Daksh Varshneya
Daksh Varshneya
Exalate commented: dakshvar22 commented: @pksvv You can still use a community hosted model like [this](https://github.com/davidalami/ConveRT/releases/download/1.0/nocontext_tf_model.tar.gz). Just pass the link as value for `model_url` option of `ConveRTFeaturizer`.
Status: Even with the above changes, the model training is not deterministic. Will need to try a different approach to first determine what's the first point of non-determinism in the...
Hey @b-quachtran Apologies for the delay in response. As far as I can see, we haven't shared the benchmarking numbers on GPU with them. Our contractor Markus was leading that...
Hi @scharnk, Yes default params seem to be off for some reason. Have you been able to reproduce the pre-trained models?
Hi @yosh7 , were you able to re-produce the pre-trained models?
Can you tell the version of tensorflow you used? On Mon, Jul 6, 2020, 13:49 yosh7 wrote: > Yep. I installed everything from scratch, Linux, cuda, cudnn (this one's >...
@yosh7 I think just the import won't be enough as I am running into some other errors as well when I upgrade to TF 2.2 .Would you be able to...
@rafaelvalle Can we expect command line options to be added to `inference.py` from your side to accomplish this kind of style transfer?
> I think the reason for these problems is that, for a long time after the big e2e refactor, TensorBoard didn't really work with rasa, so we couldn't test things...
> On top of that, the DPLL does not sample uniquely, so it might sample the same labels multiple times. Maybe better to replace the sampling inside the loss with...