Update modeling doc strings FE -> IP (#21106)

* Update docs examples FE -> IP

* Remove _IMAGE_PROCESSOR_FOR_DOC

src/transformers/models/altclip/modeling_altclip.py

@@ -98,7 +98,7 @@ ALTCLIP_VISION_INPUTS_DOCSTRING = r"""
     Args:
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details.
+            [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
         output_attentions (`bool`, *optional*):
             Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
             tensors for more detail.
@@ -133,7 +133,7 @@ ALTCLIP_INPUTS_DOCSTRING = r"""
             [What are position IDs?](../glossary#position-ids)
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details.
+            [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
         return_loss (`bool`, *optional*):
             Whether or not to return the contrastive loss.
         output_attentions (`bool`, *optional*):

src/transformers/models/beit/modeling_beit.py

@@ -49,7 +49,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "BeitConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "BeitImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "microsoft/beit-base-patch16-224-pt22k"
@@ -646,7 +645,6 @@ class BeitModel(BeitPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BEIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BeitModelOutputWithPooling,
         config_class=_CONFIG_FOR_DOC,
@@ -844,7 +842,6 @@ class BeitForImageClassification(BeitPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BEIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=ImageClassifierOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/bit/modeling_bit.py

@@ -46,7 +46,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "BitConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoFeatureExtractor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "google/bit-50"
@@ -688,8 +687,8 @@ BIT_START_DOCSTRING = r"""
 BIT_INPUTS_DOCSTRING = r"""
     Args:
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
-            Pixel values. Pixel values can be obtained using [`AutoFeatureExtractor`]. See
-            [`AutoFeatureExtractor.__call__`] for details.
+            Pixel values. Pixel values can be obtained using [`AutoImageProcessor`]. See
+            [`AutoImageProcessor.__call__`] for details.
 
         output_hidden_states (`bool`, *optional*):
             Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
@@ -723,7 +722,6 @@ class BitModel(BitPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPoolingAndNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -782,7 +780,6 @@ class BitForImageClassification(BitPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(BIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=ImageClassifierOutputWithNoAttention,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/chinese_clip/modeling_chinese_clip.py

@@ -810,7 +810,7 @@ CHINESE_CLIP_VISION_INPUTS_DOCSTRING = r"""
     Args:
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`ChineseCLIPFeatureExtractor`]. See [`ChineseCLIPFeatureExtractor.__call__`] for details.
+            [`ChineseCLIPImageProcessor`]. See [`ChineseCLIPImageProcessor.__call__`] for details.
         output_attentions (`bool`, *optional*):
             Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
             tensors for more detail.
@@ -853,7 +853,7 @@ CHINESE_CLIP_INPUTS_DOCSTRING = r"""
             [What are position IDs?](../glossary#position-ids)
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`ChineseCLIPFeatureExtractor`]. See [`ChineseCLIPFeatureExtractor.__call__`] for details.
+            [`ChineseCLIPImageProcessor`]. See [`ChineseCLIPImageProcessor.__call__`] for details.
         return_loss (`bool`, *optional*):
             Whether or not to return the contrastive loss.
         output_attentions (`bool`, *optional*):

src/transformers/models/clip/modeling_clip.py

@@ -521,7 +521,7 @@ CLIP_VISION_INPUTS_DOCSTRING = r"""
     Args:
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details.
+            [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
         output_attentions (`bool`, *optional*):
             Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
             tensors for more detail.
@@ -556,7 +556,7 @@ CLIP_INPUTS_DOCSTRING = r"""
             [What are position IDs?](../glossary#position-ids)
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details.
+            [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
         return_loss (`bool`, *optional*):
             Whether or not to return the contrastive loss.
         output_attentions (`bool`, *optional*):

src/transformers/models/clip/modeling_flax_clip.py

@@ -108,7 +108,7 @@ CLIP_VISION_INPUTS_DOCSTRING = r"""
     Args:
         pixel_values (`numpy.ndarray` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details.
+            [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
         output_attentions (`bool`, *optional*):
             Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
             tensors for more detail.
@@ -143,7 +143,7 @@ CLIP_INPUTS_DOCSTRING = r"""
             [What are position IDs?](../glossary#position-ids)
         pixel_values (`numpy.ndarray` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details.
+            [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
         output_attentions (`bool`, *optional*):
             Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
             tensors for more detail.
@@ -893,7 +893,7 @@ class FlaxCLIPPreTrainedModel(FlaxPreTrainedModel):
         Args:
             pixel_values (`numpy.ndarray` of shape `(batch_size, num_channels, height, width)`):
                 Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained
-                using [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details.
+                using [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
 
         Returns:
             image_features (`jnp.ndarray` of shape `(batch_size, output_dim`): The image embeddings obtained by

src/transformers/models/clip/modeling_tf_clip.py

@@ -993,8 +993,8 @@ CLIP_TEXT_INPUTS_DOCSTRING = r"""
 CLIP_VISION_INPUTS_DOCSTRING = r"""
     Args:
         pixel_values (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` ``Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `(batch_size, num_channels, height, width)`):
-            Pixel values. Pixel values can be obtained using [`CLIPFeatureExtractor`]. See
-            [`CLIPFeatureExtractor.__call__`] for details. output_attentions (`bool`, *optional*): Whether or not to
+            Pixel values. Pixel values can be obtained using [`CLIPImageProcessor`]. See
+            [`CLIPImageProcessor.__call__`] for details. output_attentions (`bool`, *optional*): Whether or not to
             return the attentions tensors of all attention layers. See `attentions` under returned tensors for more
             detail. This argument can be used only in eager mode, in graph mode the value in the config will be used
             instead.
@@ -1020,8 +1020,8 @@ CLIP_INPUTS_DOCSTRING = r"""
 
             [What are input IDs?](../glossary#input-ids)
         pixel_values (`np.ndarray`, `tf.Tensor`, `List[tf.Tensor]` `Dict[str, tf.Tensor]` or `Dict[str, np.ndarray]` and each example must have the shape `(batch_size, num_channels, height, width)`):
-            Pixel values. Pixel values can be obtained using [`CLIPFeatureExtractor`]. See
-            [`CLIPFeatureExtractor.__call__`] for details.
+            Pixel values. Pixel values can be obtained using [`CLIPImageProcessor`]. See
+            [`CLIPImageProcessor.__call__`] for details.
         attention_mask (`np.ndarray` or `tf.Tensor` of shape `({0})`, *optional*):
             Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
 

src/transformers/models/clipseg/modeling_clipseg.py

@@ -530,7 +530,7 @@ CLIPSEG_VISION_INPUTS_DOCSTRING = r"""
     Args:
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details.
+            [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
         output_attentions (`bool`, *optional*):
             Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
             tensors for more detail.
@@ -565,7 +565,7 @@ CLIPSEG_INPUTS_DOCSTRING = r"""
             [What are position IDs?](../glossary#position-ids)
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details.
+            [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
         return_loss (`bool`, *optional*):
             Whether or not to return the contrastive loss.
         output_attentions (`bool`, *optional*):

src/transformers/models/convnext/modeling_convnext.py

@@ -44,7 +44,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "ConvNextConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "ConvNextImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "facebook/convnext-tiny-224"
@@ -346,7 +345,6 @@ class ConvNextModel(ConvNextPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(CONVNEXT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPoolingAndNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -414,7 +412,6 @@ class ConvNextForImageClassification(ConvNextPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(CONVNEXT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=ImageClassifierOutputWithNoAttention,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/cvt/modeling_cvt.py

@@ -35,7 +35,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "CvtConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "microsoft/cvt-13"
@@ -605,7 +604,6 @@ class CvtModel(CvtPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(CVT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithCLSToken,
         config_class=_CONFIG_FOR_DOC,
@@ -668,7 +666,6 @@ class CvtForImageClassification(CvtPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(CVT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=ImageClassifierOutputWithNoAttention,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/data2vec/modeling_data2vec_vision.py

@@ -48,7 +48,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "Data2VecVisionConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "BeitImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "facebook/data2vec-vision-base"
@@ -660,7 +659,6 @@ class Data2VecVisionModel(Data2VecVisionPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=Data2VecVisionModelOutputWithPooling,
         config_class=_CONFIG_FOR_DOC,
@@ -760,7 +758,6 @@ class Data2VecVisionForImageClassification(Data2VecVisionPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=ImageClassifierOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/data2vec/modeling_tf_data2vec_vision.py

@@ -53,7 +53,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "Data2VecVisionConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "BeitImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "facebook/data2vec-vision-base"
@@ -894,7 +893,6 @@ class TFData2VecVisionModel(TFData2VecVisionPreTrainedModel):
     @unpack_inputs
     @add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TFData2VecVisionModelOutputWithPooling,
         config_class=_CONFIG_FOR_DOC,
@@ -960,7 +958,6 @@ class TFData2VecVisionForImageClassification(TFData2VecVisionPreTrainedModel, TF
     @unpack_inputs
     @add_start_docstrings_to_model_forward(DATA2VEC_VISION_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=TFSequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/deit/modeling_deit.py

@@ -44,7 +44,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "DeiTConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "DeiTImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "facebook/deit-base-distilled-patch16-224"
@@ -483,7 +482,6 @@ class DeiTModel(DeiTPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPooling,
         config_class=_CONFIG_FOR_DOC,
@@ -854,7 +852,6 @@ class DeiTForImageClassificationWithTeacher(DeiTPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=DeiTForImageClassificationWithTeacherOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/deit/modeling_tf_deit.py

@@ -52,7 +52,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "DeiTConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "DeiTImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "facebook/deit-base-distilled-patch16-224"
@@ -651,7 +650,6 @@ class TFDeiTModel(TFDeiTPreTrainedModel):
     @unpack_inputs
     @add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TFBaseModelOutputWithPooling,
         config_class=_CONFIG_FOR_DOC,
@@ -1009,7 +1007,6 @@ class TFDeiTForImageClassificationWithTeacher(TFDeiTPreTrainedModel):
     @unpack_inputs
     @add_start_docstrings_to_model_forward(DEIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=TFDeiTForImageClassificationWithTeacherOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/dinat/modeling_dinat.py

@@ -57,7 +57,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "DinatConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "shi-labs/dinat-mini-in1k-224"
@@ -730,7 +729,6 @@ class DinatModel(DinatPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DINAT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=DinatModelOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -810,7 +808,6 @@ class DinatForImageClassification(DinatPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DINAT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=DinatImageClassifierOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/donut/modeling_donut_swin.py

@@ -43,7 +43,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "DonutSwinConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoFeatureExtractor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "https://huggingface.co/naver-clova-ix/donut-base"
@@ -847,8 +846,8 @@ SWIN_START_DOCSTRING = r"""
 SWIN_INPUTS_DOCSTRING = r"""
     Args:
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
-            Pixel values. Pixel values can be obtained using [`AutoFeatureExtractor`]. See
-            [`AutoFeatureExtractor.__call__`] for details.
+            Pixel values. Pixel values can be obtained using [`AutoImageProcessor`]. See
+            [`AutoImageProcessor.__call__`] for details.
         head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*):
             Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:
 
@@ -898,7 +897,6 @@ class DonutSwinModel(DonutSwinPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(SWIN_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=DonutSwinModelOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/dpt/modeling_dpt.py

@@ -49,7 +49,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "DPTConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "DPTImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "Intel/dpt-large"
@@ -898,7 +897,6 @@ class DPTModel(DPTPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(DPT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPoolingAndIntermediateActivations,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/flava/modeling_flava.py

@@ -51,7 +51,6 @@ _CHECKPOINT_FOR_DOC = "facebook/flava-full"
 
 # Codebook docstring
 _CHECKPOINT_FOR_CODEBOOK_DOC = "facebook/flava-image-codebook"
-_FEAT_EXTRACTOR_FOR_DOC = "FlavaFeatureExtractor"
 _CONFIG_CLASS_FOR_IMAGE_MODEL_DOC = "FlavaImageConfig"
 _CONFIG_CLASS_FOR_TEXT_MODEL_DOC = "FlavaTextConfig"
 _CONFIG_CLASS_FOR_MULTIMODAL_MODEL_DOC = "FlavaMultimodalConfig"
@@ -750,8 +749,8 @@ FLAVA_INPUTS_DOCSTRING_COMMON = r"""
 FLAVA_IMAGE_INPUTS_DOCSTRING_BASE = r"""
     Args:
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
-            Pixel values. Pixel values can be obtained using [`FlavaFeatureExtractor`]. See
-            [`FlavaFeatureExtractor.__call__`] for details.
+            Pixel values. Pixel values can be obtained using [`FlavaImageProcessor`]. See
+            [`FlavaImageProcessor.__call__`] for details.
 
         bool_masked_pos (`torch.BoolTensor` of shape `(batch_size, image_num_patches)`):
             Boolean masked positions. Indicates which patches are masked (1) and which aren't (0).
@@ -926,7 +925,6 @@ class FlavaImageModel(FlavaPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(FLAVA_IMAGE_INPUTS_DOCSTRING.format("batch_size, image_num_patches"))
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPooling,
         config_class=_CONFIG_CLASS_FOR_IMAGE_MODEL_DOC,
@@ -1568,22 +1566,22 @@ class FlavaImageCodebook(FlavaPreTrainedModel):
         """
         Args:
             pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
-                Pixel values. Codebook pixel values can be obtained using [`FlavaFeatureExtractor`] by passing
-                `return_codebook_pixels=True`. See [`FlavaFeatureExtractor.__call__`] for details.
+                Pixel values. Codebook pixel values can be obtained using [`FlavaImageProcessor`] by passing
+                `return_codebook_pixels=True`. See [`FlavaImageProcessor.__call__`] for details.
 
         Examples:
         ```python
         >>> from PIL import Image
         >>> import requests
-        >>> from transformers import FlavaFeatureExtractor, FlavaImageCodebook
+        >>> from transformers import FlavaImageProcessor, FlavaImageCodebook
 
         >>> model = FlavaImageCodebook.from_pretrained("{0}")
-        >>> feature_extractor = FlavaFeatureExtractor.from_pretrained("{0}")
+        >>> image_processor = FlavaImageProcessor.from_pretrained("{0}")
 
         >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> image = Image.open(requests.get(url, stream=True).raw)
 
-        >>> inputs = feature_extractor([image], return_codebook_pixels=True, return_tensors="pt")
+        >>> inputs = image_processor([image], return_codebook_pixels=True, return_tensors="pt")
         >>> inputs = dict(pixel_values=inputs.codebook_pixel_values)
 
         >>> outputs = model.get_codebook_indices(**inputs)
@@ -1602,23 +1600,23 @@ class FlavaImageCodebook(FlavaPreTrainedModel):
         """
         Args:
             pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
-                Pixel values. Codebook pixel values can be obtained using [`FlavaFeatureExtractor`] by passing
-                `return_codebook_pixels=True`. See [`FlavaFeatureExtractor.__call__`] for details.
+                Pixel values. Codebook pixel values can be obtained using [`FlavaImageProcessor`] by passing
+                `return_codebook_pixels=True`. See [`FlavaImageProcessor.__call__`] for details.
 
         Examples:
 
         ```python
         >>> from PIL import Image
         >>> import requests
-        >>> from transformers import FlavaFeatureExtractor, FlavaImageCodebook
+        >>> from transformers import FlavaImageProcessor, FlavaImageCodebook
 
         >>> model = FlavaImageCodebook.from_pretrained("{0}")
-        >>> feature_extractor = FlavaFeatureExtractor.from_pretrained("{0}")
+        >>> image_processor = FlavaImageProcessor.from_pretrained("{0}")
 
         >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> image = Image.open(requests.get(url, stream=True).raw)
 
-        >>> inputs = feature_extractor([image], return_codebook_pixels=True, return_tensors="pt")
+        >>> inputs = image_processor([image], return_codebook_pixels=True, return_tensors="pt")
         >>> inputs = dict(pixel_values=inputs.codebook_pixel_values)
 
         >>> outputs = model(**inputs)

src/transformers/models/git/modeling_git.py

@@ -916,7 +916,7 @@ GIT_VISION_INPUTS_DOCSTRING = r"""
     Args:
         pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
             Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using
-            [`CLIPFeatureExtractor`]. See [`CLIPFeatureExtractor.__call__`] for details.
+            [`CLIPImageProcessor`]. See [`CLIPImageProcessor.__call__`] for details.
         output_attentions (`bool`, *optional*):
             Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
             tensors for more detail.

src/transformers/models/glpn/modeling_glpn.py

@@ -41,7 +41,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "GLPNConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "GLPNImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "vinvino02/glpn-kitti"
@@ -503,7 +502,6 @@ class GLPNModel(GLPNPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(GLPN_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutput,
         config_class=_CONFIG_FOR_DOC,