Update Readme

README.md

@@ -35,33 +35,33 @@ You can use this particular checkpoint for semantic, instance and panoptic segme
 Here is how to use this model:
 
 ```python
-from transformers import OneFormerFeatureExtractor, OneFormerForUniversalSegmentation
+from transformers import OneFormerImageProcessor, OneFormerForUniversalSegmentation
 from PIL import Image
 import requests
 url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/ade20k.jpeg"
 image = Image.open(requests.get(url, stream=True).raw)
 
 # Loading a single model for all three tasks
-feature_extractor = OneFormerFeatureExtractor.from_pretrained("shi-labs/oneformer_ade20k_dinat_large")
+image_processor = OneFormerImageProcessor.from_pretrained("shi-labs/oneformer_ade20k_dinat_large")
 model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_ade20k_dinat_large")
 
 # Semantic Segmentation
-semantic_inputs = feature_extractor(images=image, ["semantic"] return_tensors="pt")
+semantic_inputs = image_processor(images=image, ["semantic"] return_tensors="pt")
 semantic_outputs = model(**semantic_inputs)
-# pass through feature_extractor for postprocessing
-predicted_semantic_map = feature_extractor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
+# pass through image_processor for postprocessing
+predicted_semantic_map = image_processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
 
 # Instance Segmentation
-instance_inputs = feature_extractor(images=image, ["instance"] return_tensors="pt")
+instance_inputs = image_processor(images=image, ["instance"] return_tensors="pt")
 instance_outputs = model(**instance_inputs)
-# pass through feature_extractor for postprocessing
-predicted_instance_map = feature_extractor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
+# pass through image_processor for postprocessing
+predicted_instance_map = image_processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
 
 # Panoptic Segmentation
-panoptic_inputs = feature_extractor(images=image, ["panoptic"] return_tensors="pt")
+panoptic_inputs = image_processor(images=image, ["panoptic"] return_tensors="pt")
 panoptic_outputs = model(**panoptic_inputs)
-# pass through feature_extractor for postprocessing
-predicted_semantic_map = feature_extractor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
+# pass through image_processor for postprocessing
+predicted_semantic_map = image_processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
 ```
 
 For more examples, please refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/oneformer).