maxtri

I meet a similarity problem. my system is redhat7 ,my GPU is K80 in Azure .my cuda is cuda8. my error is NVIDIA-SMI has failed because it couldn't communicate with...

@rizkyario sorry for my simple. Details as follows: Azure's Linux system lacks a lot of basic packages. My solution is one by one to install those packages I need before...

> 嗯，同样发现了这个问题，KL散度的公式里期望前面应该加个exp。 第9页的KL 散度 的期望前面不需要添加exp吧, 因为这个公式直接根据上一行的L(qj) 紧扣KL 定义得到的

> pdf第九页将ELOB改写成KL散度时应该是qi(Zi)和那个伪分布p(X,Z)之间的KL散度吧，所以之后的迭代公式里更新的是ln(qj(zj))而不是qj(zj) “pdf第九页将ELOB改写成KL散度时应该是qi(Zi)和那个伪分布p(X,Z)之间的KL散度吧” 为什么是qi(zi), 我理解 qi(zi)在第9页第一个 公式中被积没了。

check your python version, it should be use python2

if you use ananconda , you can install opencv by conda: conda install opencv