diff --git a/samples/dnn/dnn_model_runner/dnn_conversion/paddlepaddle/README.md b/samples/dnn/dnn_model_runner/dnn_conversion/paddlepaddle/README.md
index 3dd4e054c5..7aba491c9d 100644
--- a/samples/dnn/dnn_model_runner/dnn_conversion/paddlepaddle/README.md
+++ b/samples/dnn/dnn_model_runner/dnn_conversion/paddlepaddle/README.md
@@ -1,6 +1,18 @@
 # Run PaddlePaddle model by OpenCV
 
-This tutorial shows how to run PaddlePaddle model by opencv, run the example code as below,
+This tutorial shows how to run PaddlePaddle model by opencv.
+
+## Environment Setup
+
+```shell
+pip install paddlepaddle-gpu
+pip install paddlehub
+pip install paddle2onnx
+```
+
+## Run PaddlePaddle model demo
+
+Run the example code as below,
 
 ```shell
 python paddle_resnet50.py
@@ -8,6 +20,6 @@ python paddle_resnet50.py
 
 there are 3 part of this execution
 
-- 1. Export PaddlePaddle ResNet50 model to onnx format
-- 2. Use `cv2.dnn.readNetFromONNX` load model file
-- 3. Preprocess image file and do inference
+- 1. Export PaddlePaddle ResNet50 model to onnx format;
+- 2. Use `cv2.dnn.readNetFromONNX` load model file;
+- 3. Preprocess image file and do inference.
diff --git a/samples/dnn/dnn_model_runner/dnn_conversion/requirements.txt b/samples/dnn/dnn_model_runner/dnn_conversion/requirements.txt
index 555ce099c1..eb217e27df 100644
--- a/samples/dnn/dnn_model_runner/dnn_conversion/requirements.txt
+++ b/samples/dnn/dnn_model_runner/dnn_conversion/requirements.txt
@@ -10,4 +10,5 @@ tensorflow-gpu>=2.1.0
 
 paddlepaddle>=2.0.0
 paddlepaddle-gpu>=2.0.0
+paddlehub>=2.1.0
 paddle2onnx>=0.5.1