Dls5 week 1 assignment 3 epoch is wrong

Hello. Everytime I run my LSTM model I take different result for epoch 1 etc although in the previous section the model seems to behave ok

Moreover in exercise 2 I do not understand why my code does not run correctly

ValueError: Layer lstm_2 expects 13 inputs, but it received 3 input tensors. Inputs received: [<tf.Tensor ‘input_17:0’ shape=(None, 1, 90) dtype=float32>, <tf.Tensor ‘a0_16:0’ shape=(None, 64) dtype=float32>, <tf.Tensor ‘c0_16:0’ shape=(None, 64) dtype=float32>]

I am really stuck here

Hi @kvamvake ,

Have you found a solution to the problem? Let’s know if further help is needed.

I saw similar issue, where # of inputs expected kept increasing after each run. After restarting the kernel the problem disappeared (i hope i didn’t speak too soon since I’m still working on this part)

Hi @AndrewChan ,

The kernel can go into an inactive mode, as a result, the execution environment may not have all the values/references needed. So, it is a good habit to ensure the kernel is healthy, and rerun the code cells to bring in all the references.