jiegzhan/multi-class-text-classification-cnn-rnn

Can it work if “non_static” in parameters sets "True"?

Aurelius84 opened this issue · 0 comments

Thanks for your sharing project, and I find the "non-static" in the config.

I just find the code like this:
with open(trained_dir + 'embeddings.pickle', 'wb') as outfile:
pickle.dump(embedding_mat, outfile, pickle.HIGHEST_PROTOCOL)

"embedding_mat" is formed by np.uniform and when I train using "non-static : True", the val is changed just in model "cnn_rnn". when I save it ,it still was the val formed by np.uniform.

So, I don't know if I decript clearly. when I want to using variable embedding, it will work just set "non_static : True"?

Thank you