# What is VAE?

VAE is short for Variational Auto-Encoder which is proposed by Kingma et al. in Auto-Encoding Variational Bayes. It extends the Variational Bayesian (VB) method by deriving a tractable lower bound and a reparameterization trick that allows the bound to be optimized using stochastic gradient updating.

# 服务器端

$jupyter notebook --generate-config  ## 2.生成登录密码 进入ipython from notebook.auth import passwd passwd()  会生成一个密钥’sha1…’ 复制下来. ## 3.修改配置文件 c.NotebookApp.ip='localhost' 设置本地端口可访问 c.NotebookApp.password = u'sha:ce...刚才复制的那个密文' c.NotebookApp.open_browser = False # 禁止自动打开浏览器 c.NotebookApp.port =8888 #随便指定一个端口  ## 4.启动jupyter notebook $ jupyter notebook


# 本地端

## 1.端口映射

*为了更方便使用,在使用ssh登录服务器时进行端口映射

ssh user@remote_server_ip -L 1024 127.0.0.1:8888


# conda proxyerror 解决办法

CondaHTTPError: HTTP 000 CONNECTION FAILED for url <https://repo.continuum.io/pkgs/free/linux-64/repodata.json.bz2>
Elapsed: -

An HTTP error occurred when trying to retrieve this URL.
HTTP errors are often intermittent, and a simple retry will get you on your way.
ConnectionError...


set NO_PROXY=continuum.io,anaconda.org