Update README.md (#2)

- Update README.md (a9cab345b6535b421dab2da9a3984aa00143230e)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -20,7 +20,7 @@ Cumulatively, they make LightGlue more efficient – in terms of both memory and
 easier to train. One key property is that LightGlue is adaptive to the difficulty of the problem: the inference is 
 much faster on image pairs that are intuitively easy to match, for example because of a larger visual overlap or 
 limited appearance change. This opens up exciting prospects for deploying deep matchers in latency-sensitive 
-applications like 3D reconstruction. The code and trained models are publicly available at [github.com/cvg/LightGlue](github.com/cvg/LightGlue).
+applications like 3D reconstruction. The code and trained models are publicly available at [github.com/cvg/LightGlue](https://github.com/cvg/LightGlue).
 
 
 <img src="https://raw.githubusercontent.com/cvg/LightGlue/main/assets/easy_hard.jpg" alt="drawing" width="800"/>