Fix post_process_object_detection method descriptions (#20977)

fix post_process_object_detection descriptions

src/transformers/models/conditional_detr/image_processing_conditional_detr.py

@@ -1302,8 +1302,8 @@ class ConditionalDetrImageProcessor(BaseImageProcessor):
         self, outputs, threshold: float = 0.5, target_sizes: Union[TensorType, List[Tuple]] = None
     ):
         """
-        Converts the output of [`ConditionalDetrForObjectDetection`] into the format expected by the COCO api. Only
-        supports PyTorch.
+        Converts the raw output of [`ConditionalDetrForObjectDetection`] into final bounding boxes in (top_left_x,
+        top_left_y, bottom_right_x, bottom_right_y) format. Only supports PyTorch.
 
         Args:
             outputs ([`DetrObjectDetectionOutput`]):

src/transformers/models/deformable_detr/image_processing_deformable_detr.py

@@ -1251,8 +1251,8 @@ class DeformableDetrImageProcessor(BaseImageProcessor):
     # POSTPROCESSING METHODS - TODO: add support for other frameworks
     def post_process(self, outputs, target_sizes):
         """
-        Converts the output of [`DeformableDetrForObjectDetection`] into the format expected by the COCO api. Only
-        supports PyTorch.
+        Converts the raw output of [`DeformableDetrForObjectDetection`] into final bounding boxes in (top_left_x,
+        top_left_y, bottom_right_x, bottom_right_y) format. Only supports PyTorch.
 
         Args:
             outputs ([`DeformableDetrObjectDetectionOutput`]):
@@ -1299,8 +1299,8 @@ class DeformableDetrImageProcessor(BaseImageProcessor):
         self, outputs, threshold: float = 0.5, target_sizes: Union[TensorType, List[Tuple]] = None
     ):
         """
-        Converts the output of [`DeformableDetrForObjectDetection`] into the format expected by the COCO api. Only
-        supports PyTorch.
+        Converts the raw output of [`DeformableDetrForObjectDetection`] into final bounding boxes in (top_left_x,
+        top_left_y, bottom_right_x, bottom_right_y) format. Only supports PyTorch.
 
         Args:
             outputs ([`DetrObjectDetectionOutput`]):

src/transformers/models/detr/image_processing_detr.py

@@ -1222,8 +1222,8 @@ class DetrImageProcessor(BaseImageProcessor):
     # inspired by https://github.com/facebookresearch/detr/blob/master/models/detr.py#L258
     def post_process(self, outputs, target_sizes):
         """
-        Converts the output of [`DetrForObjectDetection`] into the format expected by the COCO api. Only supports
-        PyTorch.
+        Converts the raw output of [`DetrForObjectDetection`] into final bounding boxes in (top_left_x, top_left_y,
+        bottom_right_x, bottom_right_y) format. Only supports PyTorch.
 
         Args:
             outputs ([`DetrObjectDetectionOutput`]):
@@ -1499,8 +1499,8 @@ class DetrImageProcessor(BaseImageProcessor):
         self, outputs, threshold: float = 0.5, target_sizes: Union[TensorType, List[Tuple]] = None
     ):
         """
-        Converts the output of [`DetrForObjectDetection`] into the format expected by the COCO api. Only supports
-        PyTorch.
+        Converts the raw output of [`DetrForObjectDetection`] into final bounding boxes in (top_left_x, top_left_y,
+        bottom_right_x, bottom_right_y) format. Only supports PyTorch.
 
         Args:
             outputs ([`DetrObjectDetectionOutput`]):

src/transformers/models/owlvit/image_processing_owlvit.py

@@ -329,7 +329,8 @@ class OwlViTImageProcessor(BaseImageProcessor):
 
     def post_process(self, outputs, target_sizes):
         """
-        Converts the output of [`OwlViTForObjectDetection`] into the format expected by the COCO api.
+        Converts the raw output of [`OwlViTForObjectDetection`] into final bounding boxes in (top_left_x, top_left_y,
+        bottom_right_x, bottom_right_y) format.
 
         Args:
             outputs ([`OwlViTObjectDetectionOutput`]):

src/transformers/models/yolos/image_processing_yolos.py

@@ -1116,14 +1116,14 @@ class YolosImageProcessor(BaseImageProcessor):
         return encoded_inputs
 
     # POSTPROCESSING METHODS - TODO: add support for other frameworks
-    # Copied from transformers.models.detr.image_processing_detr.DetrImageProcessor.post_process
+    # Copied from transformers.models.detr.image_processing_detr.DetrImageProcessor.post_process  with Detr->Yolos
     def post_process(self, outputs, target_sizes):
         """
-        Converts the output of [`DetrForObjectDetection`] into the format expected by the COCO api. Only supports
-        PyTorch.
+        Converts the raw output of [`YolosForObjectDetection`] into final bounding boxes in (top_left_x, top_left_y,
+        bottom_right_x, bottom_right_y) format. Only supports PyTorch.
 
         Args:
-            outputs ([`DetrObjectDetectionOutput`]):
+            outputs ([`YolosObjectDetectionOutput`]):
                 Raw outputs of the model.
             target_sizes (`torch.Tensor` of shape `(batch_size, 2)`):
                 Tensor containing the size (height, width) of each image of the batch. For evaluation, this must be the
@@ -1164,8 +1164,8 @@ class YolosImageProcessor(BaseImageProcessor):
         self, outputs, threshold: float = 0.5, target_sizes: Union[TensorType, List[Tuple]] = None
     ):
         """
-        Converts the output of [`YolosForObjectDetection`] into the format expected by the COCO api. Only supports
-        PyTorch.
+        Converts the raw output of [`YolosForObjectDetection`] into final bounding boxes in (top_left_x, top_left_y,
+        bottom_right_x, bottom_right_y) format. Only supports PyTorch.
 
         Args:
             outputs ([`YolosObjectDetectionOutput`]):