update readme

Author: holyseven

README.md

@@ -1,7 +1,5 @@
 [**中文**](./README_CN.md) | English
 
-![](preview.png)
-
 [![Release](https://img.shields.io/github/release/PaddlePaddle/InterpretDL.svg)](https://github.com/PaddlePaddle/InterpretDL/releases)
 [![PyPI](https://img.shields.io/pypi/v/interpretdl.svg)](https://pypi.org/project/interpretdl)
 [![CircleCI](https://circleci.com/gh/PaddlePaddle/InterpretDL.svg?style=shield)](https://circleci.com/gh/PaddlePaddle/InterpretDL)
@@ -15,6 +13,8 @@ InterpretDL, short for *interpretations of deep learning models*, is a model int
 
 *InterpretDL is under active construction and all contributions are welcome!*
 
+![](https://user-images.githubusercontent.com/13829174/159609890-bf3f2050-1ee8-482f-baac-693d280f9039.jpg)
+
 # Why InterpretDL
 
 The increasingly complicated deep learning models make it impossible for people to understand their internal workings. Interpretability of black-box models has become the research focus of many talented researchers. InterpretDL provides a collection of both classical and new algorithms for interpreting models.

README_CN.md

@@ -14,6 +14,8 @@ InterpretDL(全称*interpretations of deep learning models*), 是基于[飞桨](
 
 *InterpretDL持续更新中，欢迎所有贡献。*
 
+![](https://user-images.githubusercontent.com/13829174/159610534-316fcc73-315d-47d3-aa07-c8e4da35c94f.jpg)
+
 # 为什么选择InterpretDL
 
 随着深度学习模型的越发复杂，人们很难去理解其内部的工作原理。“黑盒”的可解释性正成为许多优秀研究者的焦点。InterpretDL不仅支持经典的可解释性算法，也对最新的可解释性算法持续更新。