Porting RU model to Java

Dear developers,

First of all I would like to say thank you for your job. The results for Russian language looks impressive.

May be this is a strange question - but is it possible to port your models to Java? For example for usage with deeplearning4j? Or this is restricted by License?

Thanks in advance

Hi @ashg,

We do not have such plans ourselves but anyone is welcome to try if they want.
DeepPavlov is licensed under the Apache License 2.0

Thanks for your quick response.

Actually, I have made several experiments and got some issues (may be because I’m newbie in this NN area).

  1. Using Python Keras I was able to convert ru-bert model to H5 and .PB formats

  2. Unfortunately, when I tried to load .hdf5 format to Deeplearning4j (easiest way) I have got an error related to the hard coded path to c++ file on someone’s local drive. Guess that this is a deeplearning4j lib error with JNI code.

  3. After that I was able to convert hdf5 to .pb and this model was loaded to deeplearning4j.

Unfortunately due to some reasons output layer was empty and I have set it as “Encoder-12-FeedForward-Norm/add_1”.
Also I have adapted tokenization as it done in your framework.

The result is the crushed JVM.

May be I will have some questions about layers usage.

Regards,
ashg

Hi @ashg

I would be very interested to help porting DeepPavlov to Java.
Let me know in case I can help somehow in case you make your code available.

Thanks

Michael