Hello, I do not understand what’s wrong with my code. Is the implementation of Y the source of error? The model is not optimizing. Please help, thanks so much.
Hi @fireping668 ,
The problem is with Y wrongly constructed. Here is the implementation notes on how to construct Y:
Set the list of labels (integer representation of the characters): Y
- The goal is to train the RNN to predict the next letter in the name, so the labels are the list of characters that are one time-step ahead of the characters in the input
X.- For example,
Y[0]contains the same value asX[1]
- For example,
- The RNN should predict a newline at the last letter, so add
ix_newlineto the end of the labels.- Append the integer representation of the newline character to the end of
Y. - Note that
appendis an in-place operation. - It might be easier for you to add two lists together.
- Append the integer representation of the newline character to the end of
How should Y be constructed? The instruction claimed that Y should be one time step ahead. How can I implement it? How could I get the X that is one step ahead and assign it for the implementation of Y? Thanks so much!
“Y” should not include the “None” character from X[0].
So Y should start from X[1:]
1 Like
Thanks so much, solved!