fix readme

README.md

@@ -78,8 +78,8 @@ We provided the pretrained model weithts of our **ST-GCN**. The model weights ca
 ```
 bash tools/get_models.sh
 ```
-The downloaded models will be stored under ```./models```.
-<!-- If you get an error message after running above command, you can also obtain models from [GoogleDrive](https://drive.google.com/open?id=1koTe3ces06NCntVdfLxF7O2Z4l_5csnX) or [BaiduYun](https://pan.baidu.com/s/1dwKG2TLvG-R1qeIiE4MjeA#list/path=%2FShare%2FAAAI18%2Fst-gcn&parentPath=%2FShare), and manually put them into ```./models```. -->
+<!-- The downloaded models will be stored under ```./models```. -->
+You can also obtain models from [GoogleDrive](https://drive.google.com/open?id=1koTe3ces06NCntVdfLxF7O2Z4l_5csnX) or [BaiduYun](https://pan.baidu.com/s/1dwKG2TLvG-R1qeIiE4MjeA#list/path=%2FShare%2FAAAI18%2Fst-gcn&parentPath=%2FShare), and manually put them into ```./models```.
 
 ## Demo
 To visualize how ST-GCN exploit local correlation and local pattern, we compute the feature vector magnitude of each node in the final spatial temporal graph, and overlay them on the original video. **Openpose** should be ready for extracting human skeletons from videos. The skeleton based action recognition results is also shwon thereon.