Abhishek Kandoi

Just checked. Stanford CoreNLP requires a minimum of 3GB of RAM as it works on a huge dataset. So I guess we cannot use heroku free tier(512MB max). Since we...

@jayant1992 1. I did check the Python wrapper and tried to contact the repo owner about memory requirements. Unfortunately, the **wrapper doesn't support Sentiment Analysis**. 2. Conducted a few tests...

As @khare_ashwini said, we are currently using the Python API for Google Datastore. Since its internal working doesn't support `LIKE` queries(for performance reasons), we had to rely on single result...

What is the status on the new design/architecture?

Is someone working on this?

I have committed the changes in the pull request #182 Will you please check this out and let me know if something has to be changed

Is there any chance that I could use this for blind deconvolution of audio signal mixtures?

I have samples of audio recording from two microphones separated by some distance. There are two simultaneous speakers. Basically a convolutive mixture of two sound sources. Another example of such...

It seems the function is only defined and never used. How did you guys use this loss function? We are trying to reproduce your results @talsperre