diff --git a/README.md b/README.md
index ff1514f..c7a2891 100644
--- a/README.md
+++ b/README.md
@@ -10,6 +10,7 @@ All the models are implemented in pytorch/mxnet/tensorflown first, and export a
 
 ## News
 
+- `2 Apr 2021`. [mingyu6yang](https://github.com/mingyu6yang) added a python wrapper for retinaface, [makaveli10](https://github.com/makaveli10) added DenseNet-121.
 - `17 Mar 2021`. [wuzuowuyou](https://github.com/wuzuowuyou) added refinedet, which utilized libtorch to do postprocessing.
 - `5 Mar 2021`. [chgit0214](https://github.com/chgit0214) added the LPRNet.
 - `31 Jan 2021`. RepVGG added by [upczww](https://github.com/upczww).
@@ -82,6 +83,7 @@ Following models are implemented.
 |[repvgg](./repvgg)| RepVGG, pytorch implementation from [DingXiaoH/RepVGG](https://github.com/DingXiaoH/RepVGG) |
 |[lprnet](./lprnet)| LPRNet, pytorch implementation from [xuexingyu24/License_Plate_Detection_Pytorch](https://github.com/xuexingyu24/License_Plate_Detection_Pytorch) |
 |[refinedet](./refinedet)| RefineDet, pytorch implementation from [luuuyi/RefineDet.PyTorch](https://github.com/luuuyi/RefineDet.PyTorch) |
+|[densenet](./densenet)| DenseNet-121, from torchvision.models |
 
 ## Model Zoo
 
diff --git a/densenet/README.md b/densenet/README.md
index 3282287..9d71107 100644
--- a/densenet/README.md
+++ b/densenet/README.md
@@ -1,6 +1,6 @@
 # Densenet121
 
-The Pytorch implementation is [makaveli10/densenet](https://github.com/makaveli10/torchtrtz/tree/main/densenet).
+The Pytorch implementation is [makaveli10/densenet](https://github.com/makaveli10/torchtrtz/tree/main/densenet). Model from torchvision.
 The tensorrt implemenation is taken from [makaveli10/cpptensorrtz](https://github.com/makaveli10/cpptensorrtz/).
 
 ## How to Run
@@ -13,8 +13,8 @@ git clone https://github.com/makaveli10/torchtrtz.git
 
 // go to torchtrtz/densenet
 // Enter these two commands to create densenet121.wts
- $ python models.py
- $ python gen_trtwts.py
+python models.py
+python gen_trtwts.py
 ```
 
 2. build densenet and run
@@ -26,11 +26,12 @@ mkdir build
 cd build
 cmake ..
 make
-sudo ./densenet -s  // serialize model to file i.e. 'LPRnet.engine'
+sudo ./densenet -s  // serialize model to file i.e. 'densenet.engine'
 sudo ./densenet -d  // deserialize model and run inference
 ```
 
 3. Verify output from [torch impl](https://github.com/makaveli10/torchtrtz/blob/main/densenet/README.md)
+
 TensorRT output[:5]:
 ```
     [-0.587389, -0.329202, -1.83404, -1.89935, -0.928404]
diff --git a/refinedet/README.md b/refinedet/README.md
index aaafdb3..4290cf6 100755
--- a/refinedet/README.md
+++ b/refinedet/README.md
@@ -3,6 +3,7 @@
 For the Pytorch implementation, you can refer to [luuuyi/RefineDet.PyTorch](https://github.com/luuuyi/RefineDet.PyTorch)
 
 ## How to run
+
 ```
 1. generate wts file. from pytorch
 python gen_wts_refinedet.py
@@ -19,21 +20,22 @@ make
 ```
 
 ## dependence
+
 ```
 TensorRT7.0.0.11 
 OpenCV >= 3.4
 libtorch >=1.1.0
 ```
 
-
 ## feature
+
 1.tensorrt Multi output  
 2.L2norm  
 3.Postprocessing with libtorch
 
-
 ## More Information
 
 See the readme in [home page.](https://github.com/wang-xinyu/tensorrtx)  
 [tensorrt tutorials](https://github.com/wang-xinyu/tensorrtx/tree/master/tutorials)  
 For more detailed guidance, see [yhl blog](https://www.cnblogs.com/yanghailin/p/14525128.html)
+
diff --git a/retinaface/README.md b/retinaface/README.md
index 6e4aa9b..c5284a9 100644
--- a/retinaface/README.md
+++ b/retinaface/README.md
@@ -44,15 +44,13 @@ sudo ./retina_r50 -d  // deserialize model file and run inference.
 
 3. check the images generated, as follows. 0_result.jpg
 
-4. we  also provide a tensorrt model in python
+4. we also provide a python wrapper
 
-   ```
-   // install python-tensorrt, pycuda, etc.
-   // ensure the retina_r50.engine and libdecodeplugin.so have been built
-   python retinaface_trt.py
-   ```
-
-   
+```
+// install python-tensorrt, pycuda, etc.
+// ensure the retina_r50.engine and libdecodeplugin.so have been built
+python retinaface_trt.py
+```
 
 # INT8 Quantization
 
@@ -70,4 +68,5 @@ sudo ./retina_r50 -d  // deserialize model file and run inference.
 
 ## More Information
 
-See the readme in [home page.](https://github.com/wang-xinyu/tensorrtx)
+Check the readme in [home page.](https://github.com/wang-xinyu/tensorrtx)
+