Fix post process function called in the instance segmentation example of mask2former (#34588)

* Fix post process function called in the instance segmentation example of mask2former

* fix description and additional notes for post_process_instance_segmentation of maskformers

* remove white space in maskformers post_process_instance_segmentation doc

* change image.size[::-1] to height and width for clarity in segmentation examples

docs/source/en/model_doc/rt_detr.md

@@ -57,7 +57,7 @@ Initially, an image is processed using a pre-trained convolutional neural networ
 >>> with torch.no_grad():
 ...     outputs = model(**inputs)
 
->>> results = image_processor.post_process_object_detection(outputs, target_sizes=torch.tensor([image.size[::-1]]), threshold=0.3)
+>>> results = image_processor.post_process_object_detection(outputs, target_sizes=torch.tensor([(image.height, image.width)]), threshold=0.3)
 
 >>> for result in results:
 ...     for score, label_id, box in zip(result["scores"], result["labels"], result["boxes"]):

examples/pytorch/instance-segmentation/README.md

@@ -148,7 +148,7 @@ with torch.no_grad():
     outputs = model(**inputs)
 
 # Post-process outputs
-outputs = image_processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])
+outputs = image_processor.post_process_instance_segmentation(outputs, target_sizes=[(image.height, image.width)])
 
 print("Mask shape: ", outputs[0]["segmentation"].shape)
 print("Mask values: ", outputs[0]["segmentation"].unique())

src/transformers/models/mask2former/image_processing_mask2former.py

@@ -1034,7 +1034,8 @@ class Mask2FormerImageProcessor(BaseImageProcessor):
     ) -> List[Dict]:
         """
         Converts the output of [`Mask2FormerForUniversalSegmentationOutput`] into instance segmentation predictions.
-        Only supports PyTorch.
+        Only supports PyTorch. If instances could overlap, set either return_coco_annotation or return_binary_maps
+        to `True` to get the correct segmentation result.
 
         Args:
             outputs ([`Mask2FormerForUniversalSegmentation`]):
@@ -1056,9 +1057,10 @@ class Mask2FormerImageProcessor(BaseImageProcessor):
                 (one per detected instance).
         Returns:
             `List[Dict]`: A list of dictionaries, one per image, each dictionary containing two keys:
-            - **segmentation** -- A tensor of shape `(height, width)` where each pixel represents a `segment_id` or
+            - **segmentation** -- A tensor of shape `(height, width)` where each pixel represents a `segment_id`, or
               `List[List]` run-length encoding (RLE) of the segmentation map if return_coco_annotation is set to
-              `True`. Set to `None` if no mask if found above `threshold`.
+              `True`, or a tensor of shape `(num_instances, height, width)` if return_binary_maps is set to `True`.
+              Set to `None` if no mask if found above `threshold`.
             - **segments_info** -- A dictionary that contains additional information on each segment.
                 - **id** -- An integer representing the `segment_id`.
                 - **label_id** -- An integer representing the label / semantic class id corresponding to `segment_id`.

src/transformers/models/mask2former/modeling_mask2former.py

@@ -2428,8 +2428,8 @@ class Mask2FormerForUniversalSegmentation(Mask2FormerPreTrainedModel):
         >>> masks_queries_logits = outputs.masks_queries_logits
 
         >>> # Perform post-processing to get instance segmentation map
-        >>> pred_instance_map = image_processor.post_process_semantic_segmentation(
-        ...     outputs, target_sizes=[image.size[::-1]]
+        >>> pred_instance_map = image_processor.post_process_instance_segmentation(
+        ...     outputs, target_sizes=[(image.height, image.width)]
         ... )[0]
         >>> print(pred_instance_map.shape)
         torch.Size([480, 640])
@@ -2462,7 +2462,7 @@ class Mask2FormerForUniversalSegmentation(Mask2FormerPreTrainedModel):
 
         >>> # Perform post-processing to get semantic segmentation map
         >>> pred_semantic_map = image_processor.post_process_semantic_segmentation(
-        ...     outputs, target_sizes=[image.size[::-1]]
+        ...     outputs, target_sizes=[(image.height, image.width)]
         ... )[0]
         >>> print(pred_semantic_map.shape)
         torch.Size([512, 683])
@@ -2496,7 +2496,7 @@ class Mask2FormerForUniversalSegmentation(Mask2FormerPreTrainedModel):
 
         >>> # Perform post-processing to get panoptic segmentation map
         >>> pred_panoptic_map = image_processor.post_process_panoptic_segmentation(
-        ...     outputs, target_sizes=[image.size[::-1]]
+        ...     outputs, target_sizes=[(image.height, image.width)]
         ... )[0]["segmentation"]
         >>> print(pred_panoptic_map.shape)
         torch.Size([338, 676])

src/transformers/models/maskformer/image_processing_maskformer.py

@@ -1080,7 +1080,8 @@ class MaskFormerImageProcessor(BaseImageProcessor):
     ) -> List[Dict]:
         """
         Converts the output of [`MaskFormerForInstanceSegmentationOutput`] into instance segmentation predictions. Only
-        supports PyTorch.
+        supports PyTorch. If instances could overlap, set either return_coco_annotation or return_binary_maps
+        to `True` to get the correct segmentation result.
 
         Args:
             outputs ([`MaskFormerForInstanceSegmentation`]):
@@ -1102,9 +1103,10 @@ class MaskFormerImageProcessor(BaseImageProcessor):
                 (one per detected instance).
         Returns:
             `List[Dict]`: A list of dictionaries, one per image, each dictionary containing two keys:
-            - **segmentation** -- A tensor of shape `(height, width)` where each pixel represents a `segment_id` or
+            - **segmentation** -- A tensor of shape `(height, width)` where each pixel represents a `segment_id`, or
               `List[List]` run-length encoding (RLE) of the segmentation map if return_coco_annotation is set to
-              `True`. Set to `None` if no mask if found above `threshold`.
+              `True`, or a tensor of shape `(num_instances, height, width)` if return_binary_maps is set to `True`.
+              Set to `None` if no mask if found above `threshold`.
             - **segments_info** -- A dictionary that contains additional information on each segment.
                 - **id** -- An integer representing the `segment_id`.
                 - **label_id** -- An integer representing the label / semantic class id corresponding to `segment_id`.

src/transformers/models/maskformer/modeling_maskformer.py

@@ -1780,7 +1780,7 @@ class MaskFormerForInstanceSegmentation(MaskFormerPreTrainedModel):
 
         >>> # you can pass them to image_processor for postprocessing
         >>> predicted_semantic_map = image_processor.post_process_semantic_segmentation(
-        ...     outputs, target_sizes=[image.size[::-1]]
+        ...     outputs, target_sizes=[(image.height, image.width)]
         ... )[0]
 
         >>> # we refer to the demo notebooks for visualization (see "Resources" section in the MaskFormer docs)
@@ -1810,7 +1810,7 @@ class MaskFormerForInstanceSegmentation(MaskFormerPreTrainedModel):
         >>> masks_queries_logits = outputs.masks_queries_logits
 
         >>> # you can pass them to image_processor for postprocessing
-        >>> result = image_processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
+        >>> result = image_processor.post_process_panoptic_segmentation(outputs, target_sizes=[(image.height, image.width)])[0]
 
         >>> # we refer to the demo notebooks for visualization (see "Resources" section in the MaskFormer docs)
         >>> predicted_panoptic_map = result["segmentation"]

src/transformers/models/oneformer/modeling_oneformer.py

@@ -3161,7 +3161,7 @@ class OneFormerForUniversalSegmentation(OneFormerPreTrainedModel):
 
         >>> # you can pass them to processor for semantic postprocessing
         >>> predicted_semantic_map = processor.post_process_semantic_segmentation(
-        ...     outputs, target_sizes=[image.size[::-1]]
+        ...     outputs, target_sizes=[(image.height, image.width)]
         ... )[0]
         >>> f"👉 Semantic Predictions Shape: {list(predicted_semantic_map.shape)}"
         '👉 Semantic Predictions Shape: [512, 683]'
@@ -3178,7 +3178,7 @@ class OneFormerForUniversalSegmentation(OneFormerPreTrainedModel):
 
         >>> # you can pass them to processor for instance postprocessing
         >>> predicted_instance_map = processor.post_process_instance_segmentation(
-        ...     outputs, target_sizes=[image.size[::-1]]
+        ...     outputs, target_sizes=[(image.height, image.width)]
         ... )[0]["segmentation"]
         >>> f"👉 Instance Predictions Shape: {list(predicted_instance_map.shape)}"
         '👉 Instance Predictions Shape: [512, 683]'
@@ -3195,7 +3195,7 @@ class OneFormerForUniversalSegmentation(OneFormerPreTrainedModel):
 
         >>> # you can pass them to processor for panoptic postprocessing
         >>> predicted_panoptic_map = processor.post_process_panoptic_segmentation(
-        ...     outputs, target_sizes=[image.size[::-1]]
+        ...     outputs, target_sizes=[(image.height, image.width)]
         ... )[0]["segmentation"]
         >>> f"👉 Panoptic Predictions Shape: {list(predicted_panoptic_map.shape)}"
         '👉 Panoptic Predictions Shape: [512, 683]'

src/transformers/models/seggpt/modeling_seggpt.py

@@ -962,7 +962,7 @@ class SegGptForImageSegmentation(SegGptPreTrainedModel):
 
         >>> inputs = image_processor(images=image_input, prompt_images=image_prompt, prompt_masks=mask_prompt, return_tensors="pt")
         >>> outputs = model(**inputs)
-        >>> result = image_processor.post_process_semantic_segmentation(outputs, target_sizes=[image_input.size[::-1]])[0]
+        >>> result = image_processor.post_process_semantic_segmentation(outputs, target_sizes=[(image_input.height, image_input.width)])[0]
         >>> print(list(result.shape))
         [170, 297]
         ```