Fix snippets
Browse files
    	
        README.md
    CHANGED
    
    | @@ -38,7 +38,7 @@ Here is how to use this model: | |
| 38 | 
             
            from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation
         | 
| 39 | 
             
            from PIL import Image
         | 
| 40 | 
             
            import requests
         | 
| 41 | 
            -
            url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/ | 
| 42 | 
             
            image = Image.open(requests.get(url, stream=True).raw)
         | 
| 43 |  | 
| 44 | 
             
            # Loading a single model for all three tasks
         | 
| @@ -49,19 +49,19 @@ model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_ad | |
| 49 | 
             
            semantic_inputs = processor(images=image, task_inputs=["semantic"], return_tensors="pt")
         | 
| 50 | 
             
            semantic_outputs = model(**semantic_inputs)
         | 
| 51 | 
             
            # pass through image_processor for postprocessing
         | 
| 52 | 
            -
            predicted_semantic_map = processor.post_process_semantic_segmentation( | 
| 53 |  | 
| 54 | 
             
            # Instance Segmentation
         | 
| 55 | 
             
            instance_inputs = processor(images=image, task_inputs=["instance"], return_tensors="pt")
         | 
| 56 | 
             
            instance_outputs = model(**instance_inputs)
         | 
| 57 | 
             
            # pass through image_processor for postprocessing
         | 
| 58 | 
            -
            predicted_instance_map = processor.post_process_instance_segmentation( | 
| 59 |  | 
| 60 | 
             
            # Panoptic Segmentation
         | 
| 61 | 
             
            panoptic_inputs = processor(images=image, task_inputs=["panoptic"], return_tensors="pt")
         | 
| 62 | 
             
            panoptic_outputs = model(**panoptic_inputs)
         | 
| 63 | 
             
            # pass through image_processor for postprocessing
         | 
| 64 | 
            -
            predicted_semantic_map = processor.post_process_panoptic_segmentation( | 
| 65 | 
             
            ```
         | 
| 66 |  | 
| 67 | 
             
            For more examples, please refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/oneformer).
         | 
|  | |
| 38 | 
             
            from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation
         | 
| 39 | 
             
            from PIL import Image
         | 
| 40 | 
             
            import requests
         | 
| 41 | 
            +
            url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/resolve/main/ade20k.jpeg"
         | 
| 42 | 
             
            image = Image.open(requests.get(url, stream=True).raw)
         | 
| 43 |  | 
| 44 | 
             
            # Loading a single model for all three tasks
         | 
|  | |
| 49 | 
             
            semantic_inputs = processor(images=image, task_inputs=["semantic"], return_tensors="pt")
         | 
| 50 | 
             
            semantic_outputs = model(**semantic_inputs)
         | 
| 51 | 
             
            # pass through image_processor for postprocessing
         | 
| 52 | 
            +
            predicted_semantic_map = processor.post_process_semantic_segmentation(semantic_outputs, target_sizes=[image.size[::-1]])[0]
         | 
| 53 |  | 
| 54 | 
             
            # Instance Segmentation
         | 
| 55 | 
             
            instance_inputs = processor(images=image, task_inputs=["instance"], return_tensors="pt")
         | 
| 56 | 
             
            instance_outputs = model(**instance_inputs)
         | 
| 57 | 
             
            # pass through image_processor for postprocessing
         | 
| 58 | 
            +
            predicted_instance_map = processor.post_process_instance_segmentation(instance_outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
         | 
| 59 |  | 
| 60 | 
             
            # Panoptic Segmentation
         | 
| 61 | 
             
            panoptic_inputs = processor(images=image, task_inputs=["panoptic"], return_tensors="pt")
         | 
| 62 | 
             
            panoptic_outputs = model(**panoptic_inputs)
         | 
| 63 | 
             
            # pass through image_processor for postprocessing
         | 
| 64 | 
            +
            predicted_semantic_map = processor.post_process_panoptic_segmentation(panoptic_outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
         | 
| 65 | 
             
            ```
         | 
| 66 |  | 
| 67 | 
             
            For more examples, please refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/oneformer).
         | 

