Divesh Pandey

Some other modifications are also possible in CSV class. * Currently, if some CSV object holds some fixed sized rows and user wishes to append some more rows, then there...

In case of Hindi data, there are surely many 'O' entries. Fixing this is not entirely possible, as we would have to go through entire dataset, or create a new...

That image suggests that you are surely doing something wrong. How was the output when you were training the model using keras. Was valid. acc increasing steadily(at a optimum rate)...

Sorry for late replying. Were you also getting very low loss (in negative powers of 10) and NaN values during training?

The problem is version numbers. I should have made requirements.txt. I used ```Keras==1.2.1``` and ```tensorflow-gpu==0.12.1```. Though I had tensorflow with GPU support, you can avoid that by installing just ```tensorflow==0.12.1```....

I trained one model just now. Output in my case: 

Sorry I can't do that. Its not available

Sorry for late replying Can you replace the line ``` with codecs.open(datapath, 'r') as f: ``` by ``` with codecs.open(datapath, 'r', encoding='utf8') as f: ``` ? See if this works....

I hope you have all spacy data downloaded (for getting vectors). Different versions can surely be a problem. But I also faced a similar problem while I was working on...

You’re welcome @jenniferzhu I am using ```spacy==1.6.0``` currently.