Update README.md

Author: BradleyHWQ

README.md

@@ -1,8 +1,9 @@
 # Autoencoder-Image-Compression
 Pytorch implementation for image compression and reconstruction via autoencoder
 
-This is an autoencoder with cylic loss and coding parsing loss for image compression and reconstruction. Network backbone is simple 3-layer 
-fully conv (encoder) and symmetrical for decoder. Finally it can achieve 21 mean PSNR on CLIC dataset (CVPR 2019 workshop).
+This is an autoencoder with cylic loss and coding parsing loss for image compression and reconstruction. Network backbone is simple 3-layer fully conv (encoder) and symmetrical for decoder. Finally it can achieve 21 mean PSNR on CLIC dataset (CVPR 2019 workshop).
+
+![image](http://github.com/RobinWenqian/Autoencoder-Image-Compression/raw/master/Methodology.pdf)
 
 You can download
 training data from this url: https://drive.google.com/drive/folders/1wU1CO6WcQOraIaY2KSk7cRVaAXcm_A2R?usp=sharing