Naveen Jafer

@ferasodh Hi, I was running into similar errors too. The session is initialized as follows for the Dev process. `step, summaries, loss, accuracy, precision = sess.run( [global_step, dev_summary_op, cnn.loss, cnn.accuracy,...

@j314erre The code in the train.py that you have created in your gist seems to be using the load_data_and_labels function from data_helpers, but you have not fed the path of...

Anyone who is looking to Use Multi class classification with the latest versions of tensorflow with pre-trained Word2Vec, feel free to use this consolidated fork https://github.com/naveenjafer/cnn-text-classification-tf that builds on all...

The modified code that I have used for the same is https://github.com/naveenjafer/cnn-text-classification-tf

@yoonkim Would you be able to help with this?

Hi Jagan, Yes I did manage to get a crude workaround to it, The problem lies in the fact that the new word doesnt exist in the vocab_processor that is...

Yes, that is a possibility that would work too, but since I had spent more time on the code for the train.py for modifying it for my use case of...

Hi Jagan, So in this implementation followed by denny, this is a static training where the initial word 2 vecs presented do not change with the training, so the cosine...

@honnibal The regular Relu is only a special case of the Leaky Relu where the alpha parameter is 0. So what I have done as of now, is kept the...

Hi @honnibal any update on this? Would love to complete this with all the extra time the lockdowns are giving us.