Update README.md

README.md

@@ -35,32 +35,27 @@ fine-tuned versions on a task that interests you.
 Here is how to use this model:
 
 ```python
-import requests
 import torch
 from PIL import Image
-from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation
-
+import requests
+from transformers import SamModel, SamProcessor
 
-# load Mask2Former fine-tuned on COCO panoptic segmentation
-processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-large-coco-panoptic")
-model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-large-coco-panoptic")
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = SamModel.from_pretrained("facebook/sam-vit-huge").to(device)
+processor = SamProcessor.from_pretrained("facebook/sam-vit-huge")
 
-url = "http://images.cocodataset.org/val2017/000000039769.jpg"
-image = Image.open(requests.get(url, stream=True).raw)
-inputs = processor(images=image, return_tensors="pt")
+img_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png"
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB")
+input_points = [[[450, 600]]]  # 2D location of a window in the image
 
+inputs = processor(raw_image, input_points=input_points, return_tensors="pt").to(device)
 with torch.no_grad():
     outputs = model(**inputs)
 
-# model predicts class_queries_logits of shape `(batch_size, num_queries)`
-# and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
-class_queries_logits = outputs.class_queries_logits
-masks_queries_logits = outputs.masks_queries_logits
-
-# you can pass them to processor for postprocessing
-result = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
-# we refer to the demo notebooks for visualization (see "Resources" section in the Mask2Former docs)
-predicted_panoptic_map = result["segmentation"]
+masks = processor.image_processor.post_process_masks(
+    outputs.pred_masks.cpu(), inputs["original_sizes"].cpu(), inputs["reshaped_input_sizes"].cpu()
+)
+scores = outputs.iou_scores
 ```
 
 For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/mask2former).