Vighnesh Birodkar
Vighnesh Birodkar
I think something along the lines of smaller blobs floating around the two main blobs of the scikit-learn logo would be cool
Hey, we never really managed to get this to work. If you would like to read the report on this we can send it to you via email.
Actually here it is, I just realized it is public. http://www.cs.nyu.edu/~akv245/inf/writeup.pdf
The results there were from the Yelp Review dataset.
There is already code to pre-process the yelp review dataset and train with it. Let us know if you have any trouble.
I just notices that your dataset size is 100. You should really be training with the whole Yelp dataset
Because it just hasn't seen enough data to learn anything useful.
The repo is exactly what we used in the report. Over-fitting won't work like that in this case because generation is done using beam search. Let me see if I...
I don't really have a solution right now. Just gathering data. When we the result of `cut_normalized` is different, can we see what 2 different results look like ? This...
@jni, a `pyx` file is to be compiled into C code and eventually an `.so` or `.dll` file. A `pxi` is analogous to the C `#include` directive, it will simply...