From 67b1335cb9b3cb39e290c0afad424816daf7e357 Mon Sep 17 00:00:00 2001
From: NielsRogge <48327001+NielsRogge@users.noreply.github.com>
Date: Mon, 11 Dec 2023 19:03:42 +0100
Subject: [PATCH] Update bounding box format everywhere (#27944)

Update formats
---
 docs/source/en/model_doc/detr.md                              | 2 +-
 docs/source/en/model_doc/owlv2.md                             | 2 +-
 docs/source/en/model_doc/owlvit.md                            | 2 +-
 docs/source/en/tasks/object_detection.md                      | 2 +-
 docs/source/ja/tasks/object_detection.md                      | 2 +-
 docs/source/ko/tasks/object_detection.md                      | 2 +-
 .../conditional_detr/image_processing_conditional_detr.py     | 4 ++--
 .../models/conditional_detr/modeling_conditional_detr.py      | 2 +-
 .../models/deformable_detr/modeling_deformable_detr.py        | 2 +-
 src/transformers/models/deta/modeling_deta.py                 | 2 +-
 src/transformers/models/detr/modeling_detr.py                 | 2 +-
 src/transformers/models/owlv2/modeling_owlv2.py               | 2 +-
 src/transformers/models/owlvit/modeling_owlvit.py             | 2 +-
 .../models/table_transformer/modeling_table_transformer.py    | 2 +-
 src/transformers/models/yolos/modeling_yolos.py               | 2 +-
 15 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/docs/source/en/model_doc/detr.md b/docs/source/en/model_doc/detr.md
index c36bd4380e..60937b6012 100644
--- a/docs/source/en/model_doc/detr.md
+++ b/docs/source/en/model_doc/detr.md
@@ -146,7 +146,7 @@ As a summary, consider the following table:
 | **Model** | [`~transformers.DetrForObjectDetection`] | [`~transformers.DetrForSegmentation`] | [`~transformers.DetrForSegmentation`] |
 | **Example dataset** | COCO detection | COCO detection, COCO panoptic | COCO panoptic  |                                                                        |
 | **Format of annotations to provide to**  [`~transformers.DetrImageProcessor`] | {'image_id': `int`, 'annotations': `List[Dict]`} each Dict being a COCO object annotation  | {'image_id': `int`, 'annotations': `List[Dict]`}  (in case of COCO detection) or {'file_name': `str`, 'image_id': `int`, 'segments_info': `List[Dict]`} (in case of COCO panoptic) | {'file_name': `str`, 'image_id': `int`, 'segments_info': `List[Dict]`} and masks_path (path to directory containing PNG files of the masks) |
-| **Postprocessing** (i.e. converting the output of the model to COCO API) | [`~transformers.DetrImageProcessor.post_process`] | [`~transformers.DetrImageProcessor.post_process_segmentation`] | [`~transformers.DetrImageProcessor.post_process_segmentation`], [`~transformers.DetrImageProcessor.post_process_panoptic`] |
+| **Postprocessing** (i.e. converting the output of the model to Pascal VOC format) | [`~transformers.DetrImageProcessor.post_process`] | [`~transformers.DetrImageProcessor.post_process_segmentation`] | [`~transformers.DetrImageProcessor.post_process_segmentation`], [`~transformers.DetrImageProcessor.post_process_panoptic`] |
 | **evaluators** | `CocoEvaluator` with `iou_types="bbox"` | `CocoEvaluator` with `iou_types="bbox"` or `"segm"` | `CocoEvaluator` with `iou_tupes="bbox"` or `"segm"`, `PanopticEvaluator` |
 
 In short, one should prepare the data either in COCO detection or COCO panoptic format, then use
diff --git a/docs/source/en/model_doc/owlv2.md b/docs/source/en/model_doc/owlv2.md
index 12000af9ed..75fab0853a 100644
--- a/docs/source/en/model_doc/owlv2.md
+++ b/docs/source/en/model_doc/owlv2.md
@@ -56,7 +56,7 @@ OWLv2 is, just like its predecessor [OWL-ViT](owlvit), a zero-shot text-conditio
 
 >>> # Target image sizes (height, width) to rescale box predictions [batch_size, 2]
 >>> target_sizes = torch.Tensor([image.size[::-1]])
->>> # Convert outputs (bounding boxes and class logits) to COCO API
+>>> # Convert outputs (bounding boxes and class logits) to Pascal VOC Format (xmin, ymin, xmax, ymax)
 >>> results = processor.post_process_object_detection(outputs=outputs, target_sizes=target_sizes, threshold=0.1)
 >>> i = 0  # Retrieve predictions for the first image for the corresponding text queries
 >>> text = texts[i]
diff --git a/docs/source/en/model_doc/owlvit.md b/docs/source/en/model_doc/owlvit.md
index 0ba26eeb37..c40d3a9e7a 100644
--- a/docs/source/en/model_doc/owlvit.md
+++ b/docs/source/en/model_doc/owlvit.md
@@ -55,7 +55,7 @@ OWL-ViT is a zero-shot text-conditioned object detection model. OWL-ViT uses [CL
 
 >>> # Target image sizes (height, width) to rescale box predictions [batch_size, 2]
 >>> target_sizes = torch.Tensor([image.size[::-1]])
->>> # Convert outputs (bounding boxes and class logits) to COCO API
+>>> # Convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
 >>> results = processor.post_process_object_detection(outputs=outputs, target_sizes=target_sizes, threshold=0.1)
 >>> i = 0  # Retrieve predictions for the first image for the corresponding text queries
 >>> text = texts[i]
diff --git a/docs/source/en/tasks/object_detection.md b/docs/source/en/tasks/object_detection.md
index 7511ee66dd..6f53655e7c 100644
--- a/docs/source/en/tasks/object_detection.md
+++ b/docs/source/en/tasks/object_detection.md
@@ -512,7 +512,7 @@ Finally, load the metrics and run the evaluation.
 ...         outputs = model(pixel_values=pixel_values, pixel_mask=pixel_mask)
 
 ...         orig_target_sizes = torch.stack([target["orig_size"] for target in labels], dim=0)
-...         results = im_processor.post_process(outputs, orig_target_sizes)  # convert outputs of model to COCO api
+...         results = im_processor.post_process(outputs, orig_target_sizes)  # convert outputs of model to Pascal VOC format (xmin, ymin, xmax, ymax)
 
 ...         module.add(prediction=results, reference=labels)
 ...         del batch
diff --git a/docs/source/ja/tasks/object_detection.md b/docs/source/ja/tasks/object_detection.md
index 845a259cd7..389e7bdf2f 100644
--- a/docs/source/ja/tasks/object_detection.md
+++ b/docs/source/ja/tasks/object_detection.md
@@ -518,7 +518,7 @@ DETR モデルをトレーニングできる「ラベル」。画像プロセッ
 ...         outputs = model(pixel_values=pixel_values, pixel_mask=pixel_mask)
 
 ...         orig_target_sizes = torch.stack([target["orig_size"] for target in labels], dim=0)
-...         results = im_processor.post_process(outputs, orig_target_sizes)  # convert outputs of model to COCO api
+...         results = im_processor.post_process(outputs, orig_target_sizes)  # convert outputs of model to Pascal VOC format (xmin, ymin, xmax, ymax)
 
 ...         module.add(prediction=results, reference=labels)
 ...         del batch
diff --git a/docs/source/ko/tasks/object_detection.md b/docs/source/ko/tasks/object_detection.md
index ca384d0381..0076bba6f8 100644
--- a/docs/source/ko/tasks/object_detection.md
+++ b/docs/source/ko/tasks/object_detection.md
@@ -504,7 +504,7 @@ COCO 데이터 세트를 빌드하는 API는 데이터를 특정 형식으로 
 ...         outputs = model(pixel_values=pixel_values, pixel_mask=pixel_mask)
 
 ...         orig_target_sizes = torch.stack([target["orig_size"] for target in labels], dim=0)
-...         results = im_processor.post_process(outputs, orig_target_sizes)  # convert outputs of model to COCO api
+...         results = im_processor.post_process(outputs, orig_target_sizes)  # convert outputs of model to Pascal VOC format (xmin, ymin, xmax, ymax)
 
 ...         module.add(prediction=results, reference=labels)
 ...         del batch
diff --git a/src/transformers/models/conditional_detr/image_processing_conditional_detr.py b/src/transformers/models/conditional_detr/image_processing_conditional_detr.py
index 3ec0696430..23e493e08b 100644
--- a/src/transformers/models/conditional_detr/image_processing_conditional_detr.py
+++ b/src/transformers/models/conditional_detr/image_processing_conditional_detr.py
@@ -1330,8 +1330,8 @@ class ConditionalDetrImageProcessor(BaseImageProcessor):
     # POSTPROCESSING METHODS - TODO: add support for other frameworks
     def post_process(self, outputs, target_sizes):
         """
-        Converts the output of [`ConditionalDetrForObjectDetection`] into the format expected by the COCO api. Only
-        supports PyTorch.
+        Converts the output of [`ConditionalDetrForObjectDetection`] into the format expected by the Pascal VOC format (xmin, ymin, xmax, ymax).
+        Only supports PyTorch.
 
         Args:
             outputs ([`ConditionalDetrObjectDetectionOutput`]):
diff --git a/src/transformers/models/conditional_detr/modeling_conditional_detr.py b/src/transformers/models/conditional_detr/modeling_conditional_detr.py
index fd9a9d7e6f..d903abffaf 100644
--- a/src/transformers/models/conditional_detr/modeling_conditional_detr.py
+++ b/src/transformers/models/conditional_detr/modeling_conditional_detr.py
@@ -1805,7 +1805,7 @@ class ConditionalDetrForObjectDetection(ConditionalDetrPreTrainedModel):
 
         >>> outputs = model(**inputs)
 
-        >>> # convert outputs (bounding boxes and class logits) to COCO API
+        >>> # convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
         >>> target_sizes = torch.tensor([image.size[::-1]])
         >>> results = image_processor.post_process_object_detection(outputs, threshold=0.5, target_sizes=target_sizes)[
         ...     0
diff --git a/src/transformers/models/deformable_detr/modeling_deformable_detr.py b/src/transformers/models/deformable_detr/modeling_deformable_detr.py
index 2a93fc2aa0..3767eef039 100755
--- a/src/transformers/models/deformable_detr/modeling_deformable_detr.py
+++ b/src/transformers/models/deformable_detr/modeling_deformable_detr.py
@@ -1900,7 +1900,7 @@ class DeformableDetrForObjectDetection(DeformableDetrPreTrainedModel):
         >>> inputs = image_processor(images=image, return_tensors="pt")
         >>> outputs = model(**inputs)
 
-        >>> # convert outputs (bounding boxes and class logits) to COCO API
+        >>> # convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
         >>> target_sizes = torch.tensor([image.size[::-1]])
         >>> results = image_processor.post_process_object_detection(outputs, threshold=0.5, target_sizes=target_sizes)[
         ...     0
diff --git a/src/transformers/models/deta/modeling_deta.py b/src/transformers/models/deta/modeling_deta.py
index 19f0250e6f..8362b49eee 100644
--- a/src/transformers/models/deta/modeling_deta.py
+++ b/src/transformers/models/deta/modeling_deta.py
@@ -1851,7 +1851,7 @@ class DetaForObjectDetection(DetaPreTrainedModel):
         >>> inputs = image_processor(images=image, return_tensors="pt")
         >>> outputs = model(**inputs)
 
-        >>> # convert outputs (bounding boxes and class logits) to COCO API
+        >>> # convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
         >>> target_sizes = torch.tensor([image.size[::-1]])
         >>> results = image_processor.post_process_object_detection(outputs, threshold=0.5, target_sizes=target_sizes)[
         ...     0
diff --git a/src/transformers/models/detr/modeling_detr.py b/src/transformers/models/detr/modeling_detr.py
index 9b73d0e651..e0680e1874 100644
--- a/src/transformers/models/detr/modeling_detr.py
+++ b/src/transformers/models/detr/modeling_detr.py
@@ -1535,7 +1535,7 @@ class DetrForObjectDetection(DetrPreTrainedModel):
         >>> inputs = image_processor(images=image, return_tensors="pt")
         >>> outputs = model(**inputs)
 
-        >>> # convert outputs (bounding boxes and class logits) to COCO API
+        >>> # convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
         >>> target_sizes = torch.tensor([image.size[::-1]])
         >>> results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[
         ...     0
diff --git a/src/transformers/models/owlv2/modeling_owlv2.py b/src/transformers/models/owlv2/modeling_owlv2.py
index 6cc996966b..5146fbb89d 100644
--- a/src/transformers/models/owlv2/modeling_owlv2.py
+++ b/src/transformers/models/owlv2/modeling_owlv2.py
@@ -1576,7 +1576,7 @@ class Owlv2ForObjectDetection(Owlv2PreTrainedModel):
 
         >>> target_sizes = torch.Tensor([unnormalized_image.size[::-1]])
 
-        >>> # Convert outputs (bounding boxes and class logits) to COCO API
+        >>> # Convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
         >>> results = processor.post_process_image_guided_detection(
         ...     outputs=outputs, threshold=0.9, nms_threshold=0.3, target_sizes=target_sizes
         ... )
diff --git a/src/transformers/models/owlvit/modeling_owlvit.py b/src/transformers/models/owlvit/modeling_owlvit.py
index 8c502c410d..b8e8a36fec 100644
--- a/src/transformers/models/owlvit/modeling_owlvit.py
+++ b/src/transformers/models/owlvit/modeling_owlvit.py
@@ -1517,7 +1517,7 @@ class OwlViTForObjectDetection(OwlViTPreTrainedModel):
         ...     outputs = model.image_guided_detection(**inputs)
         >>> # Target image sizes (height, width) to rescale box predictions [batch_size, 2]
         >>> target_sizes = torch.Tensor([image.size[::-1]])
-        >>> # Convert outputs (bounding boxes and class logits) to COCO API
+        >>> # Convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
         >>> results = processor.post_process_image_guided_detection(
         ...     outputs=outputs, threshold=0.6, nms_threshold=0.3, target_sizes=target_sizes
         ... )
diff --git a/src/transformers/models/table_transformer/modeling_table_transformer.py b/src/transformers/models/table_transformer/modeling_table_transformer.py
index 92aac58e74..81afcdc9c1 100644
--- a/src/transformers/models/table_transformer/modeling_table_transformer.py
+++ b/src/transformers/models/table_transformer/modeling_table_transformer.py
@@ -1431,7 +1431,7 @@ class TableTransformerForObjectDetection(TableTransformerPreTrainedModel):
         >>> inputs = image_processor(images=image, return_tensors="pt")
         >>> outputs = model(**inputs)
 
-        >>> # convert outputs (bounding boxes and class logits) to COCO API
+        >>> # convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
         >>> target_sizes = torch.tensor([image.size[::-1]])
         >>> results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[
         ...     0
diff --git a/src/transformers/models/yolos/modeling_yolos.py b/src/transformers/models/yolos/modeling_yolos.py
index b2f0ca0db5..65ffbfced4 100755
--- a/src/transformers/models/yolos/modeling_yolos.py
+++ b/src/transformers/models/yolos/modeling_yolos.py
@@ -756,7 +756,7 @@ class YolosForObjectDetection(YolosPreTrainedModel):
         >>> inputs = image_processor(images=image, return_tensors="pt")
         >>> outputs = model(**inputs)
 
-        >>> # convert outputs (bounding boxes and class logits) to COCO API
+        >>> # convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
         >>> target_sizes = torch.tensor([image.size[::-1]])
         >>> results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[
         ...     0