Adrian Lisko
Adrian Lisko
Thanks! The idea behind the double batchnormalization comes from the noise injection in the dirty part of the encoder, i.e. first normalize the batch by its mean and std, then...
So it turns out that something is going wrong after using scaling and bias layer instead of the second batchnormalization (which made everything smooth by normalizing the batch again). The...
> Let me point out that I was just guessing on what you were trying to achieve, so please take my advice with a grain of salt. To get things...
> Luckily, you don't have to access the mean and std used by the encoder, you can just compute them yourself. Theano will see that the expressions are equivalent and...
Hi @f0k, not yet. Although this version is working, I still need to push my latest changes. I refactored the code and fixed some pooling-layer inconsistencies with the original ladder...
@f0k I think, it's ready for merge.
You have to define it in your ssh config, there is no other way at the moment. I am dealing with the same problem, where I cannot automate docker deployment...
@AndrewKirkovski HUGE thank you for sharing the workaround.
@msaglietto Thank you, but using allowRepaint doesn't have any effect. The problem seems to be that every diagram engine function has implicit repaintCanvas, which in turn completely prevents repainting the...
@davakh unfortunately not