Course 4 week 2 assignment 1 exercise 2

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I’m getting stuck on the assert function assert np.allclose(A.numpy(), convolutional_block_output1), “Wrong values when training=False.”

I got the error message. As per instruction, each block contains in the norm function contain the training = training part.

I’m a bit confused on how to fix the code

2

Hey @Massimo_Esposito,
Can you please post the entire traceback of the error that you received here?

Cheers,
Elemento

3

Cattura
Cattura1114×206 15.6 KB

here you go @Elemento

4

Hey @Massimo_Esposito,

If you have ensured this, then I believe there is some issue with your implementation for the convolutional_block function. Can you please DM your code for the same to me?

Cheers,
Elemento

5

If you got the handling of the training parameter correct, the other common mistake is not to pass the correct input value to the “shortcut” step. The instructions don’t really talk much about that, but the picture of what happens is pretty clear in the diagrams in this section. The “shortcut” logic is a pretty big deal here. :nerd_face:

6

I got it! Your tip was too good!