sjksong

@Liu0329 @jazzsaxmafia @RutgersHan @1230pitchanqw Hello,I'm a undergraduate from Communication University Of China ,I'm currently working on this area for my graduation paper . Could you please tell me if you...

I use the author's original model （didn't change the h(t) = o(t) *  tanh(c(t)) ）after 12 epoch ,the current loss only reduced to 2.96379992 ，is it right ？the loss is...

i think the original code is right ，count represents steps