Dear Friends,
I have been working on my NLP with TensorFlow assignment and unfortunately could not manage an accuracy of 72%. Here is the structure of my function. I tried with more than 1 LSTM layers. Also played with LSTM unit numbers as well as embedding layer output dimension. Even tried a dropout layer. Here is my code. Any ideas to improve the model? :
# mentor edit: code removed
Hello everyone. I just solved my own question. I think I should delete it from as it is somehow including the answer. I just modified/reduced my learning_rate. Kind Regards. TB
It’s great that you solved your own question.
In the future, please don’t share your code on the forum. That’s not allowed by the Code of Conduct. I’ll clean up the issue in this thread.
Thanks for your reply and your reminder TMosh. I will be careful about that in the future. Kind Regards. TB