Hello,
Is it possible to check somewhere the function “rnn_forward” also with “loss” output?
I supose that the implementation in the first exercise is without “loss” and in the second excercise the ‘‘loss’’ appears as output.
Thank you.
Jiri
If you’d like to see the source for the rnn_forward function used in the Dinosaurus Island exercise, just click “File → Open” from that notebook and have a look around. You can tell the name of the file to open by examining the “import” cell, which is the first code cell in the notebook. There’s a general topic about this on the FAQ Thread FWIW …
1 Like