TF

Suggest to use pyinstrument to benchmark You’ll see which functionalities to de-activate by default. > On Apr 2, 2021, at 23:53, No Ke ***@***.***> wrote: > >  > Ok,...

Sorry, am too busy... Check my profile and count the number of commits done.... It takes 5 lines of code Random dataset numpy random: 10000 rows x 50cols run pandas...

Because having a large number of files on disk, is not good for disk performance.... ( 300k files x 1000 ). Is it a way than to encapsulate the folder...

Hi, Still showing error for umap-learn==0.5.1 should we use dense for .transform ? .fit works well with sparse

Exactly: Either concat, or Mean We need to pass the gradient and end to end training > On Feb 23, 2022, at 16:19, Yi-Xuan Xu ***@***.***> wrote: > > ...

N1, N2,Nx are different NN models. We aggregate through concat their embedding output. BigX = [ X1,….Xn] and feed into another NN (ie merging). This extensively used (ie Siamese Network…)...

We are NOT dealing with output !!! Output is kind of useless for End to End training… We are dealing witht the last embedding. > On Feb 24, 2022, at...

Sure. At 1st version, Maybe, we can use same optimizer, scheduler for the ensemble model Goal is to have a one liner for easy Ensemble End to End. > On...

1) Yes, that is the core of the question. grouping message based on contents. And post process the grouping messages. Usually, latency come from post-processing the messages (database access).

Hello, Sounds good. What about having Python wrapper to use the library ? PyGMO uses Python wrapper to encapsulate the C code. So this is very convenient. Your project looks...