Jindra Helcl

+1

For example this one: https://arxiv.org/abs/1609.08144

The Edinburgh paper on deep architectures just came out today: https://arxiv.org/abs/1707.07631

No, nor we are planning to right now. You can contribute if you want :)

Hi, please also note that increasing batch size for inference likely won't bring any time improvements on CPUs. Moreover, as far as I know, other toolkits don't provide this feature...

Hi, first, you need to run `bin/neuralmonkey-train tests/vocab.ini` so the vocabulary is created.

That depends - it needs to be done consistently. From model part point of view, we need to either apply dropout on the output or after fetching the input. I...

Hi, the examples from the tutorials are outdated. If you leave the `runners_batch_size` parameter, it should work fine. You can refer to `tests/*.ini` for working examples of configuration files.

Takže #796 je na #786 a tohle je na obojím? :-)

Vypadá to, že je to špatně narebasovaný, protože se jako součást ukazuje tvuj PR (#818) řešící to, co jsem udělal v #819