OmarMAmin

Any one found a solution? I'm still getting blank answers

I'm also interested in this question, please if any one can help that would be great, can we set Vatic locally on a local network and collaborate locally in the...

I'm having an issue trying to run the offline-mode. I want to run vatic on my personal pc, but i'm stuck in a small issue after "turkic status --verify" i...

Thank you so much, it fixes the issue, i got the following: Localhost: http://localhost Testing access to Amazon Mechanical Turk... ERROR! Signature or access key missing Testing access to database...

the problem in the file CompressiveTrackerModule.cpp in vatictracking folder you need to change string into std::string and it'll compile with you please let me know if you managed to get...

Hi @patrickorlando Is it possible to use label smoothing with the CrossCategoricalEntropy with the remove_accidental_hits? as setting it to large negative value, will result in some gradient if it happens...

Thanks @deychak for your contribution (Y)

@josealbertof did you have any performance improvement for label smoothing? as i believe it particularly suitable for recommendations (we don't know the GT)

@leoniloris @zhifeng-huang I believe this is some sort of overfitting, the model tried to memorize training examples, but wasn't able to generalize well to the validation ones, I believe this...

@maciejkula Any references about results comparing different negative sampling strategies --> i.e. in-batch, cross-batch, random ... etc As far as I understand the `sample_weight` can be used to model recency...