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["vision"])
+
+
 class ViTFeatureExtractor:
     def __init__(self, *args, **kwargs):
         requires_backends(self, ["vision"])