diff --git a/README.md b/README.md
index 4afb7d9fd7f8a1cdd4a5d9de0357304169da067a..3961bff3a8b8192fa900a5ac3717a707e7e1bc9f 100644
--- a/README.md
+++ b/README.md
@@ -33,7 +33,7 @@ Download the trained models at [Onedrive](https://mailstsinghuaeducn-my.sharepoi
 
 
 ## Requirements
-* Ubuntu 16.04/18.04/20.04, CUDA 10.1/10.2, python >= 3.6, PyTorch >= 1.6, torchvision
+* Ubuntu 16.04/18.04/20.04, CUDA 10.1/10.2/11.6, python >= 3.7, PyTorch >= 1.9, torchvision
 * Install `detectron2` from [source](https://github.com/facebookresearch/detectron2)
 * `sh scripts/install_deps.sh`
 * Compile the cpp extension for `farthest points sampling (fps)`: