Update README.md

README.md

@@ -10,22 +10,22 @@ To address the conflicts among multiple tasks and meet the different demands of
 Extensive experiments show that the proposed model has a better understanding of the face and achieves excellent performance for all tasks.
 Especially, it achieves 90.97\% accuracy on RAF-DB and 0.22 $\epsilon$-error on CLAP2015, which are state-of-the-art results on facial expression recognition and age estimation respectively.
 
-<img src="/pictures/SwinFace.png" alt="Image" width="500">
+<img src="pictures/SwinFace.png" alt="Image" width="500">
 
 ## Evaluate
 Here are some test results. For detailed experimental information, please refer to our paper.
 
 - Face Recognition
-<img src="https://github.com/lxq1000/SwinFace/blob/main/pictures/face%20recognition.png" alt="Image">
+<img src="pictures/face%20recognition.png" alt="Image">
 
 - Facial Expression Recognition
-<img src="https://github.com/lxq1000/SwinFace/blob/main/pictures/facial%20expression%20recognition.png" alt="Image" width="500">
+<img src="pictures/facial%20expression%20recognition.png" alt="Image" width="500">
 
 - Age Estimation
-<img src="https://github.com/lxq1000/SwinFace/blob/main/pictures/age%20estimation.png" alt="Image" width="400">
+<img src="pictures/age%20estimation.png" alt="Image" width="400">
 
 - Facial Attribute Estimation  
-<img src="https://github.com/lxq1000/SwinFace/blob/main/pictures/facial%20attribute%20estimation.png" alt="Image">
+<img src="pictures/facial%20attribute%20estimation.png" alt="Image">