Fix snippet

#2
by merve HF staff - opened
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -39,7 +39,7 @@ Here is how to use this model:
39
  from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation
40
  from PIL import Image
41
  import requests
42
- url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/ade20k.jpeg"
43
  image = Image.open(requests.get(url, stream=True).raw)
44
 
45
  # Loading a single model for all three tasks
@@ -50,19 +50,19 @@ model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_ad
50
  semantic_inputs = processor(images=image, task_inputs=["semantic"], return_tensors="pt")
51
  semantic_outputs = model(**semantic_inputs)
52
  # pass through image_processor for postprocessing
53
- predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
54
 
55
  # Instance Segmentation
56
  instance_inputs = processor(images=image, task_inputs=["instance"], return_tensors="pt")
57
  instance_outputs = model(**instance_inputs)
58
  # pass through image_processor for postprocessing
59
- predicted_instance_map = processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
60
 
61
  # Panoptic Segmentation
62
  panoptic_inputs = processor(images=image, task_inputs=["panoptic"], return_tensors="pt")
63
  panoptic_outputs = model(**panoptic_inputs)
64
  # pass through image_processor for postprocessing
65
- predicted_semantic_map = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
66
  ```
67
 
68
  For more examples, please refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/oneformer).
 
39
  from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation
40
  from PIL import Image
41
  import requests
42
+ url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/resolve/main/ade20k.jpeg"
43
  image = Image.open(requests.get(url, stream=True).raw)
44
 
45
  # Loading a single model for all three tasks
 
50
  semantic_inputs = processor(images=image, task_inputs=["semantic"], return_tensors="pt")
51
  semantic_outputs = model(**semantic_inputs)
52
  # pass through image_processor for postprocessing
53
+ predicted_semantic_map = processor.post_process_semantic_segmentation(semantic_outputs, target_sizes=[image.size[::-1]])[0]
54
 
55
  # Instance Segmentation
56
  instance_inputs = processor(images=image, task_inputs=["instance"], return_tensors="pt")
57
  instance_outputs = model(**instance_inputs)
58
  # pass through image_processor for postprocessing
59
+ predicted_instance_map = processor.post_process_instance_segmentation(instance_outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
60
 
61
  # Panoptic Segmentation
62
  panoptic_inputs = processor(images=image, task_inputs=["panoptic"], return_tensors="pt")
63
  panoptic_outputs = model(**panoptic_inputs)
64
  # pass through image_processor for postprocessing
65
+ predicted_semantic_map = processor.post_process_panoptic_segmentation(panoptic_outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
66
  ```
67
 
68
  For more examples, please refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/oneformer).