Haowen Xu
Haowen Xu
The reconstruction probability $E_{q(z|x)}[p(x|z)]$ of the last points of every windows of the input test values.
As mentioned in the paper, we always use the scores of the last points of every windows. It seems that your window size is 20, and thus the first score...
Would you please give more hints about your scenario? For example, the core code of how you use Donut?
The VariableSaver (and also tf.train.Saver) may actually create new graph nodes. So you'd better use a shared VariableSaver instead of creating a new one each time you restore the model....
Unfortunately I'm not the author of ZhuSuan. You may consult @thjashin, or open a pull request to fix this memory leak. Another choice is to switch to newer versions (>=v0.1.2)...
I have upgraded the dependency to `v0.1.2` and it passes unit tests. You may have a try. But I'll not port Donut to tfsnippet >= v0.2, because the design philosophy...
你可以试试 develop 分支