Transformers
Safetensors
superglue
stevenbucaille commited on
Commit
9b7e103
1 Parent(s): dd229be

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -123,7 +123,7 @@ image1_matching_scores = outputs.matching_scores[0, 1][image1_indices]
123
  You can use the `post_process_keypoint_matching` method from the `SuperGlueImageProcessor` to get the keypoints and matches in a more readable format:
124
  ```python
125
  image_sizes = [(image.height, image.width) for image in images]
126
- outputs = processor.post_process_keypoint_matching(outputs, image_sizes, matching_threshold=0.2)
127
  for i, output in enumerate(outputs):
128
  print("For the image pair", i)
129
  for keypoint0, keypoint1, matching_score in zip(output["keypoints0"], output["keypoints1"],
 
123
  You can use the `post_process_keypoint_matching` method from the `SuperGlueImageProcessor` to get the keypoints and matches in a more readable format:
124
  ```python
125
  image_sizes = [(image.height, image.width) for image in images]
126
+ outputs = processor.post_process_keypoint_matching(outputs, image_sizes, threshold=0.2)
127
  for i, output in enumerate(outputs):
128
  print("For the image pair", i)
129
  for keypoint0, keypoint1, matching_score in zip(output["keypoints0"], output["keypoints1"],