Update instance image link and add prediction inputs

chapters/en/Unit 3 - Vision Transformers/oneformer.mdx

@@ -48,7 +48,7 @@ In summary, OneFormer represents a significant step towards universal and access
 from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation
 from PIL import Image
 import requests
-url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/ade20k.jpeg"
+url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/resolve/main/ade20k.jpeg"
 image = Image.open(requests.get(url, stream=True).raw)
 
 # Loading a single model for all three tasks
@@ -59,19 +59,19 @@ model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_ad
 semantic_inputs = processor(images=image, task_inputs=["semantic"], return_tensors="pt")
 semantic_outputs = model(**semantic_inputs)
 # pass through image_processor for postprocessing
-predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
+predicted_semantic_map = processor.post_process_semantic_segmentation(semantic_outputs, target_sizes=[image.size[::-1]])[0]
 
 # Instance Segmentation
 instance_inputs = processor(images=image, task_inputs=["instance"], return_tensors="pt")
 instance_outputs = model(**instance_inputs)
 # pass through image_processor for postprocessing
-predicted_instance_map = processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
+predicted_instance_map = processor.post_process_instance_segmentation(instance_outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
 
 # Panoptic Segmentation
 panoptic_inputs = processor(images=image, task_inputs=["panoptic"], return_tensors="pt")
 panoptic_outputs = model(**panoptic_inputs)
 # pass through image_processor for postprocessing
-predicted_semantic_map = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
+predicted_semantic_map = processor.post_process_panoptic_segmentation(panoptic_outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
 
 ```
 ## References