diff --git a/README.md b/README.md
index 105c9fa..5ce14ac 100644
--- a/README.md
+++ b/README.md
@@ -21,7 +21,7 @@ and use the pre-trained ResNet50 model ('resnet50') to generate an image embeddi
 *Write a pipeline with explicit inputs/outputs name specifications:*
 
 ```python
-from towhee.dc2 import pipe, ops, DataCollection
+from towhee import pipe, ops, DataCollection
 
 p = (
     pipe.input('path')