from transformers import AutoImageProcessor, AutoModelForKeypointMatching
import torch

processor = AutoImageProcessor.from_pretrained("zju-community/matchanything_eloftr")
model = AutoModelForKeypointMatching.from_pretrained("zju-community/matchanything_eloftr")

from transformers.image_utils import load_image
image1 = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg")
image2 = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee_edited.jpg")

images = [image1, image2]

inputs = processor(images, return_tensors="pt")
with torch.no_grad():
    outputs = model(**inputs)

image_sizes = [[(image.height, image.width) for image in images]]

outputs = processor.post_process_keypoint_matching(outputs, image_sizes, threshold=0.2)
print(outputs)

[{'keypoints0': tensor([[4514,  550],
          [4813,  683],
          [1972, 1547],
          ...
          [3916, 3408]], dtype=torch.int32),
  'keypoints1': tensor([[2280,  463],
          [2378,  613],
          [2231,  887],
          ...
          [1521, 2560]], dtype=torch.int32),
  'matching_scores': tensor([0.2189, 0.2073, 0.2414, ...
    ])}]

len(outputs[0]["keypoints0"])
# 401

plot_images = processor.visualize_keypoint_matching(images, outputs)
plot_images

from transformers import pipeline 

image_1 = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"
image_2 = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee_edited.jpg"

pipe = pipeline("keypoint-matching", model="zju-community/matchanything_eloftr")
pipe([image_1, image_2])

[{'keypoint_image_0': {'x': 2444, 'y': 2869},
  'keypoint_image_1': {'x': 837, 'y': 1500},
  'score': 0.9756593704223633},
 {'keypoint_image_0': {'x': 1248, 'y': 2819},
  'keypoint_image_1': {'x': 862, 'y': 866},
  'score': 0.9735618829727173},
 {'keypoint_image_0': {'x': 1547, 'y': 3317},
  'keypoint_image_1': {'x': 1436, 'y': 1500},
  ...
 }
]