DLS 5 - Week 1 - A1 - Build you own RNN. Getting wrong output

Course Q&A Deep Learning Specialization Sequence Models
1

In the evaluation cells for rnn_backward and lstm_backward, my code returns wrong gradients. All gradient values are 0 for some reason I could not debug. Please help.

2

Please click my name and message your notebook as an attachment.

3

Here are some hints:

  1. Inside def rnn_backward(da, caches):, gradients = ... needs to be fixed.
  2. One you fix the above bug, fixing gradients = in def lstm_backward(da, caches): is straight forward.
4

Thanks, I figured it out. I was feeding in the wrong value of the da_next to the function.