update installation

README.md

@@ -84,9 +84,19 @@ We also implemented several typical riemannian optimizers. Please refer to [[4](
 
 ## How to use CurvLearn
 
-To get started with CurvLearn quickly, we provide a simple binary classification model as a quick start and three representative examples for the application demo.
+To get started with ```CurvLearn``` quickly, we provide a simple binary classification model as a quick start and three representative examples for the application demo.
 Note that the non-Euclidean model is sensitive to the hyper-parameters such as learning rate, loss functions, optimizers, and initializers. It is necessary to tune those hyper-parameters when transferring to other datasets.
 
+### Installation
+
+```CurvLearn``` requires tensorflow=1.15, compatible with both python 2/3.
+
+The preferred way for installing is via `pip`. 
+
+```bash
+pip install curvlearn
+```
+
 ### Quick Start
 
 Here we show how to build binary classification model using ```CurvLearn```. Model includes ```Stereographic``` manifold, ```linear``` operations , ```radam``` optimizer, etc.

README_CN.md

@@ -87,6 +87,16 @@
 
 值得指出的是非欧模型往往对诸如学习率、损失函数、优化器、初始化等超参数十分敏感，当迁移到新的数据集时有必要调整参数。
 
+### 安装
+
+```CurvLearn``` 依赖于Tensorflow=1.15, 与python 2/3同时保持兼容。
+
+使用推荐使用```pip```进行安装配置。
+
+```bash
+pip install curvlearn
+```
+
 ### 快速开始
 
 这里我们展示了如何利用```CurvLearn```构建简单二分类模型，包括使用```Stereographic``` 流形，```linear``` 算子，```radam``` 优化器。