Update README.md

README.md

@@ -31,20 +31,34 @@ You can use the raw model for semantic segmentation. See the [model hub](https:/
 Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
 
 ```python
-from optimum.onnxruntime import ORTModelForSemanticSegmentation
+from transformers import SegformerImageProcessor
 from PIL import Image
 import requests
 
-feature_extractor = SegformerFeatureExtractor.from_pretrained("optimum/segformer-b0-finetuned-ade-512-512")
+from optimum.onnxruntime import ORTModelForSemanticSegmentation
+
+image_processor = SegformerImageProcessor.from_pretrained("optimum/segformer-b0-finetuned-ade-512-512")
 model = ORTModelForSemanticSegmentation.from_pretrained("optimum/segformer-b0-finetuned-ade-512-512")
 
 url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 image = Image.open(requests.get(url, stream=True).raw)
 
-inputs = feature_extractor(images=image, return_tensors="pt")
+inputs = image_processor(images=image, return_tensors="pt").to(device)
 outputs = model(**inputs)
 logits = outputs.logits  # shape (batch_size, num_labels, height/4, width/4)
 ```
+If you use pipeline:
+
+```python
+from transformers import SegformerImageProcessor, pipeline
+from optimum.onnxruntime import ORTModelForSemanticSegmentation
+
+image_processor = SegformerImageProcessor.from_pretrained("optimum/segformer-b0-finetuned-ade-512-512")
+model = ORTModelForSemanticSegmentation.from_pretrained("optimum/segformer-b0-finetuned-ade-512-512")
+
+pipe = pipeline("image-segmentation", model=model, feature_extractor=image_processor)
+pred = pipe(url)
+```
 
 For more code examples, we refer to the [Optimum documentation](https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models).