diff --git a/applications/lpcnet/README.md b/applications/lpcnet/README.md
index c0ce5cf2..42f0d8ec 100644
--- a/applications/lpcnet/README.md
+++ b/applications/lpcnet/README.md
@@ -1,6 +1,7 @@
 # Introduction
 This tool converts the lpcnet model to onnx.
 To run this code, we need first install the original lpcnet model from <https://github.com/mozilla/LPCNet/>.
+Note that lpcnet is not a package, so please add its directory to the path.
 Then run
 ```
 python convert_lpcnet_to_onnx.py [model_file]
diff --git a/applications/mrcnn_onnx/README.md b/applications/mrcnn_onnx/README.md
index 7b62d30e..22453e1c 100644
--- a/applications/mrcnn_onnx/README.md
+++ b/applications/mrcnn_onnx/README.md
@@ -1,9 +1,4 @@
 # Introduction 
-The original Keras project of Masked RCNN is: <https://github.com/matterport/Mask_RCNN>. And follow the 'Installation' section in README.md to set up the model. Actually, there is also a good tutorial <https://github.com/matterport/Mask_RCNN#step-by-step-detection> to learn about the object detection.
+The original Keras project of Masked RCNN is: <https://github.com/matterport/Mask_RCNN>. Follow the 'Installation' section in README.md to set up the model. There is also a good [tutorial](https://github.com/matterport/Mask_RCNN#step-by-step-detection) to learn about the object detection.
 
-# Convert
-```
-cd <Mask_RCNN directory>
-pip install -e .
-python MaskedRCNN.py
-```
+Currently, conversion code for this model is not ready to be checked in.
\ No newline at end of file
diff --git a/applications/yolov3/README.md b/applications/yolov3/README.md
index c0d950c1..ad640c74 100644
--- a/applications/yolov3/README.md
+++ b/applications/yolov3/README.md
@@ -1,9 +1,5 @@
 # Introduction 
 The original keras model was coming from: <https://github.com/qqwweee/keras-yolo3>, clone the project and follow the 'Quick Start' to get the pre-trained model.
 
-# Convert
-```
-export PYTHONPATH=$(the keras-yolo3 path) 
-python yolov3.py -c  # convert the model into the ONNX
-python yolov3.py data/test.jpg # run a detect example
-```
+We have converted yolov3 model successfully and uploaded to the model zoo. Currently, conversion code for this model is not ready to be checked in,
+so please use our pretrained yolov3 onnx model in the model zoo <https://github.com/onnx/models/tree/master/yolov3>
\ No newline at end of file