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

* Update docs examples FE -> IP

* Remove _IMAGE_PROCESSOR_FOR_DOC

src/transformers/models/groupvit/modeling_groupvit.py

@@ -857,7 +857,7 @@ GROUPVIT_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.
@@ -891,8 +891,8 @@ GROUPVIT_INPUTS_DOCSTRING = r"""
 
             [What are position IDs?](../glossary#position-ids)
         pixel_values (`torch.FloatTensor` of 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.
         return_loss (`bool`, *optional*):
             Whether or not to return the contrastive loss.
         output_attentions (`bool`, *optional*):

src/transformers/models/groupvit/modeling_tf_groupvit.py

@@ -1555,8 +1555,8 @@ GROUPVIT_TEXT_INPUTS_DOCSTRING = r"""
 GROUPVIT_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.
+            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
@@ -1583,8 +1583,8 @@ GROUPVIT_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/levit/modeling_levit.py

@@ -38,7 +38,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "LevitConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "LevitImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "facebook/levit-128S"
@@ -549,7 +548,6 @@ class LevitModel(LevitPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(LEVIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPoolingAndNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -618,7 +616,6 @@ class LevitForImageClassification(LevitPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(LEVIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=ImageClassifierOutputWithNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -711,7 +708,6 @@ class LevitForImageClassificationWithTeacher(LevitPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(LEVIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=LevitForImageClassificationWithTeacherOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/maskformer/modeling_maskformer.py

@@ -51,7 +51,6 @@ logger = logging.get_logger(__name__)
 
 _CONFIG_FOR_DOC = "MaskFormerConfig"
 _CHECKPOINT_FOR_DOC = "facebook/maskformer-swin-base-ade"
-_FEAT_EXTRACTOR_FOR_DOC = "MaskFormerImageProcessor"
 
 MASKFORMER_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "facebook/maskformer-swin-base-ade",

src/transformers/models/mobilenet_v1/modeling_mobilenet_v1.py

@@ -33,7 +33,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "MobileNetV1Config"
-_FEAT_EXTRACTOR_FOR_DOC = "MobileNetV1ImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "google/mobilenet_v1_1.0_224"
@@ -355,7 +354,6 @@ class MobileNetV1Model(MobileNetV1PreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILENET_V1_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPoolingAndNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -428,7 +426,6 @@ class MobileNetV1ForImageClassification(MobileNetV1PreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILENET_V1_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/mobilenet_v2/modeling_mobilenet_v2.py

@@ -43,7 +43,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "MobileNetV2Config"
-_FEAT_EXTRACTOR_FOR_DOC = "MobileNetV2ImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "google/mobilenet_v2_1.0_224"
@@ -566,7 +565,6 @@ class MobileNetV2Model(MobileNetV2PreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILENET_V2_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPoolingAndNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -639,8 +637,6 @@ class MobileNetV2ForImageClassification(MobileNetV2PreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILENET_V2_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
-        checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=ImageClassifierOutputWithNoAttention,
         config_class=_CONFIG_FOR_DOC,
         expected_output=_IMAGE_CLASS_EXPECTED_OUTPUT,

src/transformers/models/mobilevit/modeling_mobilevit.py

@@ -49,7 +49,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "MobileViTConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "MobileViTImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "apple/mobilevit-small"
@@ -745,7 +744,6 @@ class MobileViTModel(MobileViTPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILEVIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPoolingAndNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -819,7 +817,6 @@ class MobileViTForImageClassification(MobileViTPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(MOBILEVIT_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/mobilevit/modeling_tf_mobilevit.py

@@ -43,7 +43,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "MobileViTConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "MobileViTImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "apple/mobilevit-small"
@@ -839,7 +838,6 @@ class TFMobileViTModel(TFMobileViTPreTrainedModel):
     @unpack_inputs
     @add_start_docstrings_to_model_forward(MOBILEVIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TFBaseModelOutputWithPooling,
         config_class=_CONFIG_FOR_DOC,
@@ -889,7 +887,6 @@ class TFMobileViTForImageClassification(TFMobileViTPreTrainedModel, TFSequenceCl
     @unpack_inputs
     @add_start_docstrings_to_model_forward(MOBILEVIT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=TFImageClassifierOutputWithNoAttention,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/nat/modeling_nat.py

@@ -57,7 +57,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "NatConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "shi-labs/nat-mini-in1k-224"
@@ -708,7 +707,6 @@ class NatModel(NatPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(NAT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=NatModelOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -788,7 +786,6 @@ class NatForImageClassification(NatPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(NAT_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=NatImageClassifierOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/owlvit/modeling_owlvit.py

@@ -204,7 +204,7 @@ class OwlViTObjectDetectionOutput(ModelOutput):
         pred_boxes (`torch.FloatTensor` of shape `(batch_size, num_patches, 4)`):
             Normalized boxes coordinates for all queries, represented as (center_x, center_y, width, height). These
             values are normalized in [0, 1], relative to the size of each individual image in the batch (disregarding
-            possible padding). You can use [`~OwlViTFeatureExtractor.post_process_object_detection`] to retrieve the
+            possible padding). You can use [`~OwlViTImageProcessor.post_process_object_detection`] to retrieve the
             unnormalized bounding boxes.
         text_embeds (`torch.FloatTensor` of shape `(batch_size, num_max_text_queries, output_dim`):
             The text embeddings obtained by applying the projection layer to the pooled output of [`OwlViTTextModel`].
@@ -248,12 +248,12 @@ class OwlViTImageGuidedObjectDetectionOutput(ModelOutput):
         target_pred_boxes (`torch.FloatTensor` of shape `(batch_size, num_patches, 4)`):
             Normalized boxes coordinates for all queries, represented as (center_x, center_y, width, height). These
             values are normalized in [0, 1], relative to the size of each individual target image in the batch
-            (disregarding possible padding). You can use [`~OwlViTFeatureExtractor.post_process_object_detection`] to
+            (disregarding possible padding). You can use [`~OwlViTImageProcessor.post_process_object_detection`] to
             retrieve the unnormalized bounding boxes.
         query_pred_boxes (`torch.FloatTensor` of shape `(batch_size, num_patches, 4)`):
             Normalized boxes coordinates for all queries, represented as (center_x, center_y, width, height). These
             values are normalized in [0, 1], relative to the size of each individual query image in the batch
-            (disregarding possible padding). You can use [`~OwlViTFeatureExtractor.post_process_object_detection`] to
+            (disregarding possible padding). You can use [`~OwlViTImageProcessor.post_process_object_detection`] to
             retrieve the unnormalized bounding boxes.
         image_embeds (`torch.FloatTensor` of shape `(batch_size, patch_size, patch_size, output_dim`):
             Pooled output of [`OwlViTVisionModel`]. OWL-ViT represents images as a set of image patches and computes

src/transformers/models/poolformer/modeling_poolformer.py

@@ -34,7 +34,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "PoolFormerConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "PoolFormerImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "sail/poolformer_s12"
@@ -326,7 +325,6 @@ class PoolFormerModel(PoolFormerPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(POOLFORMER_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -397,7 +395,6 @@ class PoolFormerForImageClassification(PoolFormerPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(POOLFORMER_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/regnet/modeling_regnet.py

@@ -37,7 +37,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "RegNetConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "facebook/regnet-y-040"
@@ -341,7 +340,6 @@ class RegNetModel(RegNetPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(REGNET_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPoolingAndNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -399,7 +397,6 @@ class RegNetForImageClassification(RegNetPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(REGNET_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/regnet/modeling_tf_regnet.py

@@ -35,7 +35,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "RegNetConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "facebook/regnet-y-040"
@@ -411,7 +410,6 @@ class TFRegNetModel(TFRegNetPreTrainedModel):
     @unpack_inputs
     @add_start_docstrings_to_model_forward(REGNET_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TFBaseModelOutputWithPoolingAndNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -477,7 +475,6 @@ class TFRegNetForImageClassification(TFRegNetPreTrainedModel, TFSequenceClassifi
     @unpack_inputs
     @add_start_docstrings_to_model_forward(REGNET_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/resnet/modeling_resnet.py

@@ -43,7 +43,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "ResNetConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "microsoft/resnet-50"
@@ -312,7 +311,6 @@ class ResNetModel(ResNetPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(RESNET_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutputWithPoolingAndNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -369,7 +367,6 @@ class ResNetForImageClassification(ResNetPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(RESNET_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/resnet/modeling_tf_resnet.py

@@ -34,7 +34,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "ResNetConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "microsoft/resnet-50"
@@ -393,7 +392,6 @@ class TFResNetModel(TFResNetPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(RESNET_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TFBaseModelOutputWithPoolingAndNoAttention,
         config_class=_CONFIG_FOR_DOC,
@@ -458,7 +456,6 @@ class TFResNetForImageClassification(TFResNetPreTrainedModel, TFSequenceClassifi
 
     @add_start_docstrings_to_model_forward(RESNET_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=TFImageClassifierOutputWithNoAttention,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/segformer/modeling_segformer.py

@@ -42,7 +42,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "SegformerConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "SegformerImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "nvidia/mit-b0"
@@ -529,7 +528,6 @@ class SegformerModel(SegformerPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(SEGFORMER_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,
@@ -589,7 +587,6 @@ class SegformerForImageClassification(SegformerPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(SEGFORMER_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=SegFormerImageClassifierOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/segformer/modeling_tf_segformer.py

@@ -37,7 +37,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "SegformerConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "SegformerImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "nvidia/mit-b0"
@@ -606,7 +605,6 @@ class TFSegformerModel(TFSegformerPreTrainedModel):
     @unpack_inputs
     @add_start_docstrings_to_model_forward(SEGFORMER_INPUTS_DOCSTRING.format("(batch_size, sequence_length)"))
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TFBaseModelOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -659,7 +657,6 @@ class TFSegformerForImageClassification(TFSegformerPreTrainedModel, TFSequenceCl
     @unpack_inputs
     @add_start_docstrings_to_model_forward(SEGFORMER_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @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/swin/modeling_swin.py

@@ -44,7 +44,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "SwinConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "microsoft/swin-tiny-patch4-window7-224"
@@ -963,7 +962,6 @@ class SwinModel(SwinPreTrainedModel):
 
     @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=SwinModelOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1168,7 +1166,6 @@ class SwinForImageClassification(SwinPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(SWIN_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=SwinImageClassifierOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/swin/modeling_tf_swin.py

@@ -47,7 +47,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "SwinConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "microsoft/swin-tiny-patch4-window7-224"
@@ -1192,7 +1191,6 @@ class TFSwinModel(TFSwinPreTrainedModel):
 
     @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=TFSwinModelOutput,
         config_class=_CONFIG_FOR_DOC,
@@ -1429,7 +1427,6 @@ class TFSwinForImageClassification(TFSwinPreTrainedModel, TFSequenceClassificati
 
     @add_start_docstrings_to_model_forward(SWIN_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_IMAGE_CLASS_CHECKPOINT,
         output_type=TFSwinImageClassifierOutput,
         config_class=_CONFIG_FOR_DOC,

src/transformers/models/swin2sr/modeling_swin2sr.py

@@ -43,7 +43,6 @@ logger = logging.get_logger(__name__)
 
 # General docstring
 _CONFIG_FOR_DOC = "Swin2SRConfig"
-_FEAT_EXTRACTOR_FOR_DOC = "AutoImageProcessor"
 
 # Base docstring
 _CHECKPOINT_FOR_DOC = "caidas/swin2SR-classical-sr-x2-64"
@@ -823,8 +822,8 @@ SWIN2SR_START_DOCSTRING = r"""
 SWIN2SR_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]`:
 
@@ -897,7 +896,6 @@ class Swin2SRModel(Swin2SRPreTrainedModel):
 
     @add_start_docstrings_to_model_forward(SWIN2SR_INPUTS_DOCSTRING)
     @add_code_sample_docstrings(
-        processor_class=_FEAT_EXTRACTOR_FOR_DOC,
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=BaseModelOutput,
         config_class=_CONFIG_FOR_DOC,